Release: 0.5.3 (#599)

* release: 0.5.3, add extra linting rule and minor fix for EndpointDialog

* chore: revert to deprecated Message Classes as weird behavior seen in linux

* chore(api): remove unused test scripts
chore(package.json): remove unused langchain dependency

* chore(.gitignore): add /images directory to the ignore list

.devcontainer/devcontainer.json

@@ -0,0 +1,57 @@
+// {
+// 	"name": "LibreChat_dev",
+// 	// Update the 'dockerComposeFile' list if you have more compose files or use different names.
+// 	"dockerComposeFile": "docker-compose.yml",
+// 	// The 'service' property is the name of the service for the container that VS Code should
+// 	// use. Update this value and .devcontainer/docker-compose.yml to the real service name.
+// 	"service": "librechat",
+// 	// The 'workspaceFolder' property is the path VS Code should open by default when
+// 	// connected. Corresponds to a volume mount in .devcontainer/docker-compose.yml
+// 	"workspaceFolder": "/workspace"
+//     //,
+// 	// // Set *default* container specific settings.json values on container create.
+// 	// "settings": {},
+// 	// // Add the IDs of extensions you want installed when the container is created.
+// 	// "extensions": [],
+// 	// Uncomment the next line if you want to keep your containers running after VS Code shuts down.
+// 	// "shutdownAction": "none",
+// 	// Uncomment the next line to use 'postCreateCommand' to run commands after the container is created.
+// 	// "postCreateCommand": "uname -a",
+// 	// Comment out to connect as root instead. To add a non-root user, see: https://aka.ms/vscode-remote/containers/non-root.
+// 	// "remoteUser": "vscode"
+// }
+{
+    // "name": "LibreChat_dev",
+    "dockerComposeFile": "docker-compose.yml",
+    "service": "app",
+    // "image": "node:19-alpine",
+    // "workspaceFolder": "/workspaces",
+    "workspaceFolder": "/workspace",
+    // Set *default* container specific settings.json values on container create.
+    // "overrideCommand": true,
+    "customizations": {
+        "vscode": {
+            "extensions": [],
+            "settings": {
+                "terminal.integrated.profiles.linux": {
+                    "bash": null
+                }
+            }
+        }
+    },
+    "postCreateCommand": ""
+    // "workspaceMount": "src=${localWorkspaceFolder},dst=/code,type=bind,consistency=cached"
+
+    // "runArgs": [
+    //     "--cap-add=SYS_PTRACE", "--security-opt", "seccomp=unconfined",
+    //     "-v", "/tmp/.X11-unix:/tmp/.X11-unix",
+    //     "-v", "${env:XAUTHORITY}:/root/.Xauthority:rw",
+    //     "-v", "/home/${env:USER}/.cdh:/root/.cdh",
+    //     "-e", "DISPLAY=${env:DISPLAY}",
+    //     "--name=tgw_assistant_backend_dev",
+    //     "--network=host"
+    // ],
+    // "settings": {
+    //     "terminal.integrated.shell.linux": "/bin/bash"
+    // },
+}

.devcontainer/docker-compose.yml

@@ -0,0 +1,76 @@
+version: '3.4'
+
+services:
+  app:
+    # container_name: LibreChat_dev
+    image: node:19-alpine
+    # Using a Dockerfile is optional, but included for completeness.
+    # build: 
+    #   context: .
+    #   dockerfile: Dockerfile
+    #   # [Optional] You can use build args to set options. e.g. 'VARIANT' below affects the image in the Dockerfile
+    #   args: 
+    #     VARIANT: buster
+    network_mode: "host"
+    # ports:
+    #   - 3080:3080               # Change it to 9000:3080 to use nginx
+    extra_hosts: # if you are running APIs on docker you need access to, you will need to uncomment this line and next
+    - "host.docker.internal:host-gateway"
+
+    volumes:
+    #   # This is where VS Code should expect to find your project's source code and the value of "workspaceFolder" in .devcontainer/devcontainer.json
+      - ..:/workspace:cached
+    #   # - /app/client/node_modules
+    #   # - ./api:/app/api
+    #   # - ./.env:/app/.env
+    #   # - ./.env.development:/app/.env.development
+    #   # - ./.env.production:/app/.env.production
+    #   # - /app/api/node_modules
+
+    #   # Uncomment the next line to use Docker from inside the container. See https://aka.ms/vscode-remote/samples/docker-from-docker-compose for details.
+    #   # - /var/run/docker.sock:/var/run/docker.sock 
+
+    # Runs app on the same network as the service container, allows "forwardPorts" in devcontainer.json function.
+    # network_mode: service:another-service
+    
+    # Use "forwardPorts" in **devcontainer.json** to forward an app port locally. 
+    # (Adding the "ports" property to this file will not forward from a Codespace.)
+
+    # Uncomment the next line to use a non-root user for all processes - See https://aka.ms/vscode-remote/containers/non-root for details.
+    # user: vscode
+
+    # Uncomment the next four lines if you will use a ptrace-based debugger like C++, Go, and Rust.
+    # cap_add:
+    #   - SYS_PTRACE
+    # security_opt:
+    #   - seccomp:unconfined
+
+    # Overrides default command so things don't shut down after the process ends.
+    command: /bin/sh -c "while sleep 1000; do :; done"  
+
+  mongodb:
+    container_name: chat-mongodb
+    network_mode: "host"
+    # ports:
+    #   - 27018:27017
+    image: mongo
+  #   restart: always
+    volumes:
+      - ./data-node:/data/db
+    command: mongod --noauth
+  meilisearch:
+    container_name: chat-meilisearch
+    image: getmeili/meilisearch:v1.0
+    network_mode: "host"
+    # ports:
+    #   - 7700:7700
+    # env_file:
+    #   - .env
+    environment:
+      - SEARCH=false
+      - MEILI_HOST=http://0.0.0.0:7700
+      - MEILI_HTTP_ADDR=0.0.0.0:7700
+      - MEILI_MASTER_KEY=5c71cf56d672d009e36070b5bc5e47b743535ae55c818ae3b735bb6ebfb4ba63
+    volumes:
+      - ./meili_data:/meili_data
+  

.dockerignore

@@ -1,4 +1,5 @@
 **/node_modules
-api/.env
+client/dist/images
+data-node
 .env
-client/dist/images
+**/.env

.env.example

@@ -2,6 +2,8 @@
 # Server configuration: 
 ##########################
 
+APP_TITLE=LibreChat
+
 # The server will listen to localhost:3080 by default. You can change the target IP as you want. 
 # If you want to make this server available externally, for example to share the server with others 
 # or expose this from a Docker container, set host to 0.0.0.0 or your external IP interface. 
@@ -16,7 +18,7 @@ PORT=3080
 # PROXY=
 
 # Change this to your MongoDB URI if different. I recommend appending LibreChat. 
-MONGO_URI=mongodb://127.0.0.1:27017/LibreChat
+MONGO_URI=mongodb://127.0.0.1:27018/LibreChat
 
 ##########################
 # OpenAI Endpoint: 
@@ -25,12 +27,12 @@ MONGO_URI=mongodb://127.0.0.1:27017/LibreChat
 # Access key from OpenAI platform. 
 # Leave it blank to disable this feature.
 # Set to "user_provided" to allow the user to provide their API key from the UI.
-OPENAI_API_KEY=user_provided
+OPENAI_API_KEY="user_provided"
 
 # Identify the available models, separated by commas *without spaces*. 
 # The first will be default. 
 # Leave it blank to use internal settings. 
-OPENAI_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-0301,text-davinci-003,gpt-4,gpt-4-0314
+OPENAI_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-16k,gpt-3.5-turbo-0301,text-davinci-003,gpt-4,gpt-4-0314,gpt-4-0613
 
 # Reverse proxy settings for OpenAI: 
 # https://github.com/waylaidwanderer/node-chatgpt-api#using-a-reverse-proxy 
@@ -47,13 +49,24 @@ OPENAI_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-0301,text-davinci-003,gpt-4,gpt-4-0314
 # Note: I've noticed that the Azure API is much faster than the OpenAI API, so the streaming looks almost instantaneous.
 # Note "AZURE_OPENAI_API_COMPLETIONS_DEPLOYMENT_NAME" and "AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME" are optional but might be used in the future
 
-# AZURE_OPENAI_API_KEY=
+# AZURE_API_KEY=
 # AZURE_OPENAI_API_INSTANCE_NAME=
 # AZURE_OPENAI_API_DEPLOYMENT_NAME=
 # AZURE_OPENAI_API_VERSION=
 # AZURE_OPENAI_API_COMPLETIONS_DEPLOYMENT_NAME=
 # AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME=
 
+# Identify the available models, separated by commas *without spaces*. 
+# The first will be default. 
+# Leave it blank to use internal settings. 
+AZURE_OPENAI_MODELS=gpt-3.5-turbo,gpt-4
+
+# To use Azure with the Plugins endpoint, you need the variables above, and uncomment the following variable:
+# NOTE: This may not work as expected and Azure OpenAI may not support OpenAI Functions yet
+# Omit/leave it commented to use the default OpenAI API
+
+# PLUGINS_USE_AZURE="true"
+
 ##########################
 # BingAI Endpoint:   
 ##########################
@@ -98,6 +111,11 @@ CHATGPT_MODELS=text-davinci-002-render-sha,gpt-4
 # Plugins:
 #############################
 
+# Identify the available models, separated by commas *without spaces*. 
+# The first will be default. 
+# Leave it blank to use internal settings. 
+PLUGIN_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-16k,gpt-3.5-turbo-0301,gpt-4,gpt-4-0314,gpt-4-0613
+
 # For securely storing credentials, you need a fixed key and IV. You can set them here for prod and dev environments
 # If you don't set them, the app will crash on startup.
 # You need a 32-byte key (64 characters in hex) and 16-byte IV (32 characters in hex)
@@ -109,13 +127,15 @@ CREDS_IV=e2341419ec3dd3d19b13a1a87fafcbfb
 
 # AI-Assisted Google Search  
 # This bot supports searching google for answers to your questions with assistance from GPT! 
-# See detailed instructions here: https://github.com/danny-avila/chatgpt-clone/blob/main/docs/features/plugins/google_search.md
+# See detailed instructions here: https://github.com/danny-avila/LibreChat/blob/main/docs/features/plugins/google_search.md
 GOOGLE_API_KEY=
 GOOGLE_CSE_ID=
 
 # StableDiffusion WebUI
 # This bot supports StableDiffusion WebUI, using it's API to generated requested images.
-SD_WEBUI_URL=http://0.0.0.0:7860
+# See detailed instructions here: https://github.com/danny-avila/LibreChat/blob/main/docs/features/plugins/stable_diffusion.md
+# Use "http://127.0.0.1:7860" with local install and "http://host.docker.internal:7860" for docker
+SD_WEBUI_URL=http://host.docker.internal:7860
 
 ##########################
 # PaLM (Google) Endpoint: 
@@ -142,7 +162,7 @@ PROXY=
 # ENABLING SEARCH MESSAGES/CONVOS 
 # Requires the installation of the free self-hosted Meilisearch or a paid Remote Plan (Remote not tested) 
 # The easiest setup for this is through docker-compose, which takes care of it for you. 
-SEARCH=false
+SEARCH=true
 
 # REQUIRED FOR SEARCH: MeiliSearch Host, mainly for the API server to connect to the search server. 
 # Replace '0.0.0.0' with 'meilisearch' if serving MeiliSearch with docker-compose. 
@@ -164,6 +184,9 @@ MEILI_MASTER_KEY=DrhYf7zENyR6AlUCKmnz0eYASOQdl6zxH7s7MKFSfFCt
 # User System:
 ##########################
 
+# Allow Public Registration
+ALLOW_REGISTRATION=true
+
 # JWT Secrets
 JWT_SECRET=secret
 JWT_REFRESH_SECRET=secret
@@ -175,32 +198,42 @@ GOOGLE_CLIENT_ID=
 GOOGLE_CLIENT_SECRET=
 GOOGLE_CALLBACK_URL=/oauth/google/callback
 
+# OpenID:
+# See OpenID provider to get the below values
+# Create random string for OPENID_SESSION_SECRET
+# For Azure AD
+#   ISSUER:  https://login.microsoftonline.com/(tenant id)/v2.0/
+#   SCOPE:   openid profile email
+OPENID_CLIENT_ID=
+OPENID_CLIENT_SECRET=
+OPENID_ISSUER=
+OPENID_SESSION_SECRET=
+OPENID_SCOPE="openid profile email"
+OPENID_CALLBACK_URL=/oauth/openid/callback
+# If LABEL and URL are left empty, then the default OpenID label and logo are used.
+OPENID_BUTTON_LABEL=
+OPENID_IMAGE_URL=
+
 # Set the expiration delay for the secure cookie with the JWT token
 # Delay is in millisecond e.g. 7 days is 1000*60*60*24*7
 SESSION_EXPIRY=(1000 * 60 * 60 * 24) * 7
 
+# Github:
+# Get the Client ID and Secret from your Github Application
+# Add your Github Client ID and Client Secret here:
+
+GITHUB_CLIENT_ID=
+GITHUB_CLIENT_SECRET=
+GITHUB_CALLBACK_URL=/oauth/github/callback
+
 ###########################
 # Application Domains
 ###########################
 
-# Note: server = backend, client = public (the client is the url you visit)
-# For the google login to work in dev mode, you will likely need to change DOMAIN_SERVER to localhost:3090 or place it in .env.development
+# Note: 
+# Server = Backend 
+# Client = Public (the client is the url you visit)
+# For the Google login to work in dev mode, you will need to change DOMAIN_SERVER to localhost:3090 or place it in .env.development
 
 DOMAIN_CLIENT=http://localhost:3080
 DOMAIN_SERVER=http://localhost:3080
-
-###########################
-# Frontend Configuration (Vite):
-###########################
-
-# Custom app name, this text will be displayed in the landing page and the footer.
-VITE_APP_TITLE="LibreChat"
-
-# Enable Social Login
-# This enables/disables the Login with Google button on the login page.
-# Set to true if you have registered the app with google cloud services 
-# and have set the GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET above
-VITE_SHOW_GOOGLE_LOGIN_OPTION=false
-
-# Allow Public Registration
-ALLOW_REGISTRATION=true

.eslintrc.js

@@ -10,7 +10,7 @@ module.exports = {
     'eslint:recommended',
     'plugin:react/recommended',
     'plugin:react-hooks/recommended',
-    "plugin:jest/recommended",
+    'plugin:jest/recommended',
     'prettier'
   ],
   parser: '@typescript-eslint/parser',
@@ -24,34 +24,32 @@ module.exports = {
   plugins: ['react', 'react-hooks', '@typescript-eslint'],
   rules: {
     'react/react-in-jsx-scope': 'off',
-    '@typescript-eslint/ban-ts-comment': ['error', { 'ts-ignore': 'allow-with-description' }],
+    '@typescript-eslint/ban-ts-comment': ['error', { 'ts-ignore': 'allow' }],
     indent: ['error', 2, { SwitchCase: 1 }],
     'max-len': [
       'error',
       {
-        code: 150,
+        code: 120,
         ignoreStrings: true,
         ignoreTemplateLiterals: true,
         ignoreComments: true
       }
     ],
     'linebreak-style': 0,
+    'object-curly-spacing': ['error', 'always'],
+    'no-trailing-spaces': 'error',
+    'no-multiple-empty-lines': ['error', { 'max': 1 }],
     // "arrow-parens": [2, "as-needed", { requireForBlockBody: true }],
     // 'no-plusplus': ['error', { allowForLoopAfterthoughts: true }],
     'no-console': 'off',
     'import/extensions': 'off',
-    'no-use-before-define': [
-      'error',
-      {
-        functions: false
-      }
-    ],
     'no-promise-executor-return': 'off',
     'no-param-reassign': 'off',
     'no-continue': 'off',
     'no-restricted-syntax': 'off',
     'react/prop-types': ['off'],
-    'react/display-name': ['off']
+    'react/display-name': ['off'],
+    'quotes': ['error', 'single'],
   },
   overrides: [
     {
@@ -101,6 +99,18 @@ module.exports = {
         'plugin:@typescript-eslint/eslint-recommended',
         'plugin:@typescript-eslint/recommended'
       ]
+    },
+    {
+      files: './packages/data-provider/**/*.ts',
+      overrides: [
+        {
+          files: '**/*.ts',
+          parser: '@typescript-eslint/parser',
+          parserOptions: {
+            project: './packages/data-provider/tsconfig.json'
+          }
+        }
+      ]
     }
   ],
   settings: {

.github/ISSUE_TEMPLATE/BUG-REPORT.yml

@@ -58,7 +58,7 @@ body:
     id: terms
     attributes:
       label: Code of Conduct
-      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/chatgpt-clone/blob/main/documents/contributions/code_of_conduct.md)
+      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/CODE_OF_CONDUCT.md)
       options:
         - label: I agree to follow this project's Code of Conduct
           required: true

.github/ISSUE_TEMPLATE/FEATURE-REQUEST.yml

@@ -51,7 +51,7 @@ body:
     id: terms
     attributes:
       label: Code of Conduct
-      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/chatgpt-clone/blob/main/documents/contributions/code_of_conduct.md)
+      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/CODE_OF_CONDUCT.md)
       options:
         - label: I agree to follow this project's Code of Conduct
           required: true

.github/ISSUE_TEMPLATE/QUESTION.yml

@@ -52,7 +52,7 @@ body:
     id: terms
     attributes:
       label: Code of Conduct
-      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/chatgpt-clone/blob/main/documents/contributions/code_of_conduct.md)
+      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/CODE_OF_CONDUCT.md)
       options:
         - label: I agree to follow this project's Code of Conduct
           required: true

.github/workflows/backend-review.yml

@@ -1,10 +1,15 @@
-
 name: Backend Unit Tests
 on:
   push:
-    branches: [feat/playwright-jest-cicd]
+    branches:
+      - main
+      - dev
+      - release/*
   pull_request:
-    branches: [ feat/playwright-jest-cicd ]
+    branches:
+      - main
+      - dev
+      - release/*
 jobs:
   tests_Backend:
     name: Run Backend unit tests
@@ -25,10 +30,10 @@ jobs:
           cache: 'npm'
 
       - name: Install dependencies
-        run: npm ci --ignore-scripts
+        run: npm ci
 
       # - name: Install Linux X64 Sharp
-      #   run: npm install --platform=linux --arch=x64 --verbose sharp 
+      #   run: npm install --platform=linux --arch=x64 --verbose sharp
 
       - name: Run unit tests
-        run: cd api && npm run test:ci
+        run: cd api && npm run test:ci

.github/workflows/container.yml

@@ -0,0 +1,47 @@
+name: Docker Compose Build on Tag
+
+# The workflow is triggered when a tag is pushed
+on:
+  push:
+    tags:
+      - "*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      # Check out the repository
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      # Set up Docker
+      - name: Set up Docker
+        uses: docker/setup-buildx-action@v1
+
+      # Log in to GitHub Container Registry
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Run docker-compose build
+      - name: Build Docker images
+        run: |
+          cp .env.example .env
+          docker-compose build
+
+      # Get Tag Name
+      - name: Get Tag Name
+        id: tag_name
+        run: echo "TAG_NAME=${GITHUB_REF/refs\/tags\//}" >> $GITHUB_ENV
+
+      # Tag it properly before push to github
+      - name: tag image and push
+        run: |
+          docker tag librechat:latest ghcr.io/${{ github.repository_owner }}/librechat:${{ env.TAG_NAME }}
+          docker push ghcr.io/${{ github.repository_owner }}/librechat:${{ env.TAG_NAME }}
+          docker tag librechat:latest ghcr.io/${{ github.repository_owner }}/librechat:latest
+          docker push ghcr.io/${{ github.repository_owner }}/librechat:latest

.github/workflows/frontend-review.yml

@@ -2,9 +2,15 @@
 name: Frontend Unit Tests
 on:
   push:
-    branches: [main, dev]
+    branches: 
+      - main
+      - dev
+      - release/*
   pull_request:
-    branches: [main, dev]
+    branches: 
+      - main
+      - dev
+      - release/*
 jobs:
   tests_frontend:
     name: Run frontend unit tests
@@ -19,10 +25,10 @@ jobs:
           cache: 'npm'
 
       - name: Install dependencies
-        run: npm ci --ignore-scripts
+        run: npm ci
 
       - name: Build Client
-        run: cd client && npm run build:ci
+        run: npm run frontend:ci
 
       - name: Run unit tests
         run: cd client && npm run test:ci

.github/workflows/mkdocs.yaml

@@ -0,0 +1,24 @@
+name: mkdocs
+on:
+  push:
+    branches:
+      - main
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: 3.x
+      - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV 
+      - uses: actions/cache@v3
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
+      - run: pip install mkdocs-material 
+      - run: mkdocs gh-deploy --force

.gitignore

@@ -39,6 +39,7 @@ meili_data/
 api/node_modules/
 client/node_modules/
 bower_components/
+types/
 
 # Floobits
 .floo
@@ -48,10 +49,9 @@ bower_components/
 
 # Environment
 .npmrc
-.env
-!.env.example
-!.env.test.example
 .env*
+!**/.env.example
+!**/.env.test.example
 cache.json
 api/data/
 owner.yml
@@ -66,10 +66,13 @@ src/style - official.css
 .idea
 *.pem
 config.local.ts
-storageState.json
+**/storageState.json
 junit.xml
 
 # meilisearch
 meilisearch
 data.ms/*
 auth.json
+
+/packages/ux-shared/
+/images

Dockerfile

@@ -1,18 +1,14 @@
 # Base node image
 FROM node:19-alpine AS node
+
+# Install curl for health check
+RUN apk --no-cache add curl
+
 COPY . /app
 # Install dependencies
 WORKDIR /app
 RUN npm ci
 
-# Frontend variables as build args
-ARG VITE_APP_TITLE
-ARG VITE_SHOW_GOOGLE_LOGIN_OPTION
-
-# You will need to add your VITE variables to the docker-compose file
-ENV VITE_APP_TITLE=$VITE_APP_TITLE
-ENV VITE_SHOW_GOOGLE_LOGIN_OPTION=$VITE_SHOW_GOOGLE_LOGIN_OPTION
-
 # React client build
 ENV NODE_OPTIONS="--max-old-space-size=2048"
 RUN npm run frontend

README.md

@@ -1,19 +1,28 @@
 <p align="center">
-  <a href="https://discord.gg/NGaa9RPCft">
-    <picture>
-      <source media="(prefers-color-scheme: dark)" srcset="https://user-images.githubusercontent.com/110412045/228325485-9d3e618f-a980-44fe-89e9-d6d39164680e.png">
-      <img src="https://user-images.githubusercontent.com/110412045/228325485-9d3e618f-a980-44fe-89e9-d6d39164680e.png" height="128">
-    </picture>
+  <a href="https://docs.librechat.ai">
+    <img src="docs/assets/LibreChat.svg" height="256">
+  </a>
+  <a href="https://docs.librechat.ai">
     <h1 align="center">LibreChat</h1>
   </a>
 </p>
 
 <p align="center">
   <a href="https://discord.gg/NGaa9RPCft"> 
-    <img src="https://img.shields.io/discord/1086345563026489514?label=&logo=discord&style=for-the-badge&logoWidth=20&labelColor=000000&color=blueviolet">
+    <img
+      src="https://img.shields.io/discord/1086345563026489514?label=&logo=discord&style=for-the-badge&logoWidth=20&logoColor=white&labelColor=000000&color=blueviolet">
+  </a>
+  <a href="https://www.youtube.com/@LibreChat"> 
+    <img
+      src="https://img.shields.io/badge/YOUTUBE-red.svg?style=for-the-badge&logo=youtube&logoColor=white&labelColor=000000&logoWidth=20">
+  </a>
+  <a href="https://docs.librechat.ai"> 
+    <img
+      src="https://img.shields.io/badge/DOCS-blue.svg?style=for-the-badge&logo=read-the-docs&logoColor=white&labelColor=000000&logoWidth=20">
   </a>
   <a aria-label="Sponsors" href="#sponsors">
-    <img alt="" src="https://img.shields.io/badge/SPONSORS-brightgreen.svg?style=for-the-badge&labelColor=000000&logoWidth=20">
+    <img
+      src="https://img.shields.io/badge/SPONSORS-brightgreen.svg?style=for-the-badge&logo=github-sponsors&logoColor=white&labelColor=000000&logoWidth=20">
   </a>
 </p>
 
@@ -22,47 +31,26 @@ LibreChat brings together the future of assistant AIs with the revolutionary tec
 
 With LibreChat, you no longer need to opt for ChatGPT Plus and can instead use free or pay-per-call APIs. We welcome contributions, cloning, and forking to enhance the capabilities of this advanced chatbot platform.
   
-<!--   ![clone3](https://user-images.githubusercontent.com/110412045/230538752-9b99dc6e-cd02-483a-bff0-6c6e780fa7ae.gif) -->
 https://github.com/danny-avila/LibreChat/assets/110412045/c1eb0c0f-41f6-4335-b982-84b278b53d59
 
 # Features
-
 - Response streaming identical to ChatGPT through server-sent events
 - UI from original ChatGPT, including Dark mode
 - AI model selection (through 5 endpoints: OpenAI API, BingAI, ChatGPT Browser, PaLM2, Plugins)
-- Create, Save, & Share custom presets - [More info on prompt presets here](https://github.com/danny-avila/chatgpt-clone/releases/tag/v0.3.0)
+- Create, Save, & Share custom presets - [More info on prompt presets here](https://github.com/danny-avila/LibreChat/releases/tag/v0.3.0)
 - Edit and Resubmit messages with conversation branching
-- Search all messages/conversations - [More info here](https://github.com/danny-avila/chatgpt-clone/releases/tag/v0.1.0)
+- Search all messages/conversations - [More info here](https://github.com/danny-avila/LibreChat/releases/tag/v0.1.0)
 - Plugins now available (including web access, image generation and more)
 
 ---
-# ⚠️ **Breaking Changes** ⚠️
-Note: These changes only apply to users who are updating from a previous version of the app.
 
-- We have simplified the configuration process by using a single `.env` file in the root folder instead of separate `/api/.env` and `/client/.env` files.
-- If you had installed a previous version, you can run `npm run upgrade` to automatically copy the content of both files to the new `.env` file and backup the old ones in the root dir.
-- If you are installing the project for the first time, it's recommend you run the installation script `npm run install` to guide your local setup (otherwise continue to use docker)
-- The docker-compose file had some change. Review the [new docker instructions](docs\install\docker_install.md) to make sure you are setup properly. This is still the simplest and most effective method.
-- The upgrade script requires both `/api/.env` and `/client/.env` files to run properly. If you get an error about a missing client env file, just rename the `/client/.env.example` file to `/client/.env` and run the script again.
-- We have renamed the `OPENAI_KEY` variable to `OPENAI_API_KEY` to match the official documentation. The upgrade script should do this automatically for you, but please double-check that your key is correct in the new `.env` file.
-- After running the upgrade script, the `OPENAI_API_KEY` variable might be placed in a different section in the new `.env` file than before. This does not affect the functionality of the app, but if you want to keep it organized, you can look for it near the bottom of the file and move it to its usual section.
-
-##
-
-- For enhanced security, we are now asking for crypto keys for securely storing credentials in the `.env` file. Crypto keys are used to encrypt and decrypt sensitive data such as passwords and access keys. If you don't set them, the app will crash on startup.
-- You need to fill the following variables in the `.env` file with 32-byte (64 characters in hex) or 16-byte (32 characters in hex) values:
-  - `CREDS_KEY` (32-byte)
-  - `CREDS_IV` (16-byte)
-  - `JWT_SECRET` (32-byte, optional but recommended)
-- You can use this replit to generate some crypto keys quickly: https://replit.com/@daavila/crypto#index.js
-- Make sure you keep your crypto keys safe and don't share them with anyone.
-
-We apologize for any inconvenience caused by these changes. We hope you enjoy the new and improved version of our app!
+## ⚠️ [Breaking Changes as of v0.5.0](docs/general_info/breaking_changes.md#v050) ⚠️
+**Please read this before updating from a previous version**
 
 ---
 
 ## Changelog 
-- Keep up with the latest updates by visiting the releases page - [Releases](https://github.com/danny-avila/LibreChat/releases)
+Keep up with the latest updates by visiting the releases page - [Releases](https://github.com/danny-avila/LibreChat/releases)
 
 ---
 
@@ -71,11 +59,12 @@ We apologize for any inconvenience caused by these changes. We hope you enjoy th
 <details open>
   <summary><strong>Getting Started</strong></summary>
 
-  * [Docker Install](/docs/install/docker_install.md)
+  * [Docker Install](docs/install/docker_install.md)
   * [Linux Install](docs/install/linux_install.md)
   * [Mac Install](docs/install/mac_install.md)
   * [Windows Install](docs/install/windows_install.md)
   * [APIs and Tokens](docs/install/apis_and_tokens.md)
+  * [User Auth System](docs/install/user_auth_system.md)
 </details>
 
 <details>
@@ -84,8 +73,7 @@ We apologize for any inconvenience caused by these changes. We hope you enjoy th
   * [Code of Conduct](CODE_OF_CONDUCT.md)
   * [Project Origin](docs/general_info/project_origin.md)
   * [Multilingual Information](docs/general_info/multilingual_information.md)
-  * [Tech Stack](docs/general_info/tech_stack.md)
-  * [Bing Jailbreak Info](docs/general_info/bing_jailbreak_info.md)
+  * [Tech Stack](docs/general_info/tech_stack.md)   
 </details>
 
 <details>
@@ -98,14 +86,18 @@ We apologize for any inconvenience caused by these changes. We hope you enjoy th
     * [Wolfram](docs/features/plugins/wolfram.md)
     * [Make Your Own Plugin](docs/features/plugins/make_your_own.md)
 
-  * [User Auth System](docs/features/user_auth_system.md)
   * [Proxy](docs/features/proxy.md)
+  * [Bing Jailbreak](docs/features/bing_jailbreak.md)
 </details>
 
 <details>
   <summary><strong>Cloud Deployment</strong></summary>
 
+  * [Hetzner](docs/deployment/hetzner_ubuntu.md)
   * [Heroku](docs/deployment/heroku.md)
+  * [Linode](docs/deployment/linode.md)
+  * [Cloudflare](docs/deployment/cloudflare.md)
+  * [Ngrok](docs/deployment/ngrok.md)
 </details>
 
 <details>
@@ -116,7 +108,7 @@ We apologize for any inconvenience caused by these changes. We hope you enjoy th
   * [Code Standards and Conventions](docs/contributions/coding_conventions.md)
   * [Testing](docs/contributions/testing.md)
   * [Security](SECURITY.md)
-  * [Trello Board](https://trello.com/b/17z094kq/chatgpt-clone)
+  * [Trello Board](https://trello.com/b/17z094kq/LibreChate)
 </details>
 
 
@@ -124,14 +116,14 @@ We apologize for any inconvenience caused by these changes. We hope you enjoy th
 
 ## Star History
 
-[![Star History Chart](https://api.star-history.com/svg?repos=danny-avila/chatgpt-clone&type=Date)](https://star-history.com/#danny-avila/chatgpt-clone&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=danny-avila/LibreChat&type=Date)](https://star-history.com/#danny-avila/LibreChat&Date)
 
 ---
 
 ## Sponsors
 
-  Sponsored by <a href="https://github.com/DavidDev1334"><b>@DavidDev1334</b></a>, <a href="https://github.com/mjtechguy"><b>@mjtechguy</b></a>, <a href="https://github.com/Pharrcyde"><b>@Pharrcyde</b></a>, & <a href="https://github.com/fuegovic"><b>@fuegovic</b></a>
-
+  Sponsored by <a href="https://github.com/mjtechguy"><b>@mjtechguy</b></a>, <a href="https://github.com/SphaeroX"><b>@SphaeroX</b></a>, <a href="https://github.com/DavidDev1334"><b>@DavidDev1334</b></a>, <a href="https://github.com/fuegovic"><b>@fuegovic</b></a>, <a href="https://github.com/Pharrcyde"><b>@Pharrcyde</b></a> 
+  
 ---
 
 ## Contributors
@@ -146,6 +138,6 @@ For new features, components, or extensions, please open an issue and discuss be
 
 This project exists in its current state thanks to all the people who contribute
 ---
-<a href="https://github.com/danny-avila/chatgpt-clone/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=danny-avila/chatgpt-clone" />
+<a href="https://github.com/danny-avila/LibreChat/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=danny-avila/LibreChat" />
 </a>

api/app/clients/BaseClient.js

@@ -0,0 +1,550 @@
+const crypto = require('crypto');
+const TextStream = require('./TextStream');
+const { RecursiveCharacterTextSplitter } = require('langchain/text_splitter');
+const { ChatOpenAI } = require('langchain/chat_models/openai');
+const { loadSummarizationChain } = require('langchain/chains');
+const { refinePrompt } = require('./prompts/refinePrompt');
+const { getConvo, getMessages, saveMessage, updateMessage, saveConvo } = require('../../models');
+
+class BaseClient {
+  constructor(apiKey, options = {}) {
+    this.apiKey = apiKey;
+    this.sender = options.sender || 'AI';
+    this.contextStrategy = null;
+    this.currentDateString = new Date().toLocaleDateString('en-us', {
+      year: 'numeric',
+      month: 'long',
+      day: 'numeric'
+    });
+  }
+
+  setOptions() {
+    throw new Error('Method \'setOptions\' must be implemented.');
+  }
+
+  getCompletion() {
+    throw new Error('Method \'getCompletion\' must be implemented.');
+  }
+
+  async sendCompletion() {
+    throw new Error('Method \'sendCompletion\' must be implemented.');
+  }
+
+  getSaveOptions() {
+    throw new Error('Subclasses must implement getSaveOptions');
+  }
+
+  async buildMessages() {
+    throw new Error('Subclasses must implement buildMessages');
+  }
+
+  getBuildMessagesOptions() {
+    throw new Error('Subclasses must implement getBuildMessagesOptions');
+  }
+
+  async generateTextStream(text, onProgress, options = {}) {
+    const stream = new TextStream(text, options);
+    await stream.processTextStream(onProgress);
+  }
+
+  async setMessageOptions(opts = {}) {
+    if (opts && typeof opts === 'object') {
+      this.setOptions(opts);
+    }
+    const user = opts.user || null;
+    const conversationId = opts.conversationId || crypto.randomUUID();
+    const parentMessageId = opts.parentMessageId || '00000000-0000-0000-0000-000000000000';
+    const userMessageId = opts.overrideParentMessageId || crypto.randomUUID();
+    const responseMessageId = crypto.randomUUID();
+    const saveOptions = this.getSaveOptions();
+    this.abortController = opts.abortController || new AbortController();
+    this.currentMessages = await this.loadHistory(conversationId, parentMessageId) ?? [];
+
+    return {
+      ...opts,
+      user,
+      conversationId,
+      parentMessageId,
+      userMessageId,
+      responseMessageId,
+      saveOptions,
+    };
+  }
+
+  createUserMessage({ messageId, parentMessageId, conversationId, text}) {
+    const userMessage = {
+      messageId,
+      parentMessageId,
+      conversationId,
+      sender: 'User',
+      text,
+      isCreatedByUser: true
+    };
+    return userMessage;
+  }
+
+  async handleStartMethods(message, opts) {
+    const {
+      user,
+      conversationId,
+      parentMessageId,
+      userMessageId,
+      responseMessageId,
+      saveOptions,
+    } = await this.setMessageOptions(opts);
+
+    const userMessage = this.createUserMessage({
+      messageId: userMessageId,
+      parentMessageId,
+      conversationId,
+      text: message,
+    });
+
+    if (typeof opts?.getIds === 'function') {
+      opts.getIds({
+        userMessage,
+        conversationId,
+        responseMessageId
+      });
+    }
+
+    if (typeof opts?.onStart === 'function') {
+      opts.onStart(userMessage);
+    }
+
+    return {
+      ...opts,
+      user,
+      conversationId,
+      responseMessageId,
+      saveOptions,
+      userMessage,
+    };
+  }
+
+  addInstructions(messages, instructions) {
+    const payload = [];
+    if (!instructions) {
+      return messages;
+    }
+    if (messages.length > 1) {
+      payload.push(...messages.slice(0, -1));
+    }
+
+    payload.push(instructions);
+
+    if (messages.length > 0) {
+      payload.push(messages[messages.length - 1]);
+    }
+
+    return payload;
+  }
+
+  async handleTokenCountMap(tokenCountMap) {
+    if (this.currentMessages.length === 0) {
+      return;
+    }
+
+    for (let i = 0; i < this.currentMessages.length; i++) {
+      // Skip the last message, which is the user message.
+      if (i === this.currentMessages.length - 1) {
+        break;
+      }
+
+      const message = this.currentMessages[i];
+      const { messageId } = message;
+      const update = {};
+
+      if (messageId === tokenCountMap.refined?.messageId) {
+        if (this.options.debug) {
+          console.debug(`Adding refined props to ${messageId}.`);
+        }
+
+        update.refinedMessageText = tokenCountMap.refined.content;
+        update.refinedTokenCount = tokenCountMap.refined.tokenCount;
+      }
+
+      if (message.tokenCount && !update.refinedTokenCount) {
+        if (this.options.debug) {
+          console.debug(`Skipping ${messageId}: already had a token count.`);
+        }
+        continue;
+      }
+
+      const tokenCount = tokenCountMap[messageId];
+      if (tokenCount) {
+        message.tokenCount = tokenCount;
+        update.tokenCount = tokenCount;
+        await this.updateMessageInDatabase({ messageId, ...update });
+      }
+    }
+  }
+
+  concatenateMessages(messages) {
+    return messages.reduce((acc, message) => {
+      const nameOrRole = message.name ?? message.role;
+      return acc + `${nameOrRole}:\n${message.content}\n\n`;
+    }, '');
+  }
+
+  async refineMessages(messagesToRefine, remainingContextTokens) {
+    const model = new ChatOpenAI({ temperature: 0 });
+    const chain = loadSummarizationChain(model, { type: 'refine', verbose: this.options.debug, refinePrompt });
+    const splitter = new RecursiveCharacterTextSplitter({
+      chunkSize: 1500,
+      chunkOverlap: 100,
+    });
+    const userMessages = this.concatenateMessages(messagesToRefine.filter(m => m.role === 'user'));
+    const assistantMessages = this.concatenateMessages(messagesToRefine.filter(m => m.role !== 'user'));
+    const userDocs = await splitter.createDocuments([userMessages],[],{
+      chunkHeader: 'DOCUMENT NAME: User Message\n\n---\n\n',
+      appendChunkOverlapHeader: true,
+    });
+    const assistantDocs = await splitter.createDocuments([assistantMessages],[],{
+      chunkHeader: 'DOCUMENT NAME: Assistant Message\n\n---\n\n',
+      appendChunkOverlapHeader: true,
+    });
+    // const chunkSize = Math.round(concatenatedMessages.length / 512);
+    const input_documents = userDocs.concat(assistantDocs);
+    if (this.options.debug ) {
+      console.debug('Refining messages...');
+    }
+    try {
+      const res = await chain.call({
+        input_documents,
+        signal: this.abortController.signal,
+      });
+
+      const refinedMessage = {
+        role: 'assistant',
+        content: res.output_text,
+        tokenCount: this.getTokenCount(res.output_text),
+      }
+
+      if (this.options.debug ) {
+        console.debug('Refined messages', refinedMessage);
+        console.debug(`remainingContextTokens: ${remainingContextTokens}, after refining: ${remainingContextTokens - refinedMessage.tokenCount}`);
+      }
+
+      return refinedMessage;
+    } catch (e) {
+      console.error('Error refining messages');
+      console.error(e);
+      return null;
+    }
+  }
+
+  /**
+ * This method processes an array of messages and returns a context of messages that fit within a token limit.
+ * It iterates over the messages from newest to oldest, adding them to the context until the token limit is reached.
+ * If the token limit would be exceeded by adding a message, that message and possibly the previous one are added to a separate array of messages to refine.
+ * The method uses `push` and `pop` operations for efficient array manipulation, and reverses the arrays at the end to maintain the original order of the messages.
+ * The method also includes a mechanism to avoid blocking the event loop by waiting for the next tick after each iteration.
+ *
+ * @param {Array} messages - An array of messages, each with a `tokenCount` property. The messages should be ordered from oldest to newest.
+ * @returns {Object} An object with three properties: `context`, `remainingContextTokens`, and `messagesToRefine`. `context` is an array of messages that fit within the token limit. `remainingContextTokens` is the number of tokens remaining within the limit after adding the messages to the context. `messagesToRefine` is an array of messages that were not added to the context because they would have exceeded the token limit.
+ */
+  async getMessagesWithinTokenLimit(messages) {
+    let currentTokenCount = 0;
+    let context = [];
+    let messagesToRefine = [];
+    let refineIndex = -1;
+    let remainingContextTokens = this.maxContextTokens;
+
+    for (let i = messages.length - 1; i >= 0; i--) {
+      const message = messages[i];
+      const newTokenCount = currentTokenCount + message.tokenCount;
+      const exceededLimit = newTokenCount > this.maxContextTokens;
+      let shouldRefine = exceededLimit && this.shouldRefineContext;
+      let refineNextMessage = i !== 0 && i !== 1 && context.length > 0;
+
+      if (shouldRefine) {
+        messagesToRefine.push(message);
+
+        if (refineIndex === -1) {
+          refineIndex = i;
+        }
+
+        if (refineNextMessage) {
+          refineIndex = i + 1;
+          const removedMessage = context.pop();
+          messagesToRefine.push(removedMessage);
+          currentTokenCount -= removedMessage.tokenCount;
+          remainingContextTokens = this.maxContextTokens - currentTokenCount;
+          refineNextMessage = false;
+        }
+
+        continue;
+      } else if (exceededLimit) {
+        break;
+      }
+
+      context.push(message);
+      currentTokenCount = newTokenCount;
+      remainingContextTokens = this.maxContextTokens - currentTokenCount;
+      await new Promise(resolve => setImmediate(resolve));
+    }
+
+    return {
+      context: context.reverse(),
+      remainingContextTokens,
+      messagesToRefine: messagesToRefine.reverse(),
+      refineIndex
+    };
+  }
+
+  async handleContextStrategy({instructions, orderedMessages, formattedMessages}) {
+    let payload = this.addInstructions(formattedMessages, instructions);
+    let orderedWithInstructions = this.addInstructions(orderedMessages, instructions);
+    let {
+      context,
+      remainingContextTokens,
+      messagesToRefine,
+      refineIndex
+    } = await this.getMessagesWithinTokenLimit(payload);
+
+    payload = context;
+    let refinedMessage;
+
+    // if (messagesToRefine.length > 0) {
+    //   refinedMessage = await this.refineMessages(messagesToRefine, remainingContextTokens);
+    //   payload.unshift(refinedMessage);
+    //   remainingContextTokens -= refinedMessage.tokenCount;
+    // }
+    // if (remainingContextTokens <= instructions?.tokenCount) {
+    //   if (this.options.debug) {
+    //     console.debug(`Remaining context (${remainingContextTokens}) is less than instructions token count: ${instructions.tokenCount}`);
+    //   }
+
+    //   ({ context, remainingContextTokens, messagesToRefine, refineIndex } = await this.getMessagesWithinTokenLimit(payload));
+    //   payload = context;
+    // }
+
+    // Calculate the difference in length to determine how many messages were discarded if any
+    let diff = orderedWithInstructions.length - payload.length;
+
+    if (this.options.debug) {
+      console.debug('<---------------------------------DIFF--------------------------------->');
+      console.debug(`Difference between payload (${payload.length}) and orderedWithInstructions (${orderedWithInstructions.length}): ${diff}`);
+      console.debug('remainingContextTokens, this.maxContextTokens (1/2)', remainingContextTokens, this.maxContextTokens);
+    }
+
+    // If the difference is positive, slice the orderedWithInstructions array
+    if (diff > 0) {
+      orderedWithInstructions = orderedWithInstructions.slice(diff);
+    }
+
+    if (messagesToRefine.length > 0) {
+      refinedMessage = await this.refineMessages(messagesToRefine, remainingContextTokens);
+      payload.unshift(refinedMessage);
+      remainingContextTokens -= refinedMessage.tokenCount;
+    }
+
+    if (this.options.debug) {
+      console.debug('remainingContextTokens, this.maxContextTokens (2/2)', remainingContextTokens, this.maxContextTokens);
+    }
+
+    let tokenCountMap = orderedWithInstructions.reduce((map, message, index) => {
+      if (!message.messageId) {
+        return map;
+      }
+
+      if (index === refineIndex) {
+        map.refined = { ...refinedMessage, messageId: message.messageId};
+      }
+
+      map[message.messageId] = payload[index].tokenCount;
+      return map;
+    }, {});
+
+    const promptTokens = this.maxContextTokens - remainingContextTokens;
+
+    if (this.options.debug) {
+      console.debug('<-------------------------PAYLOAD/TOKEN COUNT MAP------------------------->');
+      console.debug('Payload:', payload);
+      console.debug('Token Count Map:', tokenCountMap);
+      console.debug('Prompt Tokens', promptTokens, remainingContextTokens, this.maxContextTokens);
+    }
+
+    return { payload, tokenCountMap, promptTokens, messages: orderedWithInstructions };
+  }
+
+  async sendMessage(message, opts = {}) {
+    console.log('BaseClient: sendMessage', message, opts);
+    const {
+      user,
+      conversationId,
+      responseMessageId,
+      saveOptions,
+      userMessage,
+    } = await this.handleStartMethods(message, opts);
+
+    // It's not necessary to push to currentMessages
+    // depending on subclass implementation of handling messages
+    this.currentMessages.push(userMessage);
+
+    let { prompt: payload, tokenCountMap, promptTokens } = await this.buildMessages(
+      this.currentMessages,
+      // When the userMessage is pushed to currentMessages, the parentMessage is the userMessageId.
+      // this only matters when buildMessages is utilizing the parentMessageId, and may vary on implementation
+      userMessage.messageId,
+      this.getBuildMessagesOptions(opts),
+    );
+
+    if (this.options.debug) {
+      console.debug('payload');
+      console.debug(payload);
+    }
+
+    if (tokenCountMap) {
+      console.dir(tokenCountMap, { depth: null })
+      if (tokenCountMap[userMessage.messageId]) {
+        userMessage.tokenCount = tokenCountMap[userMessage.messageId];
+        console.log('userMessage.tokenCount', userMessage.tokenCount);
+        console.log('userMessage', userMessage);
+      }
+
+      payload = payload.map((message) => {
+        const messageWithoutTokenCount = message;
+        delete messageWithoutTokenCount.tokenCount;
+        return messageWithoutTokenCount;
+      });
+      this.handleTokenCountMap(tokenCountMap);
+    }
+
+    await this.saveMessageToDatabase(userMessage, saveOptions, user);
+    const responseMessage = {
+      messageId: responseMessageId,
+      conversationId,
+      parentMessageId: userMessage.messageId,
+      isCreatedByUser: false,
+      model: this.modelOptions.model,
+      sender: this.sender,
+      text: await this.sendCompletion(payload, opts),
+      promptTokens,
+    };
+
+    if (tokenCountMap && this.getTokenCountForResponse) {
+      responseMessage.tokenCount = this.getTokenCountForResponse(responseMessage);
+      responseMessage.completionTokens = responseMessage.tokenCount;
+    }
+    await this.saveMessageToDatabase(responseMessage, saveOptions, user);
+    delete responseMessage.tokenCount;
+    return responseMessage;
+  }
+
+  async getConversation(conversationId, user = null) {
+    return await getConvo(user, conversationId);
+  }
+
+  async loadHistory(conversationId, parentMessageId = null) {
+    if (this.options.debug) {
+      console.debug('Loading history for conversation', conversationId, parentMessageId);
+    }
+
+    const messages = (await getMessages({ conversationId })) || [];
+
+    if (messages.length === 0) {
+      return [];
+    }
+
+    let mapMethod = null;
+    if (this.getMessageMapMethod) {
+      mapMethod = this.getMessageMapMethod();
+    }
+
+    return this.constructor.getMessagesForConversation(messages, parentMessageId, mapMethod);
+  }
+
+  async saveMessageToDatabase(message, endpointOptions, user = null) {
+    await saveMessage({ ...message, unfinished: false });
+    await saveConvo(user, {
+      conversationId: message.conversationId,
+      endpoint: this.options.endpoint,
+      ...endpointOptions
+    });
+  }
+
+  async updateMessageInDatabase(message) {
+    await updateMessage(message);
+  }
+
+  /**
+     * Iterate through messages, building an array based on the parentMessageId.
+     * Each message has an id and a parentMessageId. The parentMessageId is the id of the message that this message is a reply to.
+     * @param messages
+     * @param parentMessageId
+     * @returns {*[]} An array containing the messages in the order they should be displayed, starting with the root message.
+     */
+  static getMessagesForConversation(messages, parentMessageId, mapMethod = null) {
+    if (!messages || messages.length === 0) {
+      return [];
+    }
+
+    const orderedMessages = [];
+    let currentMessageId = parentMessageId;
+    while (currentMessageId) {
+      const message = messages.find(msg => {
+        const messageId = msg.messageId ?? msg.id;
+        return messageId === currentMessageId;
+      });
+      if (!message) {
+        break;
+      }
+      orderedMessages.unshift(message);
+      currentMessageId = message.parentMessageId;
+    }
+
+    if (mapMethod) {
+      return orderedMessages.map(mapMethod);
+    }
+
+    return orderedMessages;
+  }
+
+  /**
+ * Algorithm adapted from "6. Counting tokens for chat API calls" of
+ * https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
+ *
+ * An additional 2 tokens need to be added for metadata after all messages have been counted.
+ *
+ * @param {*} message
+ */
+  getTokenCountForMessage(message) {
+    let tokensPerMessage;
+    let nameAdjustment;
+    if (this.modelOptions.model.startsWith('gpt-4')) {
+      tokensPerMessage = 3;
+      nameAdjustment = 1;
+    } else {
+      tokensPerMessage = 4;
+      nameAdjustment = -1;
+    }
+
+    if (this.options.debug) {
+      console.debug('getTokenCountForMessage', message);
+    }
+
+    // Map each property of the message to the number of tokens it contains
+    const propertyTokenCounts = Object.entries(message).map(([key, value]) => {
+      if (key === 'tokenCount' || typeof value !== 'string') {
+        return 0;
+      }
+      // Count the number of tokens in the property value
+      const numTokens = this.getTokenCount(value);
+
+      // Adjust by `nameAdjustment` tokens if the property key is 'name'
+      const adjustment = (key === 'name') ? nameAdjustment : 0;
+      return numTokens + adjustment;
+    });
+
+    if (this.options.debug) {
+      console.debug('propertyTokenCounts', propertyTokenCounts);
+    }
+
+    // Sum the number of tokens in all properties and add `tokensPerMessage` for metadata
+    return propertyTokenCounts.reduce((a, b) => a + b, tokensPerMessage);
+  }
+}
+
+module.exports = BaseClient;

api/app/clients/ChatGPTClient.js

@@ -0,0 +1,570 @@
+const crypto = require('crypto');
+const Keyv = require('keyv');
+const { encoding_for_model: encodingForModel, get_encoding: getEncoding } = require('@dqbd/tiktoken');
+const { fetchEventSource } = require('@waylaidwanderer/fetch-event-source');
+const { Agent, ProxyAgent } = require('undici');
+const BaseClient = require('./BaseClient');
+
+const CHATGPT_MODEL = 'gpt-3.5-turbo';
+const tokenizersCache = {};
+
+class ChatGPTClient extends BaseClient {
+  constructor(
+    apiKey,
+    options = {},
+    cacheOptions = {},
+  ) {
+    super(apiKey, options, cacheOptions);
+
+    cacheOptions.namespace = cacheOptions.namespace || 'chatgpt';
+    this.conversationsCache = new Keyv(cacheOptions);
+    this.setOptions(options);
+  }
+
+  setOptions(options) {
+    if (this.options && !this.options.replaceOptions) {
+      // nested options aren't spread properly, so we need to do this manually
+      this.options.modelOptions = {
+        ...this.options.modelOptions,
+        ...options.modelOptions,
+      };
+      delete options.modelOptions;
+      // now we can merge options
+      this.options = {
+        ...this.options,
+        ...options,
+      };
+    } else {
+      this.options = options;
+    }
+
+    if (this.options.openaiApiKey) {
+      this.apiKey = this.options.openaiApiKey;
+    }
+
+    const modelOptions = this.options.modelOptions || {};
+    this.modelOptions = {
+      ...modelOptions,
+      // set some good defaults (check for undefined in some cases because they may be 0)
+      model: modelOptions.model || CHATGPT_MODEL,
+      temperature: typeof modelOptions.temperature === 'undefined' ? 0.8 : modelOptions.temperature,
+      top_p: typeof modelOptions.top_p === 'undefined' ? 1 : modelOptions.top_p,
+      presence_penalty: typeof modelOptions.presence_penalty === 'undefined' ? 1 : modelOptions.presence_penalty,
+      stop: modelOptions.stop,
+    };
+
+    this.isChatGptModel = this.modelOptions.model.startsWith('gpt-');
+    const { isChatGptModel } = this;
+    this.isUnofficialChatGptModel = this.modelOptions.model.startsWith('text-chat') || this.modelOptions.model.startsWith('text-davinci-002-render');
+    const { isUnofficialChatGptModel } = this;
+
+    // Davinci models have a max context length of 4097 tokens.
+    this.maxContextTokens = this.options.maxContextTokens || (isChatGptModel ? 4095 : 4097);
+    // I decided to reserve 1024 tokens for the response.
+    // The max prompt tokens is determined by the max context tokens minus the max response tokens.
+    // Earlier messages will be dropped until the prompt is within the limit.
+    this.maxResponseTokens = this.modelOptions.max_tokens || 1024;
+    this.maxPromptTokens = this.options.maxPromptTokens || (this.maxContextTokens - this.maxResponseTokens);
+
+    if (this.maxPromptTokens + this.maxResponseTokens > this.maxContextTokens) {
+      throw new Error(`maxPromptTokens + max_tokens (${this.maxPromptTokens} + ${this.maxResponseTokens} = ${this.maxPromptTokens + this.maxResponseTokens}) must be less than or equal to maxContextTokens (${this.maxContextTokens})`);
+    }
+
+    this.userLabel = this.options.userLabel || 'User';
+    this.chatGptLabel = this.options.chatGptLabel || 'ChatGPT';
+
+    if (isChatGptModel) {
+      // Use these faux tokens to help the AI understand the context since we are building the chat log ourselves.
+      // Trying to use "<|im_start|>" causes the AI to still generate "<" or "<|" at the end sometimes for some reason,
+      // without tripping the stop sequences, so I'm using "||>" instead.
+      this.startToken = '||>';
+      this.endToken = '';
+      this.gptEncoder = this.constructor.getTokenizer('cl100k_base');
+    } else if (isUnofficialChatGptModel) {
+      this.startToken = '<|im_start|>';
+      this.endToken = '<|im_end|>';
+      this.gptEncoder = this.constructor.getTokenizer('text-davinci-003', true, {
+        '<|im_start|>': 100264,
+        '<|im_end|>': 100265,
+      });
+    } else {
+      // Previously I was trying to use "<|endoftext|>" but there seems to be some bug with OpenAI's token counting
+      // system that causes only the first "<|endoftext|>" to be counted as 1 token, and the rest are not treated
+      // as a single token. So we're using this instead.
+      this.startToken = '||>';
+      this.endToken = '';
+      try {
+        this.gptEncoder = this.constructor.getTokenizer(this.modelOptions.model, true);
+      } catch {
+        this.gptEncoder = this.constructor.getTokenizer('text-davinci-003', true);
+      }
+    }
+
+    if (!this.modelOptions.stop) {
+      const stopTokens = [this.startToken];
+      if (this.endToken && this.endToken !== this.startToken) {
+        stopTokens.push(this.endToken);
+      }
+      stopTokens.push(`\n${this.userLabel}:`);
+      stopTokens.push('<|diff_marker|>');
+      // I chose not to do one for `chatGptLabel` because I've never seen it happen
+      this.modelOptions.stop = stopTokens;
+    }
+
+    if (this.options.reverseProxyUrl) {
+      this.completionsUrl = this.options.reverseProxyUrl;
+    } else if (isChatGptModel) {
+      this.completionsUrl = 'https://api.openai.com/v1/chat/completions';
+    } else {
+      this.completionsUrl = 'https://api.openai.com/v1/completions';
+    }
+
+    return this;
+  }
+
+  static getTokenizer(encoding, isModelName = false, extendSpecialTokens = {}) {
+    if (tokenizersCache[encoding]) {
+      return tokenizersCache[encoding];
+    }
+    let tokenizer;
+    if (isModelName) {
+      tokenizer = encodingForModel(encoding, extendSpecialTokens);
+    } else {
+      tokenizer = getEncoding(encoding, extendSpecialTokens);
+    }
+    tokenizersCache[encoding] = tokenizer;
+    return tokenizer;
+  }
+
+  async getCompletion(input, onProgress, abortController = null) {
+    if (!abortController) {
+      abortController = new AbortController();
+    }
+    const modelOptions = { ...this.modelOptions };
+    if (typeof onProgress === 'function') {
+      modelOptions.stream = true;
+    }
+    if (this.isChatGptModel) {
+      modelOptions.messages = input;
+    } else {
+      modelOptions.prompt = input;
+    }
+    const { debug } = this.options;
+    const url = this.completionsUrl;
+    if (debug) {
+      console.debug();
+      console.debug(url);
+      console.debug(modelOptions);
+      console.debug();
+    }
+    const opts = {
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+      },
+      body: JSON.stringify(modelOptions),
+      dispatcher: new Agent({
+        bodyTimeout: 0,
+        headersTimeout: 0,
+      }),
+    };
+
+    if (this.apiKey && this.options.azure) {
+      opts.headers['api-key'] = this.apiKey;
+    } else if (this.apiKey) {
+      opts.headers.Authorization = `Bearer ${this.apiKey}`;
+    }
+
+    if (this.options.headers) {
+      opts.headers = { ...opts.headers, ...this.options.headers };
+    }
+
+    if (this.options.proxy) {
+      opts.dispatcher = new ProxyAgent(this.options.proxy);
+    }
+
+    if (modelOptions.stream) {
+      // eslint-disable-next-line no-async-promise-executor
+      return new Promise(async (resolve, reject) => {
+        try {
+          let done = false;
+          await fetchEventSource(url, {
+            ...opts,
+            signal: abortController.signal,
+            async onopen(response) {
+              if (response.status === 200) {
+                return;
+              }
+              if (debug) {
+                console.debug(response);
+              }
+              let error;
+              try {
+                const body = await response.text();
+                error = new Error(`Failed to send message. HTTP ${response.status} - ${body}`);
+                error.status = response.status;
+                error.json = JSON.parse(body);
+              } catch {
+                error = error || new Error(`Failed to send message. HTTP ${response.status}`);
+              }
+              throw error;
+            },
+            onclose() {
+              if (debug) {
+                console.debug('Server closed the connection unexpectedly, returning...');
+              }
+              // workaround for private API not sending [DONE] event
+              if (!done) {
+                onProgress('[DONE]');
+                abortController.abort();
+                resolve();
+              }
+            },
+            onerror(err) {
+              if (debug) {
+                console.debug(err);
+              }
+              // rethrow to stop the operation
+              throw err;
+            },
+            onmessage(message) {
+              if (debug) {
+                // console.debug(message);
+              }
+              if (!message.data || message.event === 'ping') {
+                return;
+              }
+              if (message.data === '[DONE]') {
+                onProgress('[DONE]');
+                abortController.abort();
+                resolve();
+                done = true;
+                return;
+              }
+              onProgress(JSON.parse(message.data));
+            },
+          });
+        } catch (err) {
+          reject(err);
+        }
+      });
+    }
+    const response = await fetch(
+      url,
+      {
+        ...opts,
+        signal: abortController.signal,
+      },
+    );
+    if (response.status !== 200) {
+      const body = await response.text();
+      const error = new Error(`Failed to send message. HTTP ${response.status} - ${body}`);
+      error.status = response.status;
+      try {
+        error.json = JSON.parse(body);
+      } catch {
+        error.body = body;
+      }
+      throw error;
+    }
+    return response.json();
+  }
+
+  async generateTitle(userMessage, botMessage) {
+    const instructionsPayload = {
+      role: 'system',
+      content: `Write an extremely concise subtitle for this conversation with no more than a few words. All words should be capitalized. Exclude punctuation.
+
+||>Message:
+${userMessage.message}
+||>Response:
+${botMessage.message}
+
+||>Title:`,
+    };
+
+    const titleGenClientOptions = JSON.parse(JSON.stringify(this.options));
+    titleGenClientOptions.modelOptions = {
+      model: 'gpt-3.5-turbo',
+      temperature: 0,
+      presence_penalty: 0,
+      frequency_penalty: 0,
+    };
+    const titleGenClient = new ChatGPTClient(this.apiKey, titleGenClientOptions);
+    const result = await titleGenClient.getCompletion([instructionsPayload], null);
+    // remove any non-alphanumeric characters, replace multiple spaces with 1, and then trim
+    return result.choices[0].message.content
+      .replace(/[^a-zA-Z0-9' ]/g, '')
+      .replace(/\s+/g, ' ')
+      .trim();
+  }
+
+  async sendMessage(
+    message,
+    opts = {},
+  ) {
+    if (opts.clientOptions && typeof opts.clientOptions === 'object') {
+      this.setOptions(opts.clientOptions);
+    }
+
+    const conversationId = opts.conversationId || crypto.randomUUID();
+    const parentMessageId = opts.parentMessageId || crypto.randomUUID();
+
+    let conversation = typeof opts.conversation === 'object'
+      ? opts.conversation
+      : await this.conversationsCache.get(conversationId);
+
+    let isNewConversation = false;
+    if (!conversation) {
+      conversation = {
+        messages: [],
+        createdAt: Date.now(),
+      };
+      isNewConversation = true;
+    }
+
+    const shouldGenerateTitle = opts.shouldGenerateTitle && isNewConversation;
+
+    const userMessage = {
+      id: crypto.randomUUID(),
+      parentMessageId,
+      role: 'User',
+      message,
+    };
+    conversation.messages.push(userMessage);
+
+    // Doing it this way instead of having each message be a separate element in the array seems to be more reliable,
+    // especially when it comes to keeping the AI in character. It also seems to improve coherency and context retention.
+    const { prompt: payload, context } = await this.buildPrompt(
+      conversation.messages,
+      userMessage.id,
+      {
+        isChatGptModel: this.isChatGptModel,
+        promptPrefix: opts.promptPrefix,
+      },
+    );
+
+    if (this.options.keepNecessaryMessagesOnly) {
+      conversation.messages = context;
+    }
+
+    let reply = '';
+    let result = null;
+    if (typeof opts.onProgress === 'function') {
+      await this.getCompletion(
+        payload,
+        (progressMessage) => {
+          if (progressMessage === '[DONE]') {
+            return;
+          }
+          const token = this.isChatGptModel ? progressMessage.choices[0].delta.content : progressMessage.choices[0].text;
+          // first event's delta content is always undefined
+          if (!token) {
+            return;
+          }
+          if (this.options.debug) {
+            console.debug(token);
+          }
+          if (token === this.endToken) {
+            return;
+          }
+          opts.onProgress(token);
+          reply += token;
+        },
+        opts.abortController || new AbortController(),
+      );
+    } else {
+      result = await this.getCompletion(
+        payload,
+        null,
+        opts.abortController || new AbortController(),
+      );
+      if (this.options.debug) {
+        console.debug(JSON.stringify(result));
+      }
+      if (this.isChatGptModel) {
+        reply = result.choices[0].message.content;
+      } else {
+        reply = result.choices[0].text.replace(this.endToken, '');
+      }
+    }
+
+    // avoids some rendering issues when using the CLI app
+    if (this.options.debug) {
+      console.debug();
+    }
+
+    reply = reply.trim();
+
+    const replyMessage = {
+      id: crypto.randomUUID(),
+      parentMessageId: userMessage.id,
+      role: 'ChatGPT',
+      message: reply,
+    };
+    conversation.messages.push(replyMessage);
+
+    const returnData = {
+      response: replyMessage.message,
+      conversationId,
+      parentMessageId: replyMessage.parentMessageId,
+      messageId: replyMessage.id,
+      details: result || {},
+    };
+
+    if (shouldGenerateTitle) {
+      conversation.title = await this.generateTitle(userMessage, replyMessage);
+      returnData.title = conversation.title;
+    }
+
+    await this.conversationsCache.set(conversationId, conversation);
+
+    if (this.options.returnConversation) {
+      returnData.conversation = conversation;
+    }
+
+    return returnData;
+  }
+
+  async buildPrompt(messages, parentMessageId, { isChatGptModel = false, promptPrefix = null }) {
+    const orderedMessages = this.constructor.getMessagesForConversation(messages, parentMessageId);
+
+    promptPrefix = (promptPrefix || this.options.promptPrefix || '').trim();
+    if (promptPrefix) {
+      // If the prompt prefix doesn't end with the end token, add it.
+      if (!promptPrefix.endsWith(`${this.endToken}`)) {
+        promptPrefix = `${promptPrefix.trim()}${this.endToken}\n\n`;
+      }
+      promptPrefix = `${this.startToken}Instructions:\n${promptPrefix}`;
+    } else {
+      const currentDateString = new Date().toLocaleDateString(
+        'en-us',
+        { year: 'numeric', month: 'long', day: 'numeric' },
+      );
+      promptPrefix = `${this.startToken}Instructions:\nYou are ChatGPT, a large language model trained by OpenAI. Respond conversationally.\nCurrent date: ${currentDateString}${this.endToken}\n\n`;
+    }
+
+    const promptSuffix = `${this.startToken}${this.chatGptLabel}:\n`; // Prompt ChatGPT to respond.
+
+    const instructionsPayload = {
+      role: 'system',
+      name: 'instructions',
+      content: promptPrefix,
+    };
+
+    const messagePayload = {
+      role: 'system',
+      content: promptSuffix,
+    };
+
+    let currentTokenCount;
+    if (isChatGptModel) {
+      currentTokenCount = this.getTokenCountForMessage(instructionsPayload) + this.getTokenCountForMessage(messagePayload);
+    } else {
+      currentTokenCount = this.getTokenCount(`${promptPrefix}${promptSuffix}`);
+    }
+    let promptBody = '';
+    const maxTokenCount = this.maxPromptTokens;
+
+    const context = [];
+
+    // Iterate backwards through the messages, adding them to the prompt until we reach the max token count.
+    // Do this within a recursive async function so that it doesn't block the event loop for too long.
+    const buildPromptBody = async () => {
+      if (currentTokenCount < maxTokenCount && orderedMessages.length > 0) {
+        const message = orderedMessages.pop();
+        const roleLabel = message?.isCreatedByUser || message?.role?.toLowerCase() === 'user' ? this.userLabel : this.chatGptLabel;
+        const messageString = `${this.startToken}${roleLabel}:\n${message?.text ?? message?.message}${this.endToken}\n`;
+        let newPromptBody;
+        if (promptBody || isChatGptModel) {
+          newPromptBody = `${messageString}${promptBody}`;
+        } else {
+          // Always insert prompt prefix before the last user message, if not gpt-3.5-turbo.
+          // This makes the AI obey the prompt instructions better, which is important for custom instructions.
+          // After a bunch of testing, it doesn't seem to cause the AI any confusion, even if you ask it things
+          // like "what's the last thing I wrote?".
+          newPromptBody = `${promptPrefix}${messageString}${promptBody}`;
+        }
+
+        context.unshift(message);
+
+        const tokenCountForMessage = this.getTokenCount(messageString);
+        const newTokenCount = currentTokenCount + tokenCountForMessage;
+        if (newTokenCount > maxTokenCount) {
+          if (promptBody) {
+            // This message would put us over the token limit, so don't add it.
+            return false;
+          }
+          // This is the first message, so we can't add it. Just throw an error.
+          throw new Error(`Prompt is too long. Max token count is ${maxTokenCount}, but prompt is ${newTokenCount} tokens long.`);
+        }
+        promptBody = newPromptBody;
+        currentTokenCount = newTokenCount;
+        // wait for next tick to avoid blocking the event loop
+        await new Promise(resolve => setImmediate(resolve));
+        return buildPromptBody();
+      }
+      return true;
+    };
+
+    await buildPromptBody();
+
+    const prompt = `${promptBody}${promptSuffix}`;
+    if (isChatGptModel) {
+      messagePayload.content = prompt;
+      // Add 2 tokens for metadata after all messages have been counted.
+      currentTokenCount += 2;
+    }
+
+    // Use up to `this.maxContextTokens` tokens (prompt + response), but try to leave `this.maxTokens` tokens for the response.
+    this.modelOptions.max_tokens = Math.min(this.maxContextTokens - currentTokenCount, this.maxResponseTokens);
+
+    if (this.options.debug) {
+      console.debug(`Prompt : ${prompt}`);
+    }
+
+    if (isChatGptModel) {
+      return { prompt: [instructionsPayload, messagePayload], context };
+    }
+    return { prompt, context };
+  }
+
+  getTokenCount(text) {
+    return this.gptEncoder.encode(text, 'all').length;
+  }
+
+  /**
+ * Algorithm adapted from "6. Counting tokens for chat API calls" of
+ * https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
+ *
+ * An additional 2 tokens need to be added for metadata after all messages have been counted.
+ *
+ * @param {*} message
+ */
+  getTokenCountForMessage(message) {
+    let tokensPerMessage;
+    let nameAdjustment;
+    if (this.modelOptions.model.startsWith('gpt-4')) {
+      tokensPerMessage = 3;
+      nameAdjustment = 1;
+    } else {
+      tokensPerMessage = 4;
+      nameAdjustment = -1;
+    }
+
+    // Map each property of the message to the number of tokens it contains
+    const propertyTokenCounts = Object.entries(message).map(([key, value]) => {
+      // Count the number of tokens in the property value
+      const numTokens = this.getTokenCount(value);
+
+      // Adjust by `nameAdjustment` tokens if the property key is 'name'
+      const adjustment = (key === 'name') ? nameAdjustment : 0;
+      return numTokens + adjustment;
+    });
+
+    // Sum the number of tokens in all properties and add `tokensPerMessage` for metadata
+    return propertyTokenCounts.reduce((a, b) => a + b, tokensPerMessage);
+  }
+}
+
+module.exports = ChatGPTClient;

api/app/clients/GoogleClient.js

@@ -1,8 +1,6 @@
-const crypto = require('crypto');
-const TextStream = require('../stream');
+const BaseClient = require('./BaseClient');
 const { google } = require('googleapis');
 const { Agent, ProxyAgent } = require('undici');
-const { getMessages, saveMessage, saveConvo } = require('../../models');
 const {
   encoding_for_model: encodingForModel,
   get_encoding: getEncoding
@@ -10,23 +8,36 @@ const {
 
 const tokenizersCache = {};
 
-class GoogleAgent {
+class GoogleClient extends BaseClient {
   constructor(credentials, options = {}) {
+    super('apiKey', options);
     this.client_email = credentials.client_email;
     this.project_id = credentials.project_id;
     this.private_key = credentials.private_key;
+    this.sender = 'PaLM2';
     this.setOptions(options);
-    this.currentDateString = new Date().toLocaleDateString('en-us', {
-      year: 'numeric',
-      month: 'long',
-      day: 'numeric'
-    });
   }
 
+  /* Google/PaLM2 specific methods */
   constructUrl() {
     return `https://us-central1-aiplatform.googleapis.com/v1/projects/${this.project_id}/locations/us-central1/publishers/google/models/${this.modelOptions.model}:predict`;
   }
 
+  async getClient() {
+    const scopes = ['https://www.googleapis.com/auth/cloud-platform'];
+    const jwtClient = new google.auth.JWT(this.client_email, null, this.private_key, scopes);
+
+    jwtClient.authorize((err) => {
+      if (err) {
+        console.log(err);
+        throw err;
+      }
+    });
+
+    return jwtClient;
+  }
+
+  /* Required Client methods */
   setOptions(options) {
     if (this.options && !this.options.replaceOptions) {
       // nested options aren't spread properly, so we need to do this manually
@@ -129,39 +140,19 @@ class GoogleAgent {
     return this;
   }
 
-  static getTokenizer(encoding, isModelName = false, extendSpecialTokens = {}) {
-    if (tokenizersCache[encoding]) {
-      return tokenizersCache[encoding];
-    }
-    let tokenizer;
-    if (isModelName) {
-      tokenizer = encodingForModel(encoding, extendSpecialTokens);
-    } else {
-      tokenizer = getEncoding(encoding, extendSpecialTokens);
-    }
-    tokenizersCache[encoding] = tokenizer;
-    return tokenizer;
+  getMessageMapMethod() {
+    return ((message) => ({
+      author: message?.author ?? (message.isCreatedByUser ? this.userLabel : this.modelLabel),
+      content: message?.content ?? message.text
+    })).bind(this);
   }
 
-  async getClient() {
-    const scopes = ['https://www.googleapis.com/auth/cloud-platform'];
-    const jwtClient = new google.auth.JWT(this.client_email, null, this.private_key, scopes);
-
-    jwtClient.authorize((err) => {
-      if (err) {
-        console.log(err);
-        throw err;
-      }
-    });
-
-    return jwtClient;
-  }
-
-  buildPayload(input, { messages = [] }) {
+  buildMessages(messages = []) {
+    const formattedMessages = messages.map(this.getMessageMapMethod());
     let payload = {
       instances: [
         {
-          messages: [...messages, { author: this.userLabel, content: input }]
+          messages: formattedMessages,
         }
       ],
       parameters: this.options.modelOptions
@@ -175,23 +166,24 @@ class GoogleAgent {
       payload.instances[0].examples = this.options.examples;
     }
 
+    /* TO-DO: text model needs more context since it can't process an array of messages */
     if (this.isTextModel) {
       payload.instances = [
         {
-          prompt: input
+          prompt: messages[messages.length -1].content
         }
       ];
     }
 
     if (this.options.debug) {
-      console.debug('buildPayload');
+      console.debug('GoogleClient buildMessages');
       console.dir(payload, { depth: null });
     }
 
-    return payload;
+    return { prompt: payload };
   }
 
-  async getCompletion(input, messages = [], abortController = null) {
+  async getCompletion(payload, abortController = null) {
     if (!abortController) {
       abortController = new AbortController();
     }
@@ -217,83 +209,27 @@ class GoogleAgent {
     }
 
     const client = await this.getClient();
-    const payload = this.buildPayload(input, { messages });
     const res = await client.request({ url, method: 'POST', data: payload });
     console.dir(res.data, { depth: null });
     return res.data;
   }
 
-  async loadHistory(conversationId, parentMessageId = null) {
-    if (this.options.debug) {
-      console.debug('Loading history for conversation', conversationId, parentMessageId);
-    }
-
-    if (!parentMessageId) {
-      return [];
-    }
-
-    const messages = (await getMessages({ conversationId })) || [];
-
-    if (messages.length === 0) {
-      this.currentMessages = [];
-      return [];
-    }
-
-    const orderedMessages = this.constructor.getMessagesForConversation(messages, parentMessageId);
-    return orderedMessages.map((message) => {
-      return {
-        author: message.isCreatedByUser ? this.userLabel : this.modelLabel,
-        content: message.content
-      };
-    });
-  }
-
-  async saveMessageToDatabase(message, user = null) {
-    await saveMessage({ ...message, unfinished: false });
-    await saveConvo(user, {
-      conversationId: message.conversationId,
-      endpoint: 'google',
+  getSaveOptions() {
+    return {
       ...this.modelOptions
-    });
+    };
   }
 
-  async sendMessage(message, opts = {}) {
-    if (opts && typeof opts === 'object') {
-      this.setOptions(opts);
-    }
-    console.log('sendMessage', message, opts);
+  getBuildMessagesOptions() {
+    // console.log('GoogleClient doesn\'t use getBuildMessagesOptions');
+  }
 
-    const user = opts.user || null;
-    const conversationId = opts.conversationId || crypto.randomUUID();
-    const parentMessageId = opts.parentMessageId || '00000000-0000-0000-0000-000000000000';
-    const userMessageId = opts.overrideParentMessageId || crypto.randomUUID();
-    const responseMessageId = crypto.randomUUID();
-    const messages = await this.loadHistory(conversationId, this.options?.parentMessageId);
-
-    const userMessage = {
-      messageId: userMessageId,
-      parentMessageId,
-      conversationId,
-      sender: 'User',
-      text: message,
-      isCreatedByUser: true
-    };
-
-    if (typeof opts?.getIds === 'function') {
-      opts.getIds({
-        userMessage,
-        conversationId,
-        responseMessageId
-      });
-    }
-
-    console.log('userMessage', userMessage);
-
-    await this.saveMessageToDatabase(userMessage, user);
+  async sendCompletion(payload, opts = {}) {
+    console.log('GoogleClient: sendcompletion', payload, opts);
     let reply = '';
     let blocked = false;
     try {
-      const result = await this.getCompletion(message, messages, opts.abortController);
+      const result = await this.getCompletion(payload, opts.abortController);
       blocked = result?.predictions?.[0]?.safetyAttributes?.blocked;
       reply =
         result?.predictions?.[0]?.candidates?.[0]?.content ||
@@ -312,86 +248,31 @@ class GoogleAgent {
       console.error(err);
     }
 
-    if (this.options.debug) {
-      console.debug('options');
-      console.debug(this.options);
-    }
-
     if (!blocked) {
-      const textStream = new TextStream(reply, { delay: 0.5 });
-      await textStream.processTextStream(opts.onProgress);
+      await this.generateTextStream(reply, opts.onProgress, { delay: 0.5 });
     }
 
-    const responseMessage = {
-      messageId: responseMessageId,
-      conversationId,
-      parentMessageId: userMessage.messageId,
-      sender: 'PaLM2',
-      text: reply,
-      error: blocked,
-      isCreatedByUser: false
-    };
+    return reply.trim();
+  }
 
-    await this.saveMessageToDatabase(responseMessage, user);
-    return responseMessage;
+  /* TO-DO: Handle tokens with Google tokenization NOTE: these are required */
+  static getTokenizer(encoding, isModelName = false, extendSpecialTokens = {}) {
+    if (tokenizersCache[encoding]) {
+      return tokenizersCache[encoding];
+    }
+    let tokenizer;
+    if (isModelName) {
+      tokenizer = encodingForModel(encoding, extendSpecialTokens);
+    } else {
+      tokenizer = getEncoding(encoding, extendSpecialTokens);
+    }
+    tokenizersCache[encoding] = tokenizer;
+    return tokenizer;
   }
 
   getTokenCount(text) {
     return this.gptEncoder.encode(text, 'all').length;
   }
-
-  /**
-   * Algorithm adapted from "6. Counting tokens for chat API calls" of
-   * https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
-   *
-   * An additional 2 tokens need to be added for metadata after all messages have been counted.
-   *
-   * @param {*} message
-   */
-  getTokenCountForMessage(message) {
-    // Map each property of the message to the number of tokens it contains
-    const propertyTokenCounts = Object.entries(message).map(([key, value]) => {
-      // Count the number of tokens in the property value
-      const numTokens = this.getTokenCount(value);
-
-      // Subtract 1 token if the property key is 'name'
-      const adjustment = key === 'name' ? 1 : 0;
-      return numTokens - adjustment;
-    });
-
-    // Sum the number of tokens in all properties and add 4 for metadata
-    return propertyTokenCounts.reduce((a, b) => a + b, 4);
-  }
-
-  /**
-   * Iterate through messages, building an array based on the parentMessageId.
-   * Each message has an id and a parentMessageId. The parentMessageId is the id of the message that this message is a reply to.
-   * @param messages
-   * @param parentMessageId
-   * @returns {*[]} An array containing the messages in the order they should be displayed, starting with the root message.
-   */
-  static getMessagesForConversation(messages, parentMessageId) {
-    const orderedMessages = [];
-    let currentMessageId = parentMessageId;
-    while (currentMessageId) {
-      // eslint-disable-next-line no-loop-func
-      const message = messages.find((m) => m.messageId === currentMessageId);
-      if (!message) {
-        break;
-      }
-      orderedMessages.unshift(message);
-      currentMessageId = message.parentMessageId;
-    }
-
-    if (orderedMessages.length === 0) {
-      return [];
-    }
-
-    return orderedMessages.map((msg) => ({
-      isCreatedByUser: msg.isCreatedByUser,
-      content: msg.text
-    }));
-  }
 }
 
-module.exports = GoogleAgent;
+module.exports = GoogleClient;

api/app/clients/OpenAIClient.js

@@ -0,0 +1,319 @@
+const BaseClient = require('./BaseClient');
+const ChatGPTClient = require('./ChatGPTClient');
+const { encoding_for_model: encodingForModel, get_encoding: getEncoding } = require('@dqbd/tiktoken');
+const { maxTokensMap, genAzureChatCompletion } = require('../../utils');
+
+const tokenizersCache = {};
+
+class OpenAIClient extends BaseClient {
+  constructor(apiKey, options = {}) {
+    super(apiKey, options);
+    this.ChatGPTClient = new ChatGPTClient();
+    this.buildPrompt = this.ChatGPTClient.buildPrompt.bind(this);
+    this.getCompletion = this.ChatGPTClient.getCompletion.bind(this);
+    this.sender = options.sender ?? 'ChatGPT';
+    this.contextStrategy = options.contextStrategy ? options.contextStrategy.toLowerCase() : 'discard';
+    this.shouldRefineContext = this.contextStrategy === 'refine';
+    this.azure = options.azure || false;
+    if (this.azure) {
+      this.azureEndpoint = genAzureChatCompletion(this.azure);
+    }
+    this.setOptions(options);
+  }
+
+  setOptions(options) {
+    if (this.options && !this.options.replaceOptions) {
+      this.options.modelOptions = {
+        ...this.options.modelOptions,
+        ...options.modelOptions,
+      };
+      delete options.modelOptions;
+      this.options = {
+        ...this.options,
+        ...options,
+      };
+    } else {
+      this.options = options;
+    }
+
+    if (this.options.openaiApiKey) {
+      this.apiKey = this.options.openaiApiKey;
+    }
+
+    const modelOptions = this.options.modelOptions || {};
+    if (!this.modelOptions) {
+      this.modelOptions = {
+        ...modelOptions,
+        model: modelOptions.model || 'gpt-3.5-turbo',
+        temperature: typeof modelOptions.temperature === 'undefined' ? 0.8 : modelOptions.temperature,
+        top_p: typeof modelOptions.top_p === 'undefined' ? 1 : modelOptions.top_p,
+        presence_penalty: typeof modelOptions.presence_penalty === 'undefined' ? 1 : modelOptions.presence_penalty,
+        stop: modelOptions.stop,
+      };
+    }
+
+    this.isChatCompletion = this.options.reverseProxyUrl || this.options.localAI || this.modelOptions.model.startsWith('gpt-');
+    this.isChatGptModel = this.isChatCompletion;
+    if (this.modelOptions.model === 'text-davinci-003') {
+      this.isChatCompletion = false;
+      this.isChatGptModel = false;
+    }
+    const { isChatGptModel } = this;
+    this.isUnofficialChatGptModel = this.modelOptions.model.startsWith('text-chat') || this.modelOptions.model.startsWith('text-davinci-002-render');
+    this.maxContextTokens = maxTokensMap[this.modelOptions.model] ?? 4095; // 1 less than maximum
+    this.maxResponseTokens = this.modelOptions.max_tokens || 1024;
+    this.maxPromptTokens = this.options.maxPromptTokens || (this.maxContextTokens - this.maxResponseTokens);
+
+    if (this.maxPromptTokens + this.maxResponseTokens > this.maxContextTokens) {
+      throw new Error(`maxPromptTokens + max_tokens (${this.maxPromptTokens} + ${this.maxResponseTokens} = ${this.maxPromptTokens + this.maxResponseTokens}) must be less than or equal to maxContextTokens (${this.maxContextTokens})`);
+    }
+
+    this.userLabel = this.options.userLabel || 'User';
+    this.chatGptLabel = this.options.chatGptLabel || 'Assistant';
+
+    this.setupTokens();
+    this.setupTokenizer();
+
+    if (!this.modelOptions.stop) {
+      const stopTokens = [this.startToken];
+      if (this.endToken && this.endToken !== this.startToken) {
+        stopTokens.push(this.endToken);
+      }
+      stopTokens.push(`\n${this.userLabel}:`);
+      stopTokens.push('<|diff_marker|>');
+      this.modelOptions.stop = stopTokens;
+    }
+
+    if (this.options.reverseProxyUrl) {
+      this.completionsUrl = this.options.reverseProxyUrl;
+    } else if (isChatGptModel) {
+      this.completionsUrl = 'https://api.openai.com/v1/chat/completions';
+    } else {
+      this.completionsUrl = 'https://api.openai.com/v1/completions';
+    }
+
+    if (this.azureEndpoint) {
+      this.completionsUrl = this.azureEndpoint;
+    }
+
+    if (this.azureEndpoint && this.options.debug) {
+      console.debug(`Using Azure endpoint: ${this.azureEndpoint}`, this.azure);
+    }
+
+    return this;
+  }
+
+  setupTokens() {
+    if (this.isChatCompletion) {
+      this.startToken = '||>';
+      this.endToken = '';
+    } else if (this.isUnofficialChatGptModel) {
+      this.startToken = '<|im_start|>';
+      this.endToken = '<|im_end|>';
+    } else {
+      this.startToken = '||>';
+      this.endToken = '';
+    }
+  }
+
+  setupTokenizer() {
+    this.encoding = 'text-davinci-003';
+    if (this.isChatCompletion) {
+      this.encoding = 'cl100k_base';
+      this.gptEncoder = this.constructor.getTokenizer(this.encoding);
+    } else if (this.isUnofficialChatGptModel) {
+      this.gptEncoder = this.constructor.getTokenizer(this.encoding, true, {
+        '<|im_start|>': 100264,
+        '<|im_end|>': 100265,
+      });
+    } else {
+      try {
+        this.encoding = this.modelOptions.model;
+        this.gptEncoder = this.constructor.getTokenizer(this.modelOptions.model, true);
+      } catch {
+        this.gptEncoder = this.constructor.getTokenizer(this.encoding, true);
+      }
+    }
+  }
+
+  static getTokenizer(encoding, isModelName = false, extendSpecialTokens = {}) {
+    if (tokenizersCache[encoding]) {
+      return tokenizersCache[encoding];
+    }
+    let tokenizer;
+    if (isModelName) {
+      tokenizer = encodingForModel(encoding, extendSpecialTokens);
+    } else {
+      tokenizer = getEncoding(encoding, extendSpecialTokens);
+    }
+    tokenizersCache[encoding] = tokenizer;
+    return tokenizer;
+  }
+
+  freeAndResetEncoder() {
+    try {
+      if (!this.gptEncoder) {
+        return;
+      }
+      this.gptEncoder.free();
+      delete tokenizersCache[this.encoding];
+      delete tokenizersCache.count;
+      this.setupTokenizer();
+    } catch (error) {
+      console.log('freeAndResetEncoder error');
+      console.error(error);
+    }
+  }
+
+  getTokenCount(text) {
+    try {
+      if (tokenizersCache.count >= 25) {
+        if (this.options.debug) {
+          console.debug('freeAndResetEncoder: reached 25 encodings, reseting...');
+        }
+        this.freeAndResetEncoder();
+      }
+      tokenizersCache.count = (tokenizersCache.count || 0) + 1;
+      return this.gptEncoder.encode(text, 'all').length;
+    } catch (error) {
+      this.freeAndResetEncoder();
+      return this.gptEncoder.encode(text, 'all').length;
+    }
+  }
+
+  getSaveOptions() {
+    return {
+      chatGptLabel: this.options.chatGptLabel,
+      promptPrefix: this.options.promptPrefix,
+      ...this.modelOptions
+    };
+  }
+
+  getBuildMessagesOptions(opts) {
+    return {
+      isChatCompletion: this.isChatCompletion,
+      promptPrefix: opts.promptPrefix,
+      abortController: opts.abortController,
+    };
+  }
+
+  async buildMessages(messages, parentMessageId, { isChatCompletion = false, promptPrefix = null }) {
+    if (!isChatCompletion) {
+      return await this.buildPrompt(messages, parentMessageId, { isChatGptModel: isChatCompletion, promptPrefix });
+    }
+
+    let payload;
+    let instructions;
+    let tokenCountMap;
+    let promptTokens;
+    let orderedMessages = this.constructor.getMessagesForConversation(messages, parentMessageId);
+
+    promptPrefix = (promptPrefix || this.options.promptPrefix || '').trim();
+    if (promptPrefix) {
+      promptPrefix = `Instructions:\n${promptPrefix}`;
+      instructions = {
+        role: 'system',
+        name: 'instructions',
+        content: promptPrefix
+      };
+
+      if (this.contextStrategy) {
+        instructions.tokenCount = this.getTokenCountForMessage(instructions);
+      }
+    }
+
+    const formattedMessages = orderedMessages.map((message) => {
+      let { role: _role, sender, text } = message;
+      const role = _role ?? sender;
+      const content = text ?? '';
+      const formattedMessage = {
+        role: role?.toLowerCase() === 'user' ? 'user' : 'assistant',
+        content,
+      };
+
+      if (this.options?.name && formattedMessage.role === 'user') {
+        formattedMessage.name = this.options.name;
+      }
+
+      if (this.contextStrategy) {
+        formattedMessage.tokenCount = message.tokenCount ?? this.getTokenCountForMessage(formattedMessage);
+      }
+
+      return formattedMessage;
+    });
+
+    // TODO: need to handle interleaving instructions better
+    if (this.contextStrategy) {
+      ({ payload, tokenCountMap, promptTokens, messages } =
+        await this.handleContextStrategy({ instructions, orderedMessages, formattedMessages }));
+    }
+
+    const result = {
+      prompt: payload,
+      promptTokens,
+      messages,
+    };
+
+    if (tokenCountMap) {
+      tokenCountMap.instructions = instructions?.tokenCount;
+      result.tokenCountMap = tokenCountMap;
+    }
+
+    return result;
+  }
+
+  async sendCompletion(payload, opts = {}) {
+    let reply = '';
+    let result = null;
+    if (typeof opts.onProgress === 'function') {
+      await this.getCompletion(
+        payload,
+        (progressMessage) => {
+          if (progressMessage === '[DONE]') {
+            return;
+          }
+          const token =
+            this.isChatCompletion ? progressMessage.choices?.[0]?.delta?.content : progressMessage.choices?.[0]?.text;
+          // first event's delta content is always undefined
+          if (!token) {
+            return;
+          }
+          if (this.options.debug) {
+            // console.debug(token);
+          }
+          if (token === this.endToken) {
+            return;
+          }
+          opts.onProgress(token);
+          reply += token;
+        },
+        opts.abortController || new AbortController(),
+      );
+    } else {
+      result = await this.getCompletion(
+        payload,
+        null,
+        opts.abortController || new AbortController(),
+      );
+      if (this.options.debug) {
+        console.debug(JSON.stringify(result));
+      }
+      if (this.isChatCompletion) {
+        reply = result.choices[0].message.content;
+      } else {
+        reply = result.choices[0].text.replace(this.endToken, '');
+      }
+    }
+
+    return reply.trim();
+  }
+
+  getTokenCountForResponse(response) {
+    return this.getTokenCountForMessage({
+      role: 'assistant',
+      content: response.text,
+    });
+  }
+}
+
+module.exports = OpenAIClient;

api/app/clients/PluginsClient.js

@@ -0,0 +1,540 @@
+const OpenAIClient = require('./OpenAIClient');
+const { ChatOpenAI } = require('langchain/chat_models/openai');
+const { CallbackManager } = require('langchain/callbacks');
+const { initializeCustomAgent, initializeFunctionsAgent } = require('./agents/');
+const { loadTools } = require('./tools/util');
+const { SelfReflectionTool } = require('./tools/');
+const { HumanChatMessage, AIChatMessage } = require('langchain/schema');
+const {
+  instructions,
+  imageInstructions,
+  errorInstructions,
+} = require('./prompts/instructions');
+
+class PluginsClient extends OpenAIClient {
+  constructor(apiKey, options = {}) {
+    super(apiKey, options);
+    this.sender = options.sender ?? 'Assistant';
+    this.tools = [];
+    this.actions = [];
+    this.openAIApiKey = apiKey;
+    this.setOptions(options);
+    this.executor = null;
+  }
+
+  getActions(input = null) {
+    let output = 'Internal thoughts & actions taken:\n"';
+    let actions = input || this.actions;
+
+    if (actions[0]?.action && this.functionsAgent) {
+      actions = actions.map((step) => ({
+        log: `Action: ${step.action?.tool || ''}\nInput: ${JSON.stringify(step.action?.toolInput) || ''}\nObservation: ${step.observation}`
+      }));
+    } else if (actions[0]?.action) {
+      actions = actions.map((step) => ({
+        log: `${step.action.log}\nObservation: ${step.observation}`
+      }));
+    }
+
+    actions.forEach((actionObj, index) => {
+      output += `${actionObj.log}`;
+      if (index < actions.length - 1) {
+        output += '\n';
+      }
+    });
+
+    return output + '"';
+  }
+
+  buildErrorInput(message, errorMessage) {
+    const log = errorMessage.includes('Could not parse LLM output:')
+      ? `A formatting error occurred with your response to the human's last message. You didn't follow the formatting instructions. Remember to ${instructions}`
+      : `You encountered an error while replying to the human's last message. Attempt to answer again or admit an answer cannot be given.\nError: ${errorMessage}`;
+
+    return `
+      ${log}
+
+      ${this.getActions()}
+
+      Human's last message: ${message}
+      `;
+  }
+
+  buildPromptPrefix(result, message) {
+    if ((result.output && result.output.includes('N/A')) || result.output === undefined) {
+      return null;
+    }
+
+    if (
+      result?.intermediateSteps?.length === 1 &&
+      result?.intermediateSteps[0]?.action?.toolInput === 'N/A'
+    ) {
+      return null;
+    }
+
+    const internalActions =
+      result?.intermediateSteps?.length > 0
+        ? this.getActions(result.intermediateSteps)
+        : 'Internal Actions Taken: None';
+
+    const toolBasedInstructions = internalActions.toLowerCase().includes('image')
+      ? imageInstructions
+      : '';
+
+    const errorMessage = result.errorMessage ? `${errorInstructions} ${result.errorMessage}\n` : '';
+
+    const preliminaryAnswer =
+      result.output?.length > 0 ? `Preliminary Answer: "${result.output.trim()}"` : '';
+    const prefix = preliminaryAnswer
+      ? 'review and improve the answer you generated using plugins in response to the User Message below. The user hasn\'t seen your answer or thoughts yet.'
+      : 'respond to the User Message below based on your preliminary thoughts & actions.';
+
+    return `As a helpful AI Assistant, ${prefix}${errorMessage}\n${internalActions}
+${preliminaryAnswer}
+Reply conversationally to the User based on your ${
+  preliminaryAnswer ? 'preliminary answer, ' : ''
+}internal actions, thoughts, and observations, making improvements wherever possible, but do not modify URLs.
+${
+  preliminaryAnswer
+    ? ''
+    : '\nIf there is an incomplete thought or action, you are expected to complete it in your response now.\n'
+}You must cite sources if you are using any web links. ${toolBasedInstructions}
+Only respond with your conversational reply to the following User Message:
+"${message}"`;
+  }
+
+  setOptions(options) {
+    this.agentOptions = options.agentOptions;
+    this.functionsAgent = this.agentOptions?.agent === 'functions';
+    this.agentIsGpt3 = this.agentOptions?.model.startsWith('gpt-3');
+    if (this.functionsAgent && this.agentOptions.model) {
+      this.agentOptions.model = this.getFunctionModelName(this.agentOptions.model);
+    }
+
+    super.setOptions(options);
+    this.isGpt3 = this.modelOptions.model.startsWith('gpt-3');
+
+    if (this.reverseProxyUrl) {
+      this.langchainProxy = this.reverseProxyUrl.match(/.*v1/)[0];
+    }
+  }
+
+  getSaveOptions() {
+    return {
+      chatGptLabel: this.options.chatGptLabel,
+      promptPrefix: this.options.promptPrefix,
+      ...this.modelOptions,
+      agentOptions: this.agentOptions,
+    };
+  }
+
+  saveLatestAction(action) {
+    this.actions.push(action);
+  }
+
+  getFunctionModelName(input) {
+    const prefixMap = {
+      'gpt-4': 'gpt-4-0613',
+      'gpt-4-32k': 'gpt-4-32k-0613',
+      'gpt-3.5-turbo': 'gpt-3.5-turbo-0613'
+    };
+
+    const prefix = Object.keys(prefixMap).find(key => input.startsWith(key));
+    return prefix ? prefixMap[prefix] : 'gpt-3.5-turbo-0613';
+  }
+
+  getBuildMessagesOptions(opts) {
+    return {
+      isChatCompletion: true,
+      promptPrefix: opts.promptPrefix,
+      abortController: opts.abortController,
+    };
+  }
+
+  createLLM(modelOptions, configOptions) {
+    let credentials = { openAIApiKey: this.openAIApiKey };
+    let configuration = {
+      apiKey: this.openAIApiKey,
+    };
+
+    if (this.azure) {
+      credentials = {};
+      configuration = {};
+    }
+
+    if (this.options.debug) {
+      console.debug('createLLM: configOptions');
+      console.debug(configOptions);
+    }
+
+    return new ChatOpenAI({ credentials, configuration, ...modelOptions }, configOptions);
+  }
+
+  async initialize({ user, message, onAgentAction, onChainEnd, signal }) {
+    const modelOptions = {
+      modelName: this.agentOptions.model,
+      temperature: this.agentOptions.temperature
+    };
+
+    const configOptions = {};
+
+    if (this.langchainProxy) {
+      configOptions.basePath = this.langchainProxy;
+    }
+
+    const model = this.createLLM(modelOptions, configOptions);
+
+    if (this.options.debug) {
+      console.debug(`<-----Agent Model: ${model.modelName} | Temp: ${model.temperature}----->`);
+    }
+
+    this.availableTools = await loadTools({
+      user,
+      model,
+      tools: this.options.tools,
+      functions: this.functionsAgent,
+      options: {
+        openAIApiKey: this.openAIApiKey
+      }
+    });
+    // load tools
+    for (const tool of this.options.tools) {
+      const validTool = this.availableTools[tool];
+
+      if (tool === 'plugins') {
+        const plugins = await validTool();
+        this.tools = [...this.tools, ...plugins];
+      } else if (validTool) {
+        this.tools.push(await validTool());
+      }
+    }
+
+    if (this.options.debug) {
+      console.debug('Requested Tools');
+      console.debug(this.options.tools);
+      console.debug('Loaded Tools');
+      console.debug(this.tools.map((tool) => tool.name));
+    }
+
+    if (this.tools.length > 0 && !this.functionsAgent) {
+      this.tools.push(new SelfReflectionTool({ message, isGpt3: false }));
+    } else if (this.tools.length === 0) {
+      return;
+    }
+
+    const handleAction = (action, callback = null) => {
+      this.saveLatestAction(action);
+
+      if (this.options.debug) {
+        console.debug('Latest Agent Action ', this.actions[this.actions.length - 1]);
+      }
+
+      if (typeof callback === 'function') {
+        callback(action);
+      }
+    };
+
+    // Map Messages to Langchain format
+    const pastMessages = this.currentMessages.slice(0, -1).map(
+      msg => msg?.isCreatedByUser || msg?.role?.toLowerCase() === 'user'
+        ? new HumanChatMessage(msg.text)
+        : new AIChatMessage(msg.text));
+
+    // initialize agent
+    const initializer = this.functionsAgent ? initializeFunctionsAgent : initializeCustomAgent;
+    this.executor = await initializer({
+      model,
+      signal,
+      pastMessages,
+      tools: this.tools,
+      currentDateString: this.currentDateString,
+      verbose: this.options.debug,
+      returnIntermediateSteps: true,
+      callbackManager: CallbackManager.fromHandlers({
+        async handleAgentAction(action) {
+          handleAction(action, onAgentAction);
+        },
+        async handleChainEnd(action) {
+          if (typeof onChainEnd === 'function') {
+            onChainEnd(action);
+          }
+        }
+      })
+    });
+
+    if (this.options.debug) {
+      console.debug('Loaded agent.');
+    }
+  }
+
+  async executorCall(message, signal) {
+    let errorMessage = '';
+    const maxAttempts = 1;
+
+    for (let attempts = 1; attempts <= maxAttempts; attempts++) {
+      const errorInput = this.buildErrorInput(message, errorMessage);
+      const input = attempts > 1 ? errorInput : message;
+
+      if (this.options.debug) {
+        console.debug(`Attempt ${attempts} of ${maxAttempts}`);
+      }
+
+      if (this.options.debug && errorMessage.length > 0) {
+        console.debug('Caught error, input:', input);
+      }
+
+      try {
+        this.result = await this.executor.call({ input, signal });
+        break; // Exit the loop if the function call is successful
+      } catch (err) {
+        console.error(err);
+        errorMessage = err.message;
+        if (attempts === maxAttempts) {
+          this.result.output = `Encountered an error while attempting to respond. Error: ${err.message}`;
+          this.result.intermediateSteps = this.actions;
+          this.result.errorMessage = errorMessage;
+          break;
+        }
+      }
+    }
+  }
+
+  addImages(intermediateSteps, responseMessage) {
+    if (!intermediateSteps || !responseMessage) {
+      return;
+    }
+
+    intermediateSteps.forEach(step => {
+      const { observation } = step;
+      if (!observation || !observation.includes('![')) {
+        return;
+      }
+
+      if (!responseMessage.text.includes(observation)) {
+        responseMessage.text += '\n' + observation;
+        if (this.options.debug) {
+          console.debug('added image from intermediateSteps');
+        }
+      }
+    });
+  }
+
+  async handleResponseMessage(responseMessage, saveOptions, user) {
+    responseMessage.tokenCount = this.getTokenCountForResponse(responseMessage);
+    responseMessage.completionTokens = responseMessage.tokenCount;
+    await this.saveMessageToDatabase(responseMessage, saveOptions, user);
+    delete responseMessage.tokenCount;
+    return { ...responseMessage, ...this.result };
+  }
+
+  async sendMessage(message, opts = {}) {
+    const completionMode = this.options.tools.length === 0;
+    if (completionMode) {
+      this.setOptions(opts);
+      return super.sendMessage(message, opts);
+    }
+    console.log('Plugins sendMessage', message, opts);
+    const {
+      user,
+      conversationId,
+      responseMessageId,
+      saveOptions,
+      userMessage,
+      onAgentAction,
+      onChainEnd,
+    } = await this.handleStartMethods(message, opts);
+
+    this.currentMessages.push(userMessage);
+
+    let { prompt: payload, tokenCountMap, promptTokens, messages } = await this.buildMessages(
+      this.currentMessages,
+      userMessage.messageId,
+      this.getBuildMessagesOptions({
+        promptPrefix: null,
+        abortController: this.abortController,
+      }),
+    );
+
+    if (tokenCountMap) {
+      console.dir(tokenCountMap, { depth: null })
+      if (tokenCountMap[userMessage.messageId]) {
+        userMessage.tokenCount = tokenCountMap[userMessage.messageId];
+        console.log('userMessage.tokenCount', userMessage.tokenCount);
+      }
+      payload = payload.map((message) => {
+        const messageWithoutTokenCount = message;
+        delete messageWithoutTokenCount.tokenCount;
+        return messageWithoutTokenCount;
+      });
+      this.handleTokenCountMap(tokenCountMap);
+    }
+
+    this.result = {};
+    if (messages) {
+      this.currentMessages = messages;
+    }
+    await this.saveMessageToDatabase(userMessage, saveOptions, user);
+    const responseMessage = {
+      messageId: responseMessageId,
+      conversationId,
+      parentMessageId: userMessage.messageId,
+      isCreatedByUser: false,
+      model: this.modelOptions.model,
+      sender: this.sender,
+      promptTokens,
+    };
+
+    await this.initialize({
+      user,
+      message,
+      onAgentAction,
+      onChainEnd,
+      signal: this.abortController.signal
+    });
+    await this.executorCall(message, this.abortController.signal);
+
+    // If message was aborted mid-generation
+    if (this.result?.errorMessage?.length > 0 && this.result?.errorMessage?.includes('cancel')) {
+      responseMessage.text = 'Cancelled.';
+      return await this.handleResponseMessage(responseMessage, saveOptions, user);
+    }
+
+    if (this.agentOptions.skipCompletion && this.result.output) {
+      responseMessage.text = this.result.output;
+      this.addImages(this.result.intermediateSteps, responseMessage);
+      await this.generateTextStream(this.result.output, opts.onProgress);
+      return await this.handleResponseMessage(responseMessage, saveOptions, user);
+    }
+
+    if (this.options.debug) {
+      console.debug('Plugins completion phase: this.result');
+      console.debug(this.result);
+    }
+
+    const promptPrefix = this.buildPromptPrefix(this.result, message);
+
+    if (this.options.debug) {
+      console.debug('Plugins: promptPrefix');
+      console.debug(promptPrefix);
+    }
+
+    payload = await this.buildCompletionPrompt({
+      messages: this.currentMessages,
+      promptPrefix,
+    });
+
+    if (this.options.debug) {
+      console.debug('buildCompletionPrompt Payload');
+      console.debug(payload);
+    }
+    responseMessage.text = await this.sendCompletion(payload, opts);
+    return await this.handleResponseMessage(responseMessage, saveOptions, user);
+  }
+
+  async buildCompletionPrompt({ messages, promptPrefix: _promptPrefix }) {
+    if (this.options.debug) {
+      console.debug('buildCompletionPrompt messages', messages);
+    }
+
+    const orderedMessages = messages;
+    let promptPrefix = _promptPrefix.trim();
+    // If the prompt prefix doesn't end with the end token, add it.
+    if (!promptPrefix.endsWith(`${this.endToken}`)) {
+      promptPrefix = `${promptPrefix.trim()}${this.endToken}\n\n`;
+    }
+    promptPrefix = `${this.startToken}Instructions:\n${promptPrefix}`;
+    const promptSuffix = `${this.startToken}${this.chatGptLabel ?? 'Assistant'}:\n`;
+
+    const instructionsPayload = {
+      role: 'system',
+      name: 'instructions',
+      content: promptPrefix
+    };
+
+    const messagePayload = {
+      role: 'system',
+      content: promptSuffix
+    };
+
+    if (this.isGpt3) {
+      instructionsPayload.role = 'user';
+      messagePayload.role = 'user';
+      instructionsPayload.content += `\n${promptSuffix}`;
+    }
+
+    // testing if this works with browser endpoint
+    if (!this.isGpt3 && this.reverseProxyUrl) {
+      instructionsPayload.role = 'user';
+    }
+
+    let currentTokenCount =
+        this.getTokenCountForMessage(instructionsPayload) +
+        this.getTokenCountForMessage(messagePayload);
+
+    let promptBody = '';
+    const maxTokenCount = this.maxPromptTokens;
+    // Iterate backwards through the messages, adding them to the prompt until we reach the max token count.
+    // Do this within a recursive async function so that it doesn't block the event loop for too long.
+    const buildPromptBody = async () => {
+      if (currentTokenCount < maxTokenCount && orderedMessages.length > 0) {
+        const message = orderedMessages.pop();
+        const isCreatedByUser = message.isCreatedByUser || message.role?.toLowerCase() === 'user';
+        const roleLabel = isCreatedByUser ? this.userLabel : this.chatGptLabel;
+        let messageString = `${this.startToken}${roleLabel}:\n${message.text}${this.endToken}\n`;
+        let newPromptBody = `${messageString}${promptBody}`;
+
+        const tokenCountForMessage = this.getTokenCount(messageString);
+        const newTokenCount = currentTokenCount + tokenCountForMessage;
+        if (newTokenCount > maxTokenCount) {
+          if (promptBody) {
+            // This message would put us over the token limit, so don't add it.
+            return false;
+          }
+          // This is the first message, so we can't add it. Just throw an error.
+          throw new Error(
+            `Prompt is too long. Max token count is ${maxTokenCount}, but prompt is ${newTokenCount} tokens long.`
+          );
+        }
+        promptBody = newPromptBody;
+        currentTokenCount = newTokenCount;
+        // wait for next tick to avoid blocking the event loop
+        await new Promise((resolve) => setTimeout(resolve, 0));
+        return buildPromptBody();
+      }
+      return true;
+    };
+
+    await buildPromptBody();
+    const prompt = promptBody;
+    messagePayload.content = prompt;
+    // Add 2 tokens for metadata after all messages have been counted.
+    currentTokenCount += 2;
+
+    if (this.isGpt3 && messagePayload.content.length > 0) {
+      const context = 'Chat History:\n';
+      messagePayload.content = `${context}${prompt}`;
+      currentTokenCount += this.getTokenCount(context);
+    }
+
+    // Use up to `this.maxContextTokens` tokens (prompt + response), but try to leave `this.maxTokens` tokens for the response.
+    this.modelOptions.max_tokens = Math.min(
+      this.maxContextTokens - currentTokenCount,
+      this.maxResponseTokens
+    );
+
+    if (this.isGpt3) {
+      messagePayload.content += promptSuffix;
+      return [instructionsPayload, messagePayload];
+    }
+
+    const result = [messagePayload, instructionsPayload];
+
+    if (this.functionsAgent && !this.isGpt3) {
+      result[1].content = `${result[1].content}\n${this.startToken}${this.chatGptLabel}:\nSure thing! Here is the output you requested:\n`;
+    }
+
+    return result.filter((message) => message.content.length > 0);
+  }
+}
+
+module.exports = PluginsClient;

api/app/clients/agents/CustomAgent/initializeCustomAgent.js

@@ -51,6 +51,4 @@ Query: {input}
   return AgentExecutor.fromAgentAndTools({ agent, tools, memory, ...rest });
 };
 
-module.exports = {
-  initializeCustomAgent
-};
+module.exports = initializeCustomAgent;

api/app/clients/agents/CustomAgent/outputParser.js

@@ -102,8 +102,8 @@ class CustomOutputParser extends ZeroShotAgentOutputParser {
         match
       );
       selectedTool = this.getValidTool(selectedTool);
-    } 
-    
+    }
+
     if (match && !selectedTool) {
       console.log(
         '\n\n<----------------------HIT INVALID TOOL PARSING ERROR---------------------->\n\n',

api/app/clients/agents/Functions/FunctionsAgent.js

@@ -0,0 +1,120 @@
+const { Agent } = require('langchain/agents');
+const { LLMChain } = require('langchain/chains');
+const { FunctionChatMessage, AIChatMessage } = require('langchain/schema');
+const {
+  ChatPromptTemplate,
+  MessagesPlaceholder,
+  SystemMessagePromptTemplate,
+  HumanMessagePromptTemplate
+} = require('langchain/prompts');
+const PREFIX = `You are a helpful AI assistant.`;
+
+function parseOutput(message) {
+  if (message.additional_kwargs.function_call) {
+    const function_call = message.additional_kwargs.function_call;
+    return {
+      tool: function_call.name,
+      toolInput: function_call.arguments ? JSON.parse(function_call.arguments) : {},
+      log: message.text
+    };
+  } else {
+    return { returnValues: { output: message.text }, log: message.text };
+  }
+}
+
+class FunctionsAgent extends Agent {
+  constructor(input) {
+    super({ ...input, outputParser: undefined });
+    this.tools = input.tools;
+  }
+
+  lc_namespace = ['langchain', 'agents', 'openai'];
+
+  _agentType() {
+    return 'openai-functions';
+  }
+
+  observationPrefix() {
+    return 'Observation: ';
+  }
+
+  llmPrefix() {
+    return 'Thought:';
+  }
+
+  _stop() {
+    return ['Observation:'];
+  }
+
+  static createPrompt(_tools, fields) {
+    const { prefix = PREFIX, currentDateString } = fields || {};
+
+    return ChatPromptTemplate.fromPromptMessages([
+      SystemMessagePromptTemplate.fromTemplate(`Date: ${currentDateString}\n${prefix}`),
+      new MessagesPlaceholder('chat_history'),
+      HumanMessagePromptTemplate.fromTemplate(`Query: {input}`),
+      new MessagesPlaceholder('agent_scratchpad'),
+    ]);
+  }
+
+  static fromLLMAndTools(llm, tools, args) {
+    FunctionsAgent.validateTools(tools);
+    const prompt = FunctionsAgent.createPrompt(tools, args);
+    const chain = new LLMChain({
+      prompt,
+      llm,
+      callbacks: args?.callbacks
+    });
+    return new FunctionsAgent({
+      llmChain: chain,
+      allowedTools: tools.map((t) => t.name),
+      tools
+    });
+  }
+
+  async constructScratchPad(steps) {
+    return steps.flatMap(({ action, observation }) => [
+      new AIChatMessage('', {
+        function_call: {
+          name: action.tool,
+          arguments: JSON.stringify(action.toolInput)
+        }
+      }),
+      new FunctionChatMessage(observation, action.tool)
+    ]);
+  }
+
+  async plan(steps, inputs, callbackManager) {
+    // Add scratchpad and stop to inputs
+    const thoughts = await this.constructScratchPad(steps);
+    const newInputs = Object.assign({}, inputs, { agent_scratchpad: thoughts });
+    if (this._stop().length !== 0) {
+      newInputs.stop = this._stop();
+    }
+
+    // Split inputs between prompt and llm
+    const llm = this.llmChain.llm;
+    const valuesForPrompt = Object.assign({}, newInputs);
+    const valuesForLLM = {
+      tools: this.tools
+    };
+    for (let i = 0; i < this.llmChain.llm.callKeys.length; i++) {
+      const key = this.llmChain.llm.callKeys[i];
+      if (key in inputs) {
+        valuesForLLM[key] = inputs[key];
+        delete valuesForPrompt[key];
+      }
+    }
+
+    const promptValue = await this.llmChain.prompt.formatPromptValue(valuesForPrompt);
+    const message = await llm.predictMessages(
+      promptValue.toChatMessages(),
+      valuesForLLM,
+      callbackManager
+    );
+    console.log('message', message);
+    return parseOutput(message);
+  }
+}
+
+module.exports = FunctionsAgent;

api/app/clients/agents/Functions/initializeFunctionsAgent.js

@@ -0,0 +1,35 @@
+const { initializeAgentExecutorWithOptions } = require('langchain/agents');
+const { BufferMemory, ChatMessageHistory } = require('langchain/memory');
+
+const initializeFunctionsAgent = async ({
+  tools,
+  model,
+  pastMessages,
+  // currentDateString,
+  ...rest
+}) => {
+
+  const memory = new BufferMemory({
+    chatHistory: new ChatMessageHistory(pastMessages),
+    memoryKey: 'chat_history',
+    humanPrefix: 'User',
+    aiPrefix: 'Assistant',
+    inputKey: 'input',
+    outputKey: 'output',
+    returnMessages: true,
+  });
+
+  return await initializeAgentExecutorWithOptions(
+    tools,
+    model,
+    {
+      agentType: 'openai-functions',
+      memory,
+      ...rest,
+    }
+  );
+
+};
+
+module.exports = initializeFunctionsAgent;
+

api/app/clients/agents/index.js

@@ -0,0 +1,7 @@
+const initializeCustomAgent = require('./CustomAgent/initializeCustomAgent');
+const initializeFunctionsAgent = require('./Functions/initializeFunctionsAgent');
+
+module.exports = {
+  initializeCustomAgent,
+  initializeFunctionsAgent
+};

api/app/clients/chatgpt-client.js

@@ -1,94 +0,0 @@
-require('dotenv').config();
-const { KeyvFile } = require('keyv-file');
-const { genAzureChatCompletion } = require('../../utils/genAzureEndpoints');
-const tiktoken = require('@dqbd/tiktoken');
-const tiktokenModels = require('../../utils/tiktokenModels');
-const encoding_for_model = tiktoken.encoding_for_model;
-
-const askClient = async ({
-  text,
-  parentMessageId,
-  conversationId,
-  model,
-  oaiApiKey,
-  chatGptLabel,
-  promptPrefix,
-  temperature,
-  top_p,
-  presence_penalty,
-  frequency_penalty,
-  onProgress,
-  abortController,
-  userId
-}) => {
-  const { ChatGPTClient } = await import('@waylaidwanderer/chatgpt-api');
-  const store = {
-    store: new KeyvFile({ filename: './data/cache.json' })
-  };
-
-  const azure = process.env.AZURE_OPENAI_API_KEY ? true : false;
-  let promptText = 'You are ChatGPT, a large language model trained by OpenAI.';
-  if (promptPrefix) {
-    promptText = promptPrefix;
-  }
-  const maxContextTokens = model === 'gpt-4-32k' ? 32767 : model.startsWith('gpt-4') ? 8191 : 4095; // 1 less than maximum
-  const clientOptions = {
-    reverseProxyUrl: process.env.OPENAI_REVERSE_PROXY || null,
-    azure,
-    maxContextTokens,
-    modelOptions: {
-      model,
-      temperature,
-      top_p,
-      presence_penalty,
-      frequency_penalty
-    },
-    chatGptLabel,
-    promptPrefix,
-    proxy: process.env.PROXY || null
-    // debug: true
-  };
-
-  let apiKey = oaiApiKey ? oaiApiKey : process.env.OPENAI_API_KEY || null;
-
-  if (azure) {
-    apiKey = oaiApiKey ? oaiApiKey : process.env.AZURE_OPENAI_API_KEY || null;
-    clientOptions.reverseProxyUrl = genAzureChatCompletion({
-      azureOpenAIApiInstanceName: process.env.AZURE_OPENAI_API_INSTANCE_NAME,
-      azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME,
-      azureOpenAIApiVersion: process.env.AZURE_OPENAI_API_VERSION
-    });
-  }
-
-  const client = new ChatGPTClient(apiKey, clientOptions, store);
-
-  const options = {
-    onProgress,
-    abortController,
-    ...(parentMessageId && conversationId ? { parentMessageId, conversationId } : {})
-  };
-
-  let usage = {};
-  let enc = null;
-  try {
-    enc = encoding_for_model(tiktokenModels.has(model) ? model : 'gpt-3.5-turbo');
-    usage.prompt_tokens = (enc.encode(promptText)).length + (enc.encode(text)).length;
-  } catch (e) {
-    console.log('Error encoding prompt text', e);
-  }
-  
-  const res = await client.sendMessage(text, { ...options, userId });
-
-  try {
-    usage.completion_tokens = (enc.encode(res.response)).length;
-    enc.free();
-    usage.total_tokens = usage.prompt_tokens + usage.completion_tokens;
-    res.usage = usage;
-  } catch (e) {
-    console.log('Error encoding response text', e);
-  }
-  
-  return res;
-};
-
-module.exports = { askClient };

api/app/clients/index.js

@@ -0,0 +1,15 @@
+const ChatGPTClient = require('./ChatGPTClient');
+const OpenAIClient = require('./OpenAIClient');
+const PluginsClient = require('./PluginsClient');
+const GoogleClient = require('./GoogleClient');
+const TextStream = require('./TextStream');
+const toolUtils = require('./tools/util');
+
+module.exports = {
+  ChatGPTClient,
+  OpenAIClient,
+  PluginsClient,
+  GoogleClient,
+  TextStream,
+  ...toolUtils
+};

api/app/clients/prompts/refinePrompt.js

@@ -0,0 +1,24 @@
+const { PromptTemplate } = require('langchain/prompts');
+
+const refinePromptTemplate = `Your job is to produce a final summary of the following conversation.
+We have provided an existing summary up to a certain point: "{existing_answer}"
+We have the opportunity to refine the existing summary
+(only if needed) with some more context below.
+------------
+"{text}"
+------------
+
+Given the new context, refine the original summary of the conversation.
+Do note who is speaking in the conversation to give proper context.
+If the context isn't useful, return the original summary.
+
+REFINED CONVERSATION SUMMARY:`;
+
+const refinePrompt = new PromptTemplate({
+  template: refinePromptTemplate,
+  inputVariables: ["existing_answer", "text"],
+});
+
+module.exports = {
+  refinePrompt,
+};

api/app/clients/specs/BaseClient.test.js

@@ -0,0 +1,371 @@
+const { initializeFakeClient } = require('./FakeClient');
+
+jest.mock('../../../lib/db/connectDb');
+jest.mock('../../../models', () => {
+  return function () {
+    return {
+      save: jest.fn(),
+      deleteConvos: jest.fn(),
+      getConvo: jest.fn(),
+      getMessages: jest.fn(),
+      saveMessage: jest.fn(),
+      updateMessage: jest.fn(),
+      saveConvo: jest.fn()
+    };
+  };
+});
+
+jest.mock('langchain/text_splitter', () => {
+  return {
+    RecursiveCharacterTextSplitter: jest.fn().mockImplementation(() => {
+      return { createDocuments: jest.fn().mockResolvedValue([]) };
+    }),
+  };
+});
+
+jest.mock('langchain/chat_models/openai', () => {
+  return {
+    ChatOpenAI: jest.fn().mockImplementation(() => {
+      return {};
+    }),
+  };
+});
+
+jest.mock('langchain/chains', () => {
+  return {
+    loadSummarizationChain: jest.fn().mockReturnValue({
+      call: jest.fn().mockResolvedValue({ output_text: 'Refined answer' }),
+    }),
+  };
+});
+
+let parentMessageId;
+let conversationId;
+const fakeMessages = [];
+const userMessage = 'Hello, ChatGPT!';
+const apiKey = 'fake-api-key';
+
+describe('BaseClient', () => {
+  let TestClient;
+  const options = {
+    // debug: true,
+    modelOptions: {
+      model: 'gpt-3.5-turbo',
+      temperature: 0,
+    }
+  };
+
+  beforeEach(() => {
+    TestClient = initializeFakeClient(apiKey, options, fakeMessages);
+  });
+
+  test('returns the input messages without instructions when addInstructions() is called with empty instructions', () => {
+    const messages = [
+      { content: 'Hello' },
+      { content: 'How are you?' },
+      { content: 'Goodbye' },
+    ];
+    const instructions = '';
+    const result = TestClient.addInstructions(messages, instructions);
+    expect(result).toEqual(messages);
+  });
+
+  test('returns the input messages with instructions properly added when addInstructions() is called with non-empty instructions', () => {
+    const messages = [
+      { content: 'Hello' },
+      { content: 'How are you?' },
+      { content: 'Goodbye' },
+    ];
+    const instructions = { content: 'Please respond to the question.' };
+    const result = TestClient.addInstructions(messages, instructions);
+    const expected = [
+      { content: 'Hello' },
+      { content: 'How are you?' },
+      { content: 'Please respond to the question.' },
+      { content: 'Goodbye' },
+    ];
+    expect(result).toEqual(expected);
+  });
+
+  test('concats messages correctly in concatenateMessages()', () => {
+    const messages = [
+      { name: 'User', content: 'Hello' },
+      { name: 'Assistant', content: 'How can I help you?' },
+      { name: 'User', content: 'I have a question.' },
+    ];
+    const result = TestClient.concatenateMessages(messages);
+    const expected = `User:\nHello\n\nAssistant:\nHow can I help you?\n\nUser:\nI have a question.\n\n`;
+    expect(result).toBe(expected);
+  });
+
+  test('refines messages correctly in refineMessages()', async () => {
+    const messagesToRefine = [
+      { role: 'user', content: 'Hello', tokenCount: 10 },
+      { role: 'assistant', content: 'How can I help you?', tokenCount: 20 }
+    ];
+    const remainingContextTokens = 100;
+    const expectedRefinedMessage = {
+      role: 'assistant',
+      content: 'Refined answer',
+      tokenCount: 14 // 'Refined answer'.length
+    };
+
+    const result = await TestClient.refineMessages(messagesToRefine, remainingContextTokens);
+    expect(result).toEqual(expectedRefinedMessage);
+  });
+
+  test('gets messages within token limit (under limit) correctly in getMessagesWithinTokenLimit()', async () => {
+    TestClient.maxContextTokens = 100;
+    TestClient.shouldRefineContext = true;
+    TestClient.refineMessages = jest.fn().mockResolvedValue({
+      role: 'assistant',
+      content: 'Refined answer',
+      tokenCount: 30
+    });
+
+    const messages = [
+      { role: 'user', content: 'Hello', tokenCount: 5 },
+      { role: 'assistant', content: 'How can I help you?', tokenCount: 19 },
+      { role: 'user', content: 'I have a question.', tokenCount: 18 },
+    ];
+    const expectedContext = [
+      { role: 'user', content: 'Hello', tokenCount: 5 }, // 'Hello'.length
+      { role: 'assistant', content: 'How can I help you?', tokenCount: 19 },
+      { role: 'user', content: 'I have a question.', tokenCount: 18 },
+    ];
+    const expectedRemainingContextTokens = 58; // 100 - 5 - 19 - 18
+    const expectedMessagesToRefine = [];
+
+    const result = await TestClient.getMessagesWithinTokenLimit(messages);
+    expect(result.context).toEqual(expectedContext);
+    expect(result.remainingContextTokens).toBe(expectedRemainingContextTokens);
+    expect(result.messagesToRefine).toEqual(expectedMessagesToRefine);
+  });
+
+  test('gets messages within token limit (over limit) correctly in getMessagesWithinTokenLimit()', async () => {
+    TestClient.maxContextTokens = 50; // Set a lower limit
+    TestClient.shouldRefineContext = true;
+    TestClient.refineMessages = jest.fn().mockResolvedValue({
+      role: 'assistant',
+      content: 'Refined answer',
+      tokenCount: 4
+    });
+
+    const messages = [
+      { role: 'user', content: 'I need a coffee, stat!', tokenCount: 30 },
+      { role: 'assistant', content: 'Sure, I can help with that.', tokenCount: 30 },
+      { role: 'user', content: 'Hello', tokenCount: 5 },
+      { role: 'assistant', content: 'How can I help you?', tokenCount: 19 },
+      { role: 'user', content: 'I have a question.', tokenCount: 18 },
+    ];
+    const expectedContext = [
+      { role: 'user', content: 'Hello', tokenCount: 5 },
+      { role: 'assistant', content: 'How can I help you?', tokenCount: 19 },
+      { role: 'user', content: 'I have a question.', tokenCount: 18 },
+    ];
+    const expectedRemainingContextTokens = 8; // 50 - 18 - 19 - 5
+    const expectedMessagesToRefine = [
+      { role: 'user', content: 'I need a coffee, stat!', tokenCount: 30 },
+      { role: 'assistant', content: 'Sure, I can help with that.', tokenCount: 30 },
+    ];
+
+    const result = await TestClient.getMessagesWithinTokenLimit(messages);
+    expect(result.context).toEqual(expectedContext);
+    expect(result.remainingContextTokens).toBe(expectedRemainingContextTokens);
+    expect(result.messagesToRefine).toEqual(expectedMessagesToRefine);
+  });
+
+  test('handles context strategy correctly in handleContextStrategy()', async () => {
+    TestClient.addInstructions = jest.fn().mockReturnValue([
+      { content: 'Hello' },
+      { content: 'How can I help you?' },
+      { content: 'Please provide more details.' },
+      { content: 'I can assist you with that.' }
+    ]);
+    TestClient.getMessagesWithinTokenLimit = jest.fn().mockReturnValue({
+      context: [
+        { content: 'How can I help you?' },
+        { content: 'Please provide more details.' },
+        { content: 'I can assist you with that.' }
+      ],
+      remainingContextTokens: 80,
+      messagesToRefine: [
+        { content: 'Hello' },
+      ],
+      refineIndex: 3,
+    });
+    TestClient.refineMessages = jest.fn().mockResolvedValue({
+      role: 'assistant',
+      content: 'Refined answer',
+      tokenCount: 30
+    });
+    TestClient.getTokenCountForResponse = jest.fn().mockReturnValue(40);
+
+    const instructions = { content: 'Please provide more details.' };
+    const orderedMessages = [
+      { content: 'Hello' },
+      { content: 'How can I help you?' },
+      { content: 'Please provide more details.' },
+      { content: 'I can assist you with that.' }
+    ];
+    const formattedMessages = [
+      { content: 'Hello' },
+      { content: 'How can I help you?' },
+      { content: 'Please provide more details.' },
+      { content: 'I can assist you with that.' }
+    ];
+    const expectedResult = {
+      payload: [
+        {
+          content: 'Refined answer',
+          role: 'assistant',
+          tokenCount: 30
+        },
+        { content: 'How can I help you?' },
+        { content: 'Please provide more details.' },
+        { content: 'I can assist you with that.' }
+      ],
+      promptTokens: expect.any(Number),
+      tokenCountMap: {},
+      messages: expect.any(Array),
+    };
+
+    const result = await TestClient.handleContextStrategy({
+      instructions,
+      orderedMessages,
+      formattedMessages,
+    });
+    expect(result).toEqual(expectedResult);
+  });
+
+  describe('sendMessage', () => {
+    test('sendMessage should return a response message', async () => {
+      const expectedResult = expect.objectContaining({
+        sender: TestClient.sender,
+        text: expect.any(String),
+        isCreatedByUser: false,
+        messageId: expect.any(String),
+        parentMessageId: expect.any(String),
+        conversationId: expect.any(String)
+      });
+
+      const response = await TestClient.sendMessage(userMessage);
+      parentMessageId = response.messageId;
+      conversationId = response.conversationId;
+      expect(response).toEqual(expectedResult);
+    });
+
+    test('sendMessage should work with provided conversationId and parentMessageId', async () => {
+      const userMessage = 'Second message in the conversation';
+      const opts = {
+        conversationId,
+        parentMessageId,
+        getIds: jest.fn(),
+        onStart: jest.fn()
+      };
+
+      const expectedResult = expect.objectContaining({
+        sender: TestClient.sender,
+        text: expect.any(String),
+        isCreatedByUser: false,
+        messageId: expect.any(String),
+        parentMessageId: expect.any(String),
+        conversationId: opts.conversationId
+      });
+
+      const response = await TestClient.sendMessage(userMessage, opts);
+      parentMessageId = response.messageId;
+      expect(response.conversationId).toEqual(conversationId);
+      expect(response).toEqual(expectedResult);
+      expect(opts.getIds).toHaveBeenCalled();
+      expect(opts.onStart).toHaveBeenCalled();
+      expect(TestClient.getBuildMessagesOptions).toHaveBeenCalled();
+      expect(TestClient.getSaveOptions).toHaveBeenCalled();
+    });
+
+    test('should return chat history', async () => {
+      const chatMessages = await TestClient.loadHistory(conversationId, parentMessageId);
+      expect(TestClient.currentMessages).toHaveLength(4);
+      expect(chatMessages[0].text).toEqual(userMessage);
+    });
+
+    test('setOptions is called with the correct arguments', async () => {
+      TestClient.setOptions = jest.fn();
+      const opts = { conversationId: '123', parentMessageId: '456' };
+      await TestClient.sendMessage('Hello, world!', opts);
+      expect(TestClient.setOptions).toHaveBeenCalledWith(opts);
+      TestClient.setOptions.mockClear();
+    });
+
+    test('loadHistory is called with the correct arguments', async () => {
+      const opts = { conversationId: '123', parentMessageId: '456' };
+      await TestClient.sendMessage('Hello, world!', opts);
+      expect(TestClient.loadHistory).toHaveBeenCalledWith(opts.conversationId, opts.parentMessageId);
+    });
+
+    test('getIds is called with the correct arguments', async () => {
+      const getIds = jest.fn();
+      const opts = { getIds };
+      const response = await TestClient.sendMessage('Hello, world!', opts);
+      expect(getIds).toHaveBeenCalledWith({
+        userMessage: expect.objectContaining({ text: 'Hello, world!' }),
+        conversationId: response.conversationId,
+        responseMessageId: response.messageId
+      });
+    });
+
+    test('onStart is called with the correct arguments', async () => {
+      const onStart = jest.fn();
+      const opts = { onStart };
+      await TestClient.sendMessage('Hello, world!', opts);
+      expect(onStart).toHaveBeenCalledWith(expect.objectContaining({ text: 'Hello, world!' }));
+    });
+
+    test('saveMessageToDatabase is called with the correct arguments', async () => {
+      const saveOptions = TestClient.getSaveOptions();
+      const user = {}; // Mock user
+      const opts = { user };
+      await TestClient.sendMessage('Hello, world!', opts);
+      expect(TestClient.saveMessageToDatabase).toHaveBeenCalledWith(
+        expect.objectContaining({
+          sender: expect.any(String),
+          text: expect.any(String),
+          isCreatedByUser: expect.any(Boolean),
+          messageId: expect.any(String),
+          parentMessageId: expect.any(String),
+          conversationId: expect.any(String)
+        }),
+        saveOptions,
+        user
+      );
+    });
+
+    test('sendCompletion is called with the correct arguments', async () => {
+      const payload = {}; // Mock payload
+      TestClient.buildMessages.mockReturnValue({ prompt: payload, tokenCountMap: null });
+      const opts = {};
+      await TestClient.sendMessage('Hello, world!', opts);
+      expect(TestClient.sendCompletion).toHaveBeenCalledWith(payload, opts);
+    });
+
+    test('getTokenCountForResponse is called with the correct arguments', async () => {
+      const tokenCountMap = {}; // Mock tokenCountMap
+      TestClient.buildMessages.mockReturnValue({ prompt: [], tokenCountMap });
+      TestClient.getTokenCountForResponse = jest.fn();
+      const response = await TestClient.sendMessage('Hello, world!', {});
+      expect(TestClient.getTokenCountForResponse).toHaveBeenCalledWith(response);
+    });
+
+    test('returns an object with the correct shape', async () => {
+      const response = await TestClient.sendMessage('Hello, world!', {});
+      expect(response).toEqual(expect.objectContaining({
+        sender: expect.any(String),
+        text: expect.any(String),
+        isCreatedByUser: expect.any(Boolean),
+        messageId: expect.any(String),
+        parentMessageId: expect.any(String),
+        conversationId: expect.any(String)
+      }));
+    });
+  });
+});

api/app/clients/specs/FakeClient.js

@@ -0,0 +1,185 @@
+const crypto = require('crypto');
+const BaseClient = require('../BaseClient');
+const { maxTokensMap } = require('../../../utils');
+
+class FakeClient extends BaseClient {
+  constructor(apiKey, options = {}) {
+    super(apiKey, options);
+    this.sender = 'AI Assistant';
+    this.setOptions(options);
+  }
+  setOptions(options) {
+    if (this.options && !this.options.replaceOptions) {
+      this.options.modelOptions = {
+        ...this.options.modelOptions,
+        ...options.modelOptions,
+      };
+      delete options.modelOptions;
+      this.options = {
+        ...this.options,
+        ...options,
+      };
+    } else {
+      this.options = options;
+    }
+
+    if (this.options.openaiApiKey) {
+      this.apiKey = this.options.openaiApiKey;
+    }
+
+    const modelOptions = this.options.modelOptions || {};
+    if (!this.modelOptions) {
+      this.modelOptions = {
+        ...modelOptions,
+        model: modelOptions.model || 'gpt-3.5-turbo',
+        temperature: typeof modelOptions.temperature === 'undefined' ? 0.8 : modelOptions.temperature,
+        top_p: typeof modelOptions.top_p === 'undefined' ? 1 : modelOptions.top_p,
+        presence_penalty: typeof modelOptions.presence_penalty === 'undefined' ? 1 : modelOptions.presence_penalty,
+        stop: modelOptions.stop,
+      };
+    }
+
+    this.maxContextTokens = maxTokensMap[this.modelOptions.model] ?? 4097;
+  }
+  getCompletion() {}
+  buildMessages() {}
+  getTokenCount(str) {
+    return str.length;
+  }
+  getTokenCountForMessage(message) {
+    return message?.content?.length || message.length;
+  }
+}
+
+const initializeFakeClient = (apiKey, options, fakeMessages) => {
+  let TestClient = new FakeClient(apiKey);
+  TestClient.options = options;
+  TestClient.abortController = { abort: jest.fn() };
+  TestClient.saveMessageToDatabase = jest.fn();
+  TestClient.loadHistory = jest
+    .fn()
+    .mockImplementation((conversationId, parentMessageId = null) => {
+      if (!conversationId) {
+        TestClient.currentMessages = [];
+        return Promise.resolve([]);
+      }
+
+      const orderedMessages = TestClient.constructor.getMessagesForConversation(
+        fakeMessages,
+        parentMessageId
+      );
+
+      TestClient.currentMessages = orderedMessages;
+      return Promise.resolve(orderedMessages);
+    });
+
+  TestClient.getSaveOptions = jest.fn().mockImplementation(() => {
+    return {};
+  });
+
+  TestClient.getBuildMessagesOptions = jest.fn().mockImplementation(() => {
+    return {};
+  });
+
+  TestClient.sendCompletion = jest.fn(async () => {
+    return 'Mock response text';
+  });
+
+  TestClient.sendMessage = jest.fn().mockImplementation(async (message, opts = {}) => {
+    if (opts && typeof opts === 'object') {
+      TestClient.setOptions(opts);
+    }
+
+    const user = opts.user || null;
+    const conversationId = opts.conversationId || crypto.randomUUID();
+    const parentMessageId = opts.parentMessageId || '00000000-0000-0000-0000-000000000000';
+    const userMessageId = opts.overrideParentMessageId || crypto.randomUUID();
+    const saveOptions = TestClient.getSaveOptions();
+
+    this.pastMessages = await TestClient.loadHistory(
+      conversationId,
+      TestClient.options?.parentMessageId
+    );
+
+    const userMessage = {
+      text: message,
+      sender: TestClient.sender,
+      isCreatedByUser: true,
+      messageId: userMessageId,
+      parentMessageId,
+      conversationId
+    };
+
+    const response = {
+      sender: TestClient.sender,
+      text: 'Hello, User!',
+      isCreatedByUser: false,
+      messageId: crypto.randomUUID(),
+      parentMessageId: userMessage.messageId,
+      conversationId
+    };
+
+    fakeMessages.push(userMessage);
+    fakeMessages.push(response);
+
+    if (typeof opts.getIds === 'function') {
+      opts.getIds({
+        userMessage,
+        conversationId,
+        responseMessageId: response.messageId
+      });
+    }
+
+    if (typeof opts.onStart === 'function') {
+      opts.onStart(userMessage);
+    }
+
+    let { prompt: payload, tokenCountMap } = await TestClient.buildMessages(
+      this.currentMessages,
+      userMessage.messageId,
+      TestClient.getBuildMessagesOptions(opts),
+    );
+
+    if (tokenCountMap) {
+      payload = payload.map((message, i) => {
+        const { tokenCount, ...messageWithoutTokenCount } = message;
+        // userMessage is always the last one in the payload
+        if (i === payload.length - 1) {
+          userMessage.tokenCount = message.tokenCount;
+          console.debug(`Token count for user message: ${tokenCount}`, `Instruction Tokens: ${tokenCountMap.instructions || 'N/A'}`);
+        }
+        return messageWithoutTokenCount;
+      });
+      TestClient.handleTokenCountMap(tokenCountMap);
+    }
+
+    await TestClient.saveMessageToDatabase(userMessage, saveOptions, user);
+    response.text = await TestClient.sendCompletion(payload, opts);
+    if (tokenCountMap && TestClient.getTokenCountForResponse) {
+      response.tokenCount = TestClient.getTokenCountForResponse(response);
+    }
+    await TestClient.saveMessageToDatabase(response, saveOptions, user);
+    return response;
+  });
+
+  TestClient.buildMessages = jest.fn(async (messages, parentMessageId) => {
+    const orderedMessages = TestClient.constructor.getMessagesForConversation(messages, parentMessageId);
+    const formattedMessages = orderedMessages.map((message) => {
+      let { role: _role, sender, text } = message;
+      const role = _role ?? sender;
+      const content = text ?? '';
+      return {
+        role: role?.toLowerCase() === 'user' ? 'user' : 'assistant',
+        content,
+      };
+    });
+    return {
+      prompt: formattedMessages,
+      tokenCountMap: null, // Simplified for the mock
+    };
+  });
+
+  return TestClient;
+}
+
+module.exports = { FakeClient, initializeFakeClient };

api/app/clients/specs/OpenAIClient.test.js

@@ -0,0 +1,160 @@
+const OpenAIClient = require('../OpenAIClient');
+
+describe('OpenAIClient', () => {
+  let client;
+  const model = 'gpt-4';
+  const parentMessageId = '1';
+  const messages = [
+    { role: 'user', sender: 'User', text: 'Hello', messageId: parentMessageId},
+    { role: 'assistant', sender: 'Assistant', text: 'Hi', messageId: '2' },
+  ];
+
+  beforeEach(() => {
+    const options = {
+      // debug: true,
+      openaiApiKey: 'new-api-key',
+      modelOptions: {
+        model,
+        temperature: 0.7,
+      },
+    };
+    client = new OpenAIClient('test-api-key', options);
+    client.refineMessages = jest.fn().mockResolvedValue({
+      role: 'assistant',
+      content: 'Refined answer',
+      tokenCount: 30
+    });
+  });
+
+  describe('setOptions', () => {
+    it('should set the options correctly', () => {
+      expect(client.apiKey).toBe('new-api-key');
+      expect(client.modelOptions.model).toBe(model);
+      expect(client.modelOptions.temperature).toBe(0.7);
+    });
+  });
+
+  describe('freeAndResetEncoder', () => {
+    it('should reset the encoder', () => {
+      client.freeAndResetEncoder();
+      expect(client.gptEncoder).toBeDefined();
+    });
+  });
+
+  describe('getTokenCount', () => {
+    it('should return the correct token count', () => {
+      const count = client.getTokenCount('Hello, world!');
+      expect(count).toBeGreaterThan(0);
+    });
+
+    it('should reset the encoder and count when count reaches 25', () => {
+      const freeAndResetEncoderSpy = jest.spyOn(client, 'freeAndResetEncoder');
+
+      // Call getTokenCount 25 times
+      for (let i = 0; i < 25; i++) {
+        client.getTokenCount('test text');
+      }
+
+      expect(freeAndResetEncoderSpy).toHaveBeenCalled();
+    });
+
+    it('should not reset the encoder and count when count is less than 25', () => {
+      const freeAndResetEncoderSpy = jest.spyOn(client, 'freeAndResetEncoder');
+
+      // Call getTokenCount 24 times
+      for (let i = 0; i < 24; i++) {
+        client.getTokenCount('test text');
+      }
+
+      expect(freeAndResetEncoderSpy).not.toHaveBeenCalled();
+    });
+
+    it('should handle errors and reset the encoder', () => {
+      const freeAndResetEncoderSpy = jest.spyOn(client, 'freeAndResetEncoder');
+      client.gptEncoder.encode = jest.fn().mockImplementation(() => {
+        throw new Error('Test error');
+      });
+
+      client.getTokenCount('test text');
+
+      expect(freeAndResetEncoderSpy).toHaveBeenCalled();
+    });
+  });
+
+  describe('getSaveOptions', () => {
+    it('should return the correct save options', () => {
+      const options = client.getSaveOptions();
+      expect(options).toHaveProperty('chatGptLabel');
+      expect(options).toHaveProperty('promptPrefix');
+    });
+  });
+
+  describe('getBuildMessagesOptions', () => {
+    it('should return the correct build messages options', () => {
+      const options = client.getBuildMessagesOptions({ promptPrefix: 'Hello' });
+      expect(options).toHaveProperty('isChatCompletion');
+      expect(options).toHaveProperty('promptPrefix');
+      expect(options.promptPrefix).toBe('Hello');
+    });
+  });
+
+  describe('buildMessages', () => {
+    it('should build messages correctly for chat completion', async () => {
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: true });
+      expect(result).toHaveProperty('prompt');
+    });
+
+    it('should build messages correctly for non-chat completion', async () => {
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: false });
+      expect(result).toHaveProperty('prompt');
+    });
+
+    it('should build messages correctly with a promptPrefix', async () => {
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: true, promptPrefix: 'Test Prefix' });
+      expect(result).toHaveProperty('prompt');
+      const instructions = result.prompt.find(item => item.name === 'instructions');
+      expect(instructions).toBeDefined();
+      expect(instructions.content).toContain('Test Prefix');
+    });
+
+    it('should handle context strategy correctly', async () => {
+      client.contextStrategy = 'refine';
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: true });
+      expect(result).toHaveProperty('prompt');
+      expect(result).toHaveProperty('tokenCountMap');
+    });
+
+    it('should assign name property for user messages when options.name is set', async () => {
+      client.options.name = 'Test User';
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: true });
+      const hasUserWithName = result.prompt.some(item => item.role === 'user' && item.name === 'Test User');
+      expect(hasUserWithName).toBe(true);
+    });
+
+    it('should calculate tokenCount for each message when contextStrategy is set', async () => {
+      client.contextStrategy = 'refine';
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: true });
+      const hasUserWithTokenCount = result.prompt.some(item => item.role === 'user' && item.tokenCount > 0);
+      expect(hasUserWithTokenCount).toBe(true);
+    });
+
+    it('should handle promptPrefix from options when promptPrefix argument is not provided', async () => {
+      client.options.promptPrefix = 'Test Prefix from options';
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: true });
+      const instructions = result.prompt.find(item => item.name === 'instructions');
+      expect(instructions.content).toContain('Test Prefix from options');
+    });
+
+    it('should handle case when neither promptPrefix argument nor options.promptPrefix is set', async () => {
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: true });
+      const instructions = result.prompt.find(item => item.name === 'instructions');
+      expect(instructions).toBeUndefined();
+    });
+
+    it('should handle case when getMessagesForConversation returns null or an empty array', async () => {
+      const messages = [];
+      const result = await client.buildMessages(messages, parentMessageId, { isChatCompletion: true });
+      expect(result.prompt).toEqual([]);
+    });
+  });
+});

api/app/clients/specs/OpenAIClient.tokens.js

@@ -1,7 +1,25 @@
+/*
+  This is a test script to see how much memory is used by the client when encoding.
+  On my work machine, it was able to process 10,000 encoding requests / 48.686 seconds = approximately 205.4 RPS
+  I've significantly reduced the amount of encoding needed by saving token counts in the database, so these
+  numbers should only be hit with a large amount of concurrent users
+  It would take 103 concurrent users sending 1 message every 1 second to hit these numbers, which is rather unrealistic,
+  and at that point, out-sourcing the encoding to a separate server would be a better solution
+  Also, for scaling, could increase the rate at which the encoder resets; the trade-off is more resource usage on the server.
+  Initial memory usage: 25.93 megabytes
+  Peak memory usage: 55 megabytes
+  Final memory usage: 28.03 megabytes
+  Post-test (timeout of 15s): 21.91 megabytes
+*/
+
 require('dotenv').config();
+const { OpenAIClient } = require('../');
+
+function timeout(ms) {
+  return new Promise(resolve => setTimeout(resolve, ms));
+}
 
 const run = async () => {
-  const { ChatGPTClient } = await import('@waylaidwanderer/chatgpt-api');
   const text = `
   The standard Lorem Ipsum passage, used since the 1500s
   
@@ -37,7 +55,6 @@ const run = async () => {
 
   // Calculate initial percentage of memory used
   const initialMemoryUsage = process.memoryUsage().heapUsed;
-  
 
   function printProgressBar(percentageUsed) {
     const filledBlocks = Math.round(percentageUsed / 2); // Each block represents 2%
@@ -46,20 +63,20 @@ const run = async () => {
     console.log(progressBar);
   }
 
-  const iterations = 16000;
+  const iterations = 10000;
   console.time('loopTime');
   // Trying to catch the error doesn't help; all future calls will immediately crash
   for (let i = 0; i < iterations; i++) {
     try {
       console.log(`Iteration ${i}`);
-      const client = new ChatGPTClient(apiKey, clientOptions);
+      const client = new OpenAIClient(apiKey, clientOptions);
 
       client.getTokenCount(text);
       // const encoder = client.constructor.getTokenizer('cl100k_base');
       // console.log(`Iteration ${i}: call encode()...`);
       // encoder.encode(text, 'all');
       // encoder.free();
-      
+
       const memoryUsageDuringLoop = process.memoryUsage().heapUsed;
       const percentageUsed = memoryUsageDuringLoop / maxMemory * 100;
       printProgressBar(percentageUsed);
@@ -80,10 +97,23 @@ const run = async () => {
   // const finalPercentageUsed = finalMemoryUsage / maxMemory * 100;
   console.log(`Initial memory usage: ${initialMemoryUsage / 1024 / 1024} megabytes`);
   console.log(`Final memory usage: ${finalMemoryUsage / 1024 / 1024} megabytes`);
-  setTimeout(() => {
-    const memoryUsageAfterTimeout = process.memoryUsage().heapUsed;
-    console.log(`Post timeout: ${memoryUsageAfterTimeout / 1024 / 1024} megabytes`);
-  } , 10000);
+  await timeout(15000);
+  const memoryUsageAfterTimeout = process.memoryUsage().heapUsed;
+  console.log(`Post timeout: ${memoryUsageAfterTimeout / 1024 / 1024} megabytes`);
 }
 
-run();  
+run();
+
+process.on('uncaughtException', (err) => {
+  if (!err.message.includes('fetch failed')) {
+    console.error('There was an uncaught error:');
+    console.error(err);
+  }
+
+  if (err.message.includes('fetch failed')) {
+    console.log('fetch failed error caught');
+    // process.exit(0);
+  } else {
+    process.exit(1);
+  }
+});

api/app/clients/specs/PluginsClient.test.js

@@ -0,0 +1,148 @@
+const { HumanChatMessage, AIChatMessage } = require('langchain/schema');
+const PluginsClient = require('../PluginsClient');
+const crypto = require('crypto');
+
+jest.mock('../../../lib/db/connectDb');
+jest.mock('../../../models/Conversation', () => {
+  return function () {
+    return {
+      save: jest.fn(),
+      deleteConvos: jest.fn()
+    };
+  };
+});
+
+describe('PluginsClient', () => {
+  let TestAgent;
+  let options = {
+    tools: [],
+    modelOptions: {
+      model: 'gpt-3.5-turbo',
+      temperature: 0,
+      max_tokens: 2
+    },
+    agentOptions: {
+      model: 'gpt-3.5-turbo'
+    }
+  };
+  let parentMessageId;
+  let conversationId;
+  const fakeMessages = [];
+  const userMessage = 'Hello, ChatGPT!';
+  const apiKey = 'fake-api-key';
+
+  beforeEach(() => {
+    TestAgent = new PluginsClient(apiKey, options);
+    TestAgent.loadHistory = jest
+      .fn()
+      .mockImplementation((conversationId, parentMessageId = null) => {
+        if (!conversationId) {
+          TestAgent.currentMessages = [];
+          return Promise.resolve([]);
+        }
+
+        const orderedMessages = TestAgent.constructor.getMessagesForConversation(
+          fakeMessages,
+          parentMessageId
+        );
+
+        const chatMessages = orderedMessages.map((msg) =>
+          msg?.isCreatedByUser || msg?.role?.toLowerCase() === 'user'
+            ? new HumanChatMessage(msg.text)
+            : new AIChatMessage(msg.text)
+        );
+
+        TestAgent.currentMessages = orderedMessages;
+        return Promise.resolve(chatMessages);
+      });
+    TestAgent.sendMessage = jest.fn().mockImplementation(async (message, opts = {}) => {
+      if (opts && typeof opts === 'object') {
+        TestAgent.setOptions(opts);
+      }
+      const conversationId = opts.conversationId || crypto.randomUUID();
+      const parentMessageId = opts.parentMessageId || '00000000-0000-0000-0000-000000000000';
+      const userMessageId = opts.overrideParentMessageId || crypto.randomUUID();
+      this.pastMessages = await TestAgent.loadHistory(
+        conversationId,
+        TestAgent.options?.parentMessageId
+      );
+
+      const userMessage = {
+        text: message,
+        sender: 'ChatGPT',
+        isCreatedByUser: true,
+        messageId: userMessageId,
+        parentMessageId,
+        conversationId
+      };
+
+      const response = {
+        sender: 'ChatGPT',
+        text: 'Hello, User!',
+        isCreatedByUser: false,
+        messageId: crypto.randomUUID(),
+        parentMessageId: userMessage.messageId,
+        conversationId
+      };
+
+      fakeMessages.push(userMessage);
+      fakeMessages.push(response);
+      return response;
+    });
+  });
+
+  test('initializes PluginsClient without crashing', () => {
+    expect(TestAgent).toBeInstanceOf(PluginsClient);
+  });
+
+  test('check setOptions function', () => {
+    expect(TestAgent.agentIsGpt3).toBe(true);
+  });
+
+  describe('sendMessage', () => {
+    test('sendMessage should return a response message', async () => {
+      const expectedResult = expect.objectContaining({
+        sender: 'ChatGPT',
+        text: expect.any(String),
+        isCreatedByUser: false,
+        messageId: expect.any(String),
+        parentMessageId: expect.any(String),
+        conversationId: expect.any(String)
+      });
+
+      const response = await TestAgent.sendMessage(userMessage);
+      console.log(response);
+      parentMessageId = response.messageId;
+      conversationId = response.conversationId;
+      expect(response).toEqual(expectedResult);
+    });
+
+    test('sendMessage should work with provided conversationId and parentMessageId', async () => {
+      const userMessage = 'Second message in the conversation';
+      const opts = {
+        conversationId,
+        parentMessageId
+      };
+
+      const expectedResult = expect.objectContaining({
+        sender: 'ChatGPT',
+        text: expect.any(String),
+        isCreatedByUser: false,
+        messageId: expect.any(String),
+        parentMessageId: expect.any(String),
+        conversationId: opts.conversationId
+      });
+
+      const response = await TestAgent.sendMessage(userMessage, opts);
+      parentMessageId = response.messageId;
+      expect(response.conversationId).toEqual(conversationId);
+      expect(response).toEqual(expectedResult);
+    });
+
+    test('should return chat history', async () => {
+      const chatMessages = await TestAgent.loadHistory(conversationId, parentMessageId);
+      expect(TestAgent.currentMessages).toHaveLength(4);
+      expect(chatMessages[0].text).toEqual(userMessage);
+    });
+  });
+});

api/app/clients/tools/AIPluginTool.js

@@ -10,7 +10,6 @@ export interface AIPluginToolParams {
   model: BaseLanguageModel;
 }
 
-
 export interface PathParameter {
   name: string;
   description: string;

api/app/clients/tools/DALL-E.js

@@ -2,7 +2,7 @@
 // To use this tool, you must pass in a configured OpenAIApi object.
 const fs = require('fs');
 const { Configuration, OpenAIApi } = require('openai');
-const { genAzureEndpoint } = require('../../../utils/genAzureEndpoints');
+// const { genAzureEndpoint } = require('../../../utils/genAzureEndpoints');
 const { Tool } = require('langchain/tools');
 const saveImageFromUrl = require('./saveImageFromUrl');
 const path = require('path');
@@ -11,31 +11,31 @@ class OpenAICreateImage extends Tool {
   constructor(fields = {}) {
     super();
 
-    let apiKey = fields.OPENAI_API_KEY || process.env.OPENAI_API_KEY;
-    let azureKey = fields.AZURE_OPENAI_API_KEY || process.env.AZURE_OPENAI_API_KEY;
+    let apiKey = fields.DALLE_API_KEY || this.getApiKey();
+    // let azureKey = fields.AZURE_API_KEY || process.env.AZURE_API_KEY;
     let config = { apiKey };
 
-    if (azureKey) {
-      apiKey = azureKey;
-      const azureConfig = {
-        apiKey,
-        azureOpenAIApiInstanceName: process.env.AZURE_OPENAI_API_INSTANCE_NAME || fields.azureOpenAIApiInstanceName,
-        azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME || fields.azureOpenAIApiDeploymentName,
-        azureOpenAIApiVersion: process.env.AZURE_OPENAI_API_VERSION || fields.azureOpenAIApiVersion
-      };
-      config = {
-        apiKey,
-        basePath: genAzureEndpoint({
-          ...azureConfig,
-        }),
-        baseOptions: {
-          headers: { 'api-key': apiKey },
-          params: {
-            'api-version': azureConfig.azureOpenAIApiVersion // this might change. I got the current value from the sample code at https://oai.azure.com/portal/chat
-          }
-        }
-      };
-    }
+    // if (azureKey) {
+    //   apiKey = azureKey;
+    //   const azureConfig = {
+    //     apiKey,
+    //     azureOpenAIApiInstanceName: process.env.AZURE_OPENAI_API_INSTANCE_NAME || fields.azureOpenAIApiInstanceName,
+    //     azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME || fields.azureOpenAIApiDeploymentName,
+    //     azureOpenAIApiVersion: process.env.AZURE_OPENAI_API_VERSION || fields.azureOpenAIApiVersion
+    //   };
+    //   config = {
+    //     apiKey,
+    //     basePath: genAzureEndpoint({
+    //       ...azureConfig,
+    //     }),
+    //     baseOptions: {
+    //       headers: { 'api-key': apiKey },
+    //       params: {
+    //         'api-version': azureConfig.azureOpenAIApiVersion // this might change. I got the current value from the sample code at https://oai.azure.com/portal/chat
+    //       }
+    //     }
+    //   };
+    // }
     this.openaiApi = new OpenAIApi(new Configuration(config));
     this.name = 'dall-e';
     this.description = `You can generate images with 'dall-e'. This tool is exclusively for visual content.
@@ -46,11 +46,14 @@ Guidelines:
 "Subject: [subject], Style: [style], Color: [color], Details: [details], Emotion: [emotion]"
 - Generate images only once per human query unless explicitly requested by the user`;
   }
-  // "Subject": "Mona Lisa",
-  // "Style": "Chinese traditional painting",
-  // "Color": "Mainly wash tones of ink, with small color blocks in some parts",
-  // "Details": "Mona Lisa should have long hair, a silk dress, holding a fan. The background should have mountains and trees.",
-  // "Emotion": "Serene and elegant"
+
+  getApiKey() {
+    const apiKey = process.env.DALLE_API_KEY || '';
+    if (!apiKey) {
+      throw new Error('Missing DALLE_API_KEY environment variable.');
+    }
+    return apiKey;
+  }
 
   replaceUnwantedChars(inputString) {
     return inputString.replace(/\r\n|\r|\n/g, ' ').replace('"', '').trim();

api/app/clients/tools/HttpRequestTool.js

@@ -6,7 +6,7 @@ const { Tool } = require('langchain/tools');
 //     this.name = 'requests_get';
 //     this.headers = headers;
 //     this.maxOutputLength = maxOutputLength || 2000;
-//     this.description = `A portal to the internet. Use this when you need to get specific content from a website. 
+//     this.description = `A portal to the internet. Use this when you need to get specific content from a website.
 //  - Input should be a  url (i.e. https://www.google.com). The output will be the text response of the GET request.`;
 //   }
 
@@ -27,7 +27,7 @@ const { Tool } = require('langchain/tools');
 //     this.maxOutputLength = maxOutputLength || Infinity;
 //     this.description = `Use this when you want to POST to a website.
 //  - Input should be a json string with two keys: "url" and "data".
-//  - The value of "url" should be a string, and the value of "data" should be a dictionary of 
+//  - The value of "url" should be a string, and the value of "data" should be a dictionary of
 //  - key-value pairs you want to POST to the url as a JSON body.
 //  - Be careful to always use double quotes for strings in the json string
 //  - The output will be the text response of the POST request.`;
@@ -63,23 +63,23 @@ class HttpRequestTool extends Tool {
       const urlPattern = /"url":\s*"([^"]*)"/;
       const methodPattern = /"method":\s*"([^"]*)"/;
       const dataPattern = /"data":\s*"([^"]*)"/;
-  
+
       const url = input.match(urlPattern)[1];
       const method = input.match(methodPattern)[1];
       let data = input.match(dataPattern)[1];
-  
+
       // Parse 'data' back to JSON if possible
       try {
         data = JSON.parse(data);
       } catch (e) {
         // If it's not a JSON string, keep it as is
       }
-  
+
       let options = {
         method: method,
         headers: this.headers
       };
-  
+
       if (['POST', 'PUT', 'PATCH'].includes(method.toUpperCase()) && data) {
         if (typeof data === 'object') {
           options.body = JSON.stringify(data);
@@ -88,20 +88,20 @@ class HttpRequestTool extends Tool {
         }
         options.headers['Content-Type'] = 'application/json';
       }
-  
+
       const res = await fetch(url, options);
-  
+
       const text = await res.text();
       if (text.includes('<html')) {
         return 'This tool is not designed to browse web pages. Only use it for API calls.';
       }
-  
+
       return text.slice(0, this.maxOutputLength);
     } catch (error) {
       console.log(error);
       return `${error}`;
     }
-  }  
+  }
 }
 
 module.exports = HttpRequestTool;

api/app/clients/tools/index.js

@@ -0,0 +1,23 @@
+const GoogleSearchAPI = require('./GoogleSearch');
+const HttpRequestTool = require('./HttpRequestTool');
+const AIPluginTool = require('./AIPluginTool');
+const OpenAICreateImage = require('./DALL-E');
+const StructuredSD = require('./structured/StableDiffusion');
+const StableDiffusionAPI = require('./StableDiffusion');
+const WolframAlphaAPI = require('./Wolfram');
+const StructuredWolfram = require('./structured/Wolfram');
+const SelfReflectionTool = require('./SelfReflection');
+const availableTools = require('./manifest.json');
+
+module.exports = {
+  availableTools,
+  GoogleSearchAPI,
+  HttpRequestTool,
+  AIPluginTool,
+  OpenAICreateImage,
+  StableDiffusionAPI,
+  StructuredSD,
+  WolframAlphaAPI,
+  StructuredWolfram,
+  SelfReflectionTool
+}

api/app/clients/tools/manifest.json

@@ -8,12 +8,12 @@
       {
         "authField": "GOOGLE_CSE_ID",
         "label": "Google CSE ID",
-        "description": "This is your Google Custom Search Engine ID. For instructions on how to obtain this, see <a href='https://github.com/danny-avila/chatgpt-clone/blob/main/guides/GOOGLE_SEARCH.md'>Our Docs</a>."
+        "description": "This is your Google Custom Search Engine ID. For instructions on how to obtain this, see <a href='https://github.com/danny-avila/LibreChat/blob/main/docs/features/plugins/google_search.md'>Our Docs</a>."
       },
       {
         "authField": "GOOGLE_API_KEY",
         "label": "Google API Key",
-        "description": "This is your Google Custom Search API Key. For instructions on how to obtain this, see <a href='https://github.com/danny-avila/chatgpt-clone/blob/main/guides/GOOGLE_SEARCH.md'>Our Docs</a>."
+        "description": "This is your Google Custom Search API Key. For instructions on how to obtain this, see <a href='https://github.com/danny-avila/LibreChat/blob/main/docs/features/plugins/google_search.md'>Our Docs</a>."
       }
     ]
   },

api/app/clients/tools/structured/StableDiffusion.js

@@ -0,0 +1,89 @@
+// Generates image using stable diffusion webui's api (automatic1111)
+const fs = require('fs');
+const { StructuredTool } = require('langchain/tools');
+const { z } = require('zod');
+const path = require('path');
+const axios = require('axios');
+const sharp = require('sharp');
+
+class StableDiffusionAPI extends StructuredTool {
+  constructor(fields) {
+    super();
+    this.name = 'stable-diffusion';
+    this.url = fields.SD_WEBUI_URL || this.getServerURL();
+    this.description = `You can generate images with 'stable-diffusion'. This tool is exclusively for visual content.
+Guidelines:
+- Visually describe the moods, details, structures, styles, and/or proportions of the image. Remember, the focus is on visual attributes.
+- Craft your input by "showing" and not "telling" the imagery. Think in terms of what you'd want to see in a photograph or a painting.
+- Here's an example for generating a realistic portrait photo of a man:
+"prompt":"photo of a man in black clothes, half body, high detailed skin, coastline, overcast weather, wind, waves, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3"
+"negative_prompt":"semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, out of frame, low quality, ugly, mutation, deformed"
+- Generate images only once per human query unless explicitly requested by the user`;
+    this.schema = z.object({
+      prompt: z.string().describe("Detailed keywords to describe the subject, using at least 7 keywords to accurately describe the image, separated by comma"),
+      negative_prompt: z.string().describe("Keywords we want to exclude from the final image, using at least 7 keywords to accurately describe the image, separated by comma")
+    });
+  }
+
+  replaceNewLinesWithSpaces(inputString) {
+    return inputString.replace(/\r\n|\r|\n/g, ' ');
+  }
+
+  getMarkdownImageUrl(imageName) {
+    const imageUrl = path.join(this.relativeImageUrl, imageName).replace(/\\/g, '/').replace('public/', '');
+    return `![generated image](/${imageUrl})`;
+  }
+
+  getServerURL() {
+    const url = process.env.SD_WEBUI_URL || '';
+    if (!url) {
+      throw new Error('Missing SD_WEBUI_URL environment variable.');
+    }
+    return url;
+  }
+
+  async _call(data) {
+    const url = this.url;
+    const { prompt, negative_prompt } = data;
+    const payload = {
+      prompt,
+      negative_prompt,
+      steps: 20
+    };
+    const response = await axios.post(`${url}/sdapi/v1/txt2img`, payload);
+    const image = response.data.images[0];
+    const pngPayload = { image: `data:image/png;base64,${image}` };
+    const response2 = await axios.post(`${url}/sdapi/v1/png-info`, pngPayload);
+    const info = response2.data.info;
+
+    // Generate unique name
+    const imageName = `${Date.now()}.png`;
+    this.outputPath = path.resolve(__dirname, '..', '..', '..', '..', '..', 'client', 'public', 'images');
+    const appRoot = path.resolve(__dirname, '..', '..', '..', '..', '..', 'client');
+    this.relativeImageUrl = path.relative(appRoot, this.outputPath);
+
+    // Check if directory exists, if not create it
+    if (!fs.existsSync(this.outputPath)) {
+      fs.mkdirSync(this.outputPath, { recursive: true });
+    }
+
+    try {
+      const buffer = Buffer.from(image.split(',', 1)[0], 'base64');
+      await sharp(buffer)
+        .withMetadata({
+          iptcpng: {
+            parameters: info
+          }
+        })
+        .toFile(this.outputPath + '/' + imageName);
+      this.result = this.getMarkdownImageUrl(imageName);
+    } catch (error) {
+      console.error('Error while saving the image:', error);
+      // this.result = theImageUrl;
+    }
+
+    return this.result;
+  }
+}
+
+module.exports = StableDiffusionAPI;

api/app/clients/tools/structured/Wolfram.js

@@ -0,0 +1,72 @@
+/* eslint-disable no-useless-escape */
+const axios = require('axios');
+const { StructuredTool } = require('langchain/tools');
+const { z } = require('zod');
+
+class WolframAlphaAPI extends StructuredTool {
+  constructor(fields) {
+    super();
+    this.name = 'wolfram';
+    this.apiKey = fields.WOLFRAM_APP_ID || this.getAppId();
+    this.description = `WolframAlpha offers computation, math, curated knowledge, and real-time data. It handles natural language queries and performs complex calculations. 
+Guidelines include:
+- Use English for queries and inform users if information isn't from Wolfram.
+- Use "6*10^14" for exponent notation and single-line strings for input.
+- Use Markdown for formulas and simplify queries to keywords.
+- Use single-letter variable names and named physical constants.
+- Include a space between compound units and consider equations without units when solving.
+- Make separate calls for each property and choose relevant 'Assumptions' if results aren't relevant.
+- The tool also performs data analysis, plotting, and information retrieval.`;
+    this.schema = z.object({
+      nl_query: z.string().describe("Natural language query to WolframAlpha following the guidelines"),
+    });
+  }
+
+  async fetchRawText(url) {
+    try {
+      const response = await axios.get(url, { responseType: 'text' });
+      return response.data;
+    } catch (error) {
+      console.error(`Error fetching raw text: ${error}`);
+      throw error;
+    }
+  }
+
+  getAppId() {
+    const appId = process.env.WOLFRAM_APP_ID || '';
+    if (!appId) {
+      throw new Error('Missing WOLFRAM_APP_ID environment variable.');
+    }
+    return appId;
+  }
+
+  createWolframAlphaURL(query) {
+    // Clean up query
+    const formattedQuery = query.replaceAll(/`/g, '').replaceAll(/\n/g, ' ');
+    const baseURL = 'https://www.wolframalpha.com/api/v1/llm-api';
+    const encodedQuery = encodeURIComponent(formattedQuery);
+    const appId = this.apiKey || this.getAppId();
+    const url = `${baseURL}?input=${encodedQuery}&appid=${appId}`;
+    return url;
+  }
+
+  async _call(data) {
+    try {
+      const { nl_query } = data;
+      const url = this.createWolframAlphaURL(nl_query);
+      const response = await this.fetchRawText(url);
+      return response;
+    } catch (error) {
+      if (error.response && error.response.data) {
+        console.log('Error data:', error.response.data);
+        return error.response.data;
+      } else {
+        console.log(`Error querying Wolfram Alpha`, error.message);
+        // throw error;
+        return 'There was an error querying Wolfram Alpha.';
+      }
+    }
+  }
+}
+
+module.exports = WolframAlphaAPI;

api/app/clients/tools/util/handleTools.js

@@ -1,3 +1,4 @@
+const { getUserPluginAuthValue } = require('../../../../server/services/PluginService');
 const { OpenAIEmbeddings } = require('langchain/embeddings/openai');
 const { ZapierToolKit } = require('langchain/agents');
 const {
@@ -7,14 +8,17 @@ const {
 const { ChatOpenAI } = require('langchain/chat_models/openai');
 const { Calculator } = require('langchain/tools/calculator');
 const { WebBrowser } = require('langchain/tools/webbrowser');
-const GoogleSearchAPI = require('./GoogleSearch');
-const HttpRequestTool = require('./HttpRequestTool');
-const AIPluginTool = require('./AIPluginTool');
-const OpenAICreateImage = require('./DALL-E');
-const StableDiffusionAPI = require('./StableDiffusion');
-const WolframAlphaAPI = require('./Wolfram');
-const availableTools = require('./manifest.json');
-const { getUserPluginAuthValue } = require('../../../server/services/PluginService');
+const {
+  availableTools,
+  AIPluginTool,
+  GoogleSearchAPI,
+  WolframAlphaAPI,
+  StructuredWolfram,
+  HttpRequestTool,
+  OpenAICreateImage,
+  StableDiffusionAPI,
+  StructuredSD,
+} = require('../');
 
 const validateTools = async (user, tools = []) => {
   try {
@@ -69,13 +73,13 @@ const loadToolWithAuth = async (user, authFields, ToolConstructor, options = {})
   };
 };
 
-const loadTools = async ({ user, model, tools = [], options = {} }) => {
+const loadTools = async ({ user, model, functions = null, tools = [], options = {} }) => {
   const toolConstructors = {
     calculator: Calculator,
     google: GoogleSearchAPI,
-    wolfram: WolframAlphaAPI,
+    wolfram: functions ? StructuredWolfram : WolframAlphaAPI,
     'dall-e': OpenAICreateImage,
-    'stable-diffusion': StableDiffusionAPI
+    'stable-diffusion': functions ? StructuredSD : StableDiffusionAPI
   };
 
   const customConstructors = {
@@ -109,9 +113,10 @@ const loadTools = async ({ user, model, tools = [], options = {} }) => {
       return [
         new HttpRequestTool(),
         await AIPluginTool.fromPluginUrl(
-          "https://www.klarna.com/.well-known/ai-plugin.json", new ChatOpenAI({ openAIApiKey: options.openAIApiKey, temperature: 0 })
-        ),
-      ]
+          'https://www.klarna.com/.well-known/ai-plugin.json',
+          new ChatOpenAI({ openAIApiKey: options.openAIApiKey, temperature: 0 })
+        )
+      ];
     }
   };
 

api/app/clients/tools/util/handleTools.test.js

@@ -1,14 +1,29 @@
-/* eslint-disable jest/no-conditional-expect */
-require('dotenv').config({ path: '../../../.env' });
-const mongoose = require('mongoose');
-const User = require('../../../models/User');
-const connectDb = require('../../../lib/db/connectDb');
-const { validateTools, loadTools, availableTools } = require('./index');
-const PluginService = require('../../../server/services/PluginService');
+const mockUser = {
+  _id: 'fakeId',
+  save: jest.fn(),
+  findByIdAndDelete: jest.fn(),
+};
+
+var mockPluginService = {
+  updateUserPluginAuth: jest.fn(),
+  deleteUserPluginAuth: jest.fn(),
+  getUserPluginAuthValue: jest.fn()
+};
+
+jest.mock('../../../../models/User', () => {
+  return function() {
+    return mockUser;
+  };
+});
+
+jest.mock('../../../../server/services/PluginService', () => mockPluginService);
+
+const User = require('../../../../models/User');
+const { validateTools, loadTools } = require('./');
+const PluginService = require('../../../../server/services/PluginService');
 const { BaseChatModel } = require('langchain/chat_models/openai');
 const { Calculator } = require('langchain/tools/calculator');
-const OpenAICreateImage = require('./DALL-E');
-const GoogleSearchAPI = require('./GoogleSearch');
+const { availableTools, OpenAICreateImage, GoogleSearchAPI, StructuredSD } = require('../');
 
 describe('Tool Handlers', () => {
   let fakeUser;
@@ -21,7 +36,16 @@ describe('Tool Handlers', () => {
   const authConfigs = mainPlugin.authConfig;
 
   beforeAll(async () => {
-    await connectDb();
+    mockUser.save.mockResolvedValue(undefined);
+
+    const userAuthValues = {};
+    mockPluginService.getUserPluginAuthValue.mockImplementation((userId, authField) => {
+      return userAuthValues[`${userId}-${authField}`];
+    });
+    mockPluginService.updateUserPluginAuth.mockImplementation((userId, authField, _pluginKey, credential) => {
+      userAuthValues[`${userId}-${authField}`] = credential;
+    });
+
     fakeUser = new User({
       name: 'Fake User',
       username: 'fakeuser',
@@ -41,17 +65,11 @@ describe('Tool Handlers', () => {
     }
   });
 
-  // afterEach(async () => {
-  //   // Clean up any test-specific data.
-  // });
-
   afterAll(async () => {
-    // Delete the fake user & plugin auth
-    await User.findByIdAndDelete(fakeUser._id);
+    await mockUser.findByIdAndDelete(fakeUser._id);
     for (const authConfig of authConfigs) {
       await PluginService.deleteUserPluginAuth(fakeUser._id, authConfig.authField);
     }
-    await mongoose.connection.close();
   });
 
   describe('validateTools', () => {
@@ -128,6 +146,7 @@ describe('Tool Handlers', () => {
       try {
         await loadTool2();
       } catch (error) {
+        // eslint-disable-next-line jest/no-conditional-expect
         expect(error).toBeDefined();
       }
     });
@@ -154,5 +173,17 @@ describe('Tool Handlers', () => {
       });
       expect(toolFunctions).toEqual({});
     });
+    it('should return the StructuredTool version when using functions', async () => {
+      process.env.SD_WEBUI_URL = mockCredential;
+      toolFunctions = await loadTools({
+        user: fakeUser._id,
+        model: BaseChatModel,
+        tools: ['stable-diffusion'],
+        functions: true
+      });
+      const structuredTool = await toolFunctions['stable-diffusion']();
+      expect(structuredTool).toBeInstanceOf(StructuredSD);
+      delete process.env.SD_WEBUI_URL;
+    });
   });
 });

api/app/clients/tools/util/index.js

@@ -0,0 +1,6 @@
+const { validateTools, loadTools } = require('./handleTools');
+
+module.exports = {
+  validateTools,
+  loadTools
+};

api/app/index.js

@@ -1,15 +1,15 @@
-const { askClient } = require('./clients/chatgpt-client');
-const { browserClient } = require('./clients/chatgpt-browser');
-const { askBing } = require('./clients/bingai');
+const { browserClient } = require('./chatgpt-browser');
+const { askBing } = require('./bingai');
+const clients = require('./clients');
 const titleConvo = require('./titleConvo');
 const getCitations = require('../lib/parse/getCitations');
 const citeText = require('../lib/parse/citeText');
 
 module.exports = {
-  askClient,
   browserClient,
   askBing,
   titleConvo,
   getCitations,
-  citeText
+  citeText,
+  ...clients
 };

api/app/langchain/ChatAgent.js

@@ -1,904 +0,0 @@
-const crypto = require('crypto');
-const { genAzureChatCompletion } = require('../../utils/genAzureEndpoints');
-const {
-  encoding_for_model: encodingForModel,
-  get_encoding: getEncoding
-} = require('@dqbd/tiktoken');
-const { fetchEventSource } = require('@waylaidwanderer/fetch-event-source');
-const { Agent, ProxyAgent } = require('undici');
-const TextStream = require('../stream');
-const { ChatOpenAI } = require('langchain/chat_models/openai');
-const { CallbackManager } = require('langchain/callbacks');
-const { HumanChatMessage, AIChatMessage } = require('langchain/schema');
-const { initializeCustomAgent } = require('./agents/CustomAgent/initializeCustomAgent');
-const { getMessages, saveMessage, saveConvo } = require('../../models');
-const { loadTools, SelfReflectionTool } = require('./tools');
-const {
-  instructions,
-  imageInstructions,
-  errorInstructions,
-  completionInstructions
-} = require('./instructions');
-
-const tokenizersCache = {};
-
-class ChatAgent {
-  constructor(apiKey, options = {}) {
-    this.tools = [];
-    this.actions = [];
-    this.openAIApiKey = apiKey;
-    this.azure = options.azure || false;
-    if (this.azure) {
-      const { azureOpenAIApiInstanceName, azureOpenAIApiDeploymentName, azureOpenAIApiVersion } =
-        this.azure;
-      this.azureEndpoint = genAzureChatCompletion({
-        azureOpenAIApiInstanceName,
-        azureOpenAIApiDeploymentName,
-        azureOpenAIApiVersion
-      });
-    }
-    this.setOptions(options);
-    this.executor = null;
-    this.currentDateString = new Date().toLocaleDateString('en-us', {
-      year: 'numeric',
-      month: 'long',
-      day: 'numeric'
-    });
-  }
-
-  getActions(input = null) {
-    let output = 'Internal thoughts & actions taken:\n"';
-    let actions = input || this.actions;
-
-    if (actions[0]?.action) {
-      actions = actions.map((step) => ({
-        log: `${step.action.log}\nObservation: ${step.observation}`
-      }));
-    }
-
-    actions.forEach((actionObj, index) => {
-      output += `${actionObj.log}`;
-      if (index < actions.length - 1) {
-        output += '\n';
-      }
-    });
-
-    return output + '"';
-  }
-
-  buildErrorInput(message, errorMessage) {
-    const log = errorMessage.includes('Could not parse LLM output:')
-      ? `A formatting error occurred with your response to the human's last message. You didn't follow the formatting instructions. Remember to ${instructions}`
-      : `You encountered an error while replying to the human's last message. Attempt to answer again or admit an answer cannot be given.\nError: ${errorMessage}`;
-
-    return `
-      ${log}
-
-      ${this.getActions()}
-
-      Human's last message: ${message}
-      `;
-  }
-
-  buildPromptPrefix(result, message) {
-    if ((result.output && result.output.includes('N/A')) || result.output === undefined) {
-      return null;
-    }
-
-    if (
-      result?.intermediateSteps?.length === 1 &&
-      result?.intermediateSteps[0]?.action?.toolInput === 'N/A'
-    ) {
-      return null;
-    }
-
-    const internalActions =
-      result?.intermediateSteps?.length > 0
-        ? this.getActions(result.intermediateSteps)
-        : 'Internal Actions Taken: None';
-
-    const toolBasedInstructions = internalActions.toLowerCase().includes('image')
-      ? imageInstructions
-      : '';
-
-    const errorMessage = result.errorMessage ? `${errorInstructions} ${result.errorMessage}\n` : '';
-
-    const preliminaryAnswer =
-      result.output?.length > 0 ? `Preliminary Answer: "${result.output.trim()}"` : '';
-    const prefix = preliminaryAnswer
-      ? `review and improve the answer you generated using plugins in response to the User Message below. The answer hasn't been sent to the user yet.`
-      : 'respond to the User Message below based on your preliminary thoughts & actions.';
-
-    return `As ChatGPT, ${prefix}${errorMessage}\n${internalActions}
-${preliminaryAnswer}
-Reply conversationally to the User based on your ${
-  preliminaryAnswer ? 'preliminary answer, ' : ''
-}internal actions, thoughts, and observations, making improvements wherever possible, but do not modify URLs.
-${
-  preliminaryAnswer
-    ? ''
-    : '\nIf there is an incomplete thought or action, you are expected to complete it in your response now.\n'
-}You must cite sources if you are using any web links. ${toolBasedInstructions}
-Only respond with your conversational reply to the following User Message:
-"${message}"`;
-  }
-
-  setOptions(options) {
-    if (this.options && !this.options.replaceOptions) {
-      // nested options aren't spread properly, so we need to do this manually
-      this.options.modelOptions = {
-        ...this.options.modelOptions,
-        ...options.modelOptions
-      };
-      this.options.agentOptions = {
-        ...this.options.agentOptions,
-        ...options.agentOptions
-      };
-      delete options.modelOptions;
-      delete options.agentOptions;
-      // now we can merge options
-      this.options = {
-        ...this.options,
-        ...options
-      };
-    } else {
-      this.options = options;
-    }
-
-    this.agentOptions = this.options.agentOptions || {};
-    this.agentIsGpt3 = this.agentOptions.model.startsWith('gpt-3');
-    const modelOptions = this.options.modelOptions || {};
-    this.modelOptions = {
-      ...modelOptions,
-      model: modelOptions.model || 'gpt-3.5-turbo',
-      temperature: typeof modelOptions.temperature === 'undefined' ? 0.8 : modelOptions.temperature,
-      top_p: typeof modelOptions.top_p === 'undefined' ? 1 : modelOptions.top_p,
-      presence_penalty:
-        typeof modelOptions.presence_penalty === 'undefined' ? 0 : modelOptions.presence_penalty,
-      frequency_penalty:
-        typeof modelOptions.frequency_penalty === 'undefined' ? 0 : modelOptions.frequency_penalty,
-      stop: modelOptions.stop
-    };
-
-    this.isChatGptModel = this.modelOptions.model.startsWith('gpt-');
-    this.isGpt3 = this.modelOptions.model.startsWith('gpt-3');
-    this.maxContextTokens = this.modelOptions.model === 'gpt-4-32k' ? 32767 : this.modelOptions.model.startsWith('gpt-4') ? 8191 : 4095,
-
-    // Reserve 1024 tokens for the response.
-    // The max prompt tokens is determined by the max context tokens minus the max response tokens.
-    // Earlier messages will be dropped until the prompt is within the limit.
-    this.maxResponseTokens = this.modelOptions.max_tokens || 1024;
-    this.maxPromptTokens =
-      this.options.maxPromptTokens || this.maxContextTokens - this.maxResponseTokens;
-
-    if (this.maxPromptTokens + this.maxResponseTokens > this.maxContextTokens) {
-      throw new Error(
-        `maxPromptTokens + max_tokens (${this.maxPromptTokens} + ${this.maxResponseTokens} = ${
-          this.maxPromptTokens + this.maxResponseTokens
-        }) must be less than or equal to maxContextTokens (${this.maxContextTokens})`
-      );
-    }
-
-    this.userLabel = this.options.userLabel || 'User';
-    this.chatGptLabel = this.options.chatGptLabel || 'ChatGPT';
-
-    // Use these faux tokens to help the AI understand the context since we are building the chat log ourselves.
-    // Trying to use "<|im_start|>" causes the AI to still generate "<" or "<|" at the end sometimes for some reason,
-    // without tripping the stop sequences, so I'm using "||>" instead.
-    this.startToken = '||>';
-    this.endToken = '';
-    this.gptEncoder = this.constructor.getTokenizer('cl100k_base');
-    this.completionsUrl = 'https://api.openai.com/v1/chat/completions';
-    this.reverseProxyUrl = this.options.reverseProxyUrl || process.env.OPENAI_REVERSE_PROXY;
-
-    if (this.reverseProxyUrl) {
-      this.completionsUrl = this.reverseProxyUrl;
-      this.langchainProxy = this.reverseProxyUrl.substring(0, this.reverseProxyUrl.indexOf('v1') + 'v1'.length)
-    }
-
-    if (this.azureEndpoint) {
-      this.completionsUrl = this.azureEndpoint;
-    }
-
-    if (this.azureEndpoint && this.options.debug) {
-      console.debug(`Using Azure endpoint: ${this.azureEndpoint}`, this.azure);
-    }
-  }
-
-  static getTokenizer(encoding, isModelName = false, extendSpecialTokens = {}) {
-    if (tokenizersCache[encoding]) {
-      return tokenizersCache[encoding];
-    }
-    let tokenizer;
-    if (isModelName) {
-      tokenizer = encodingForModel(encoding, extendSpecialTokens);
-    } else {
-      tokenizer = getEncoding(encoding, extendSpecialTokens);
-    }
-    tokenizersCache[encoding] = tokenizer;
-    return tokenizer;
-  }
-
-  async getCompletion(input, onProgress, abortController = null) {
-    if (!abortController) {
-      abortController = new AbortController();
-    }
-
-    const modelOptions = this.modelOptions;
-    if (typeof onProgress === 'function') {
-      modelOptions.stream = true;
-    }
-    if (this.isChatGptModel) {
-      modelOptions.messages = input;
-    } else {
-      modelOptions.prompt = input;
-    }
-    const { debug } = this.options;
-    const url = this.completionsUrl;
-    if (debug) {
-      console.debug();
-      console.debug(url);
-      console.debug(modelOptions);
-      console.debug();
-    }
-    const opts = {
-      method: 'POST',
-      headers: {
-        'Content-Type': 'application/json'
-      },
-      body: JSON.stringify(modelOptions),
-      dispatcher: new Agent({
-        bodyTimeout: 0,
-        headersTimeout: 0
-      })
-    };
-
-    if (this.azureEndpoint) {
-      opts.headers['api-key'] = this.azure.azureOpenAIApiKey;
-    } else if (this.openAIApiKey) {
-      opts.headers.Authorization = `Bearer ${this.openAIApiKey}`;
-    }
-
-    if (this.options.proxy) {
-      opts.dispatcher = new ProxyAgent(this.options.proxy);
-    }
-
-    if (modelOptions.stream) {
-      // eslint-disable-next-line no-async-promise-executor
-      return new Promise(async (resolve, reject) => {
-        try {
-          let done = false;
-          await fetchEventSource(url, {
-            ...opts,
-            signal: abortController.signal,
-            async onopen(response) {
-              if (response.status === 200) {
-                return;
-              }
-              if (debug) {
-                // console.debug(response);
-              }
-              let error;
-              try {
-                const body = await response.text();
-                error = new Error(`Failed to send message. HTTP ${response.status} - ${body}`);
-                error.status = response.status;
-                error.json = JSON.parse(body);
-              } catch {
-                error = error || new Error(`Failed to send message. HTTP ${response.status}`);
-              }
-              throw error;
-            },
-            onclose() {
-              if (debug) {
-                console.debug('Server closed the connection unexpectedly, returning...');
-              }
-              // workaround for private API not sending [DONE] event
-              if (!done) {
-                onProgress('[DONE]');
-                abortController.abort();
-                resolve();
-              }
-            },
-            onerror(err) {
-              if (debug) {
-                console.debug(err);
-              }
-              // rethrow to stop the operation
-              throw err;
-            },
-            onmessage(message) {
-              if (debug) {
-                // console.debug(message);
-              }
-              if (!message.data || message.event === 'ping') {
-                return;
-              }
-              if (message.data === '[DONE]') {
-                onProgress('[DONE]');
-                abortController.abort();
-                resolve();
-                done = true;
-                return;
-              }
-              onProgress(JSON.parse(message.data));
-            }
-          });
-        } catch (err) {
-          reject(err);
-        }
-      });
-    }
-    const response = await fetch(url, {
-      ...opts,
-      signal: abortController.signal
-    });
-    if (response.status !== 200) {
-      const body = await response.text();
-      const error = new Error(`Failed to send message. HTTP ${response.status} - ${body}`);
-      error.status = response.status;
-      try {
-        error.json = JSON.parse(body);
-      } catch {
-        error.body = body;
-      }
-      throw error;
-    }
-    return response.json();
-  }
-
-  async loadHistory(conversationId, parentMessageId = null) {
-    if (this.options.debug) {
-      console.debug('Loading history for conversation', conversationId, parentMessageId);
-    }
-
-    const messages = (await getMessages({ conversationId })) || [];
-
-    if (messages.length === 0) {
-      this.currentMessages = [];
-      return [];
-    }
-
-    const orderedMessages = this.constructor.getMessagesForConversation(messages, parentMessageId);
-    // Convert Message documents into appropriate ChatMessage instances
-    const chatMessages = orderedMessages.map((msg) =>
-      msg?.isCreatedByUser || msg?.role.toLowerCase() === 'user'
-        ? new HumanChatMessage(msg.text)
-        : new AIChatMessage(msg.text)
-    );
-
-    this.currentMessages = orderedMessages;
-
-    return chatMessages;
-  }
-
-  async saveMessageToDatabase(message, user = null) {
-    await saveMessage({ ...message, unfinished: false });
-    await saveConvo(user, {
-      conversationId: message.conversationId,
-      endpoint: 'gptPlugins',
-      chatGptLabel: this.options.chatGptLabel,
-      promptPrefix: this.options.promptPrefix,
-      ...this.modelOptions,
-      agentOptions: this.agentOptions
-    });
-  }
-
-  saveLatestAction(action) {
-    this.actions.push(action);
-  }
-
-  async initialize({ user, message, onAgentAction, onChainEnd, signal }) {
-    const modelOptions = {
-      modelName: this.agentOptions.model,
-      temperature: this.agentOptions.temperature
-    };
-
-    const configOptions = {};
-
-    if (this.langchainProxy) {
-      configOptions.basePath = this.langchainProxy;
-    }
-
-    const model = this.azure
-      ? new ChatOpenAI({
-        ...this.azure,
-        ...modelOptions
-      })
-      : new ChatOpenAI(
-        {
-          openAIApiKey: this.openAIApiKey,
-          ...modelOptions
-        },
-        configOptions
-        // {
-        //   basePath: 'http://localhost:8080/v1'
-        // }
-      );
-
-    if (this.options.debug) {
-      console.debug(`<-----Agent Model: ${model.modelName} | Temp: ${model.temperature}----->`);
-    }
-
-    this.availableTools = await loadTools({
-      user,
-      model,
-      tools: this.options.tools,
-      options: {
-        openAIApiKey: this.openAIApiKey
-      }
-    });
-    // load tools
-    for (const tool of this.options.tools) {
-      const validTool = this.availableTools[tool];
-
-      if (tool === 'plugins') {
-        const plugins = await validTool();
-        this.tools = [...this.tools, ...plugins];
-      } else if (validTool) {
-        this.tools.push(await validTool());
-      }
-    }
-
-    if (this.options.debug) {
-      console.debug('Requested Tools');
-      console.debug(this.options.tools);
-      console.debug('Loaded Tools');
-      console.debug(this.tools.map((tool) => tool.name));
-    }
-
-    if (this.tools.length > 0) {
-      this.tools.push(new SelfReflectionTool({ message, isGpt3: false }));
-    } else if (this.tools.length === 0) {
-      return;
-    }
-
-    const handleAction = (action, callback = null) => {
-      this.saveLatestAction(action);
-
-      if (this.options.debug) {
-        console.debug('Latest Agent Action ', this.actions[this.actions.length - 1]);
-      }
-
-      if (typeof callback === 'function') {
-        callback(action);
-      }
-    };
-
-    // initialize agent
-    this.executor = await initializeCustomAgent({
-      model,
-      signal,
-      tools: this.tools,
-      pastMessages: this.pastMessages,
-      currentDateString: this.currentDateString,
-      verbose: this.options.debug,
-      returnIntermediateSteps: true,
-      callbackManager: CallbackManager.fromHandlers({
-        async handleAgentAction(action) {
-          handleAction(action, onAgentAction);
-        },
-        async handleChainEnd(action) {
-          if (typeof onChainEnd === 'function') {
-            onChainEnd(action);
-          }
-        }
-      })
-    });
-
-    if (this.options.debug) {
-      console.debug('Loaded agent.');
-    }
-  }
-
-  async sendApiMessage(messages, userMessage, opts = {}) {
-    // Doing it this way instead of having each message be a separate element in the array seems to be more reliable,
-    // especially when it comes to keeping the AI in character. It also seems to improve coherency and context retention.
-    let payload = await this.buildPrompt({
-      messages: [
-        ...messages,
-        {
-          messageId: userMessage.messageId,
-          parentMessageId: userMessage.parentMessageId,
-          role: 'User',
-          text: userMessage.text
-        }
-      ],
-      ...opts
-    });
-
-    let reply = '';
-    let result = {};
-    if (typeof opts.onProgress === 'function') {
-      await this.getCompletion(
-        payload,
-        (progressMessage) => {
-          if (progressMessage === '[DONE]') {
-            return;
-          }
-          const token = this.isChatGptModel
-            ? progressMessage.choices[0].delta.content
-            : progressMessage.choices[0].text;
-          // first event's delta content is always undefined
-          if (!token) {
-            return;
-          }
-
-          if (token === this.endToken) {
-            return;
-          }
-          opts.onProgress(token);
-          reply += token;
-        },
-        opts.abortController || new AbortController()
-      );
-    } else {
-      result = await this.getCompletion(
-        payload,
-        null,
-        opts.abortController || new AbortController()
-      );
-      if (this.options.debug) {
-        console.debug(JSON.stringify(result));
-      }
-      if (this.isChatGptModel) {
-        reply = result.choices[0].message.content;
-      } else {
-        reply = result.choices[0].text.replace(this.endToken, '');
-      }
-    }
-
-    if (this.options.debug) {
-      console.debug();
-    }
-
-    return reply.trim();
-  }
-
-  async executorCall(message, signal) {
-    let errorMessage = '';
-    const maxAttempts = 1;
-
-    for (let attempts = 1; attempts <= maxAttempts; attempts++) {
-      const errorInput = this.buildErrorInput(message, errorMessage);
-      const input = attempts > 1 ? errorInput : message;
-
-      if (this.options.debug) {
-        console.debug(`Attempt ${attempts} of ${maxAttempts}`);
-      }
-
-      if (this.options.debug && errorMessage.length > 0) {
-        console.debug('Caught error, input:', input);
-      }
-
-      try {
-        this.result = await this.executor.call({ input, signal });
-        break; // Exit the loop if the function call is successful
-      } catch (err) {
-        console.error(err);
-        errorMessage = err.message;
-        if (attempts === maxAttempts) {
-          this.result.output = `Encountered an error while attempting to respond. Error: ${err.message}`;
-          this.result.intermediateSteps = this.actions;
-          this.result.errorMessage = errorMessage;
-          break;
-        }
-      }
-    }
-  }
-
-  async sendMessage(message, opts = {}) {
-    if (opts && typeof opts === 'object') {
-      this.setOptions(opts);
-    }
-    console.log('sendMessage', message, opts);
-
-    const user = opts.user || null;
-    const { onAgentAction, onChainEnd, onProgress } = opts;
-    const conversationId = opts.conversationId || crypto.randomUUID();
-    const parentMessageId = opts.parentMessageId || '00000000-0000-0000-0000-000000000000';
-    const userMessageId = opts.overrideParentMessageId || crypto.randomUUID();
-    const responseMessageId = crypto.randomUUID();
-    this.pastMessages = await this.loadHistory(conversationId, this.options?.parentMessageId);
-
-    const userMessage = {
-      messageId: userMessageId,
-      parentMessageId,
-      conversationId,
-      sender: 'User',
-      text: message,
-      isCreatedByUser: true
-    };
-
-    if (typeof opts?.getIds === 'function') {
-      opts.getIds({
-        userMessage,
-        conversationId,
-        responseMessageId
-      });
-    }
-
-    if (typeof opts?.onStart === 'function') {
-      opts.onStart(userMessage);
-    }
-
-    await this.saveMessageToDatabase(userMessage, user);
-
-    this.result = {};
-    const responseMessage = {
-      messageId: responseMessageId,
-      conversationId,
-      parentMessageId: userMessage.messageId,
-      isCreatedByUser: false,
-      model: this.modelOptions.model,
-      sender: 'ChatGPT'
-    };
-
-    if (this.options.debug) {
-      console.debug('options');
-      console.debug(this.options);
-    }
-
-    const completionMode = this.options.tools.length === 0;
-    if (!completionMode) {
-      await this.initialize({
-        user,
-        message,
-        onAgentAction,
-        onChainEnd,
-        signal: opts.abortController.signal
-      });
-      await this.executorCall(message, opts.abortController.signal);
-    }
-
-    // If message was aborted mid-generation
-    if (this.result?.errorMessage?.length > 0 && this.result?.errorMessage?.includes('cancel')) {
-      responseMessage.text = 'Cancelled.';
-      await this.saveMessageToDatabase(responseMessage, user);
-      return { ...responseMessage, ...this.result };
-    }
-
-    if (!this.agentIsGpt3 && this.result.output) {
-      responseMessage.text = this.result.output;
-      await this.saveMessageToDatabase(responseMessage, user);
-      const textStream = new TextStream(this.result.output);
-      await textStream.processTextStream(onProgress);
-      return { ...responseMessage, ...this.result };
-    }
-
-    if (this.options.debug) {
-      console.debug('this.result', this.result);
-    }
-
-    const userProvidedPrefix = completionMode && this.options?.promptPrefix?.length > 0;
-    const promptPrefix = userProvidedPrefix
-      ? this.options.promptPrefix
-      : this.buildPromptPrefix(this.result, message);
-
-    if (this.options.debug) {
-      console.debug('promptPrefix', promptPrefix);
-    }
-
-    const finalReply = await this.sendApiMessage(this.currentMessages, userMessage, { ...opts, completionMode, promptPrefix });
-    responseMessage.text = finalReply;
-    await this.saveMessageToDatabase(responseMessage, user);
-    return { ...responseMessage, ...this.result };
-  }
-
-  async buildPrompt({ messages, promptPrefix: _promptPrefix, completionMode = false, isChatGptModel = true }) {
-    if (this.options.debug) {
-      console.debug('buildPrompt messages', messages);
-    }
-
-    const orderedMessages = messages;
-    let promptPrefix = _promptPrefix;
-    if (promptPrefix) {
-      promptPrefix = promptPrefix.trim();
-      // If the prompt prefix doesn't end with the end token, add it.
-      if (!promptPrefix.endsWith(`${this.endToken}`)) {
-        promptPrefix = `${promptPrefix.trim()}${this.endToken}\n\n`;
-      }
-      promptPrefix = `${this.startToken}Instructions:\n${promptPrefix}`;
-    } else {
-      promptPrefix = `${this.startToken}${completionInstructions} ${this.currentDateString}${this.endToken}\n\n`;
-    }
-
-    const promptSuffix = `${this.startToken}${this.chatGptLabel}:\n`; // Prompt ChatGPT to respond.
-
-    const instructionsPayload = {
-      role: 'system',
-      name: 'instructions',
-      content: promptPrefix
-    };
-
-    const messagePayload = {
-      role: 'system',
-      content: promptSuffix
-    };
-
-    if (this.isGpt3) {
-      instructionsPayload.role = 'user';
-      messagePayload.role = 'user';
-    }
-
-    if (this.isGpt3 && completionMode) {
-      instructionsPayload.content += `\n${promptSuffix}`;
-    }
-
-    // testing if this works with browser endpoint
-    if (!this.isGpt3 && this.reverseProxyUrl) {
-      instructionsPayload.role = 'user';
-    }
-
-    let currentTokenCount;
-    if (isChatGptModel) {
-      currentTokenCount =
-        this.getTokenCountForMessage(instructionsPayload) +
-        this.getTokenCountForMessage(messagePayload);
-    } else {
-      currentTokenCount = this.getTokenCount(`${promptPrefix}${promptSuffix}`);
-    }
-    let promptBody = '';
-    const maxTokenCount = this.maxPromptTokens;
-
-    // Iterate backwards through the messages, adding them to the prompt until we reach the max token count.
-    // Do this within a recursive async function so that it doesn't block the event loop for too long.
-    const buildPromptBody = async () => {
-      if (currentTokenCount < maxTokenCount && orderedMessages.length > 0) {
-        const message = orderedMessages.pop();
-        // const roleLabel = message.role === 'User' ? this.userLabel : this.chatGptLabel;
-        const roleLabel = message.role;
-        let messageString = `${this.startToken}${roleLabel}:\n${message.text}${this.endToken}\n`;
-        let newPromptBody;
-        if (promptBody || isChatGptModel) {
-          newPromptBody = `${messageString}${promptBody}`;
-        } else {
-          // Always insert prompt prefix before the last user message, if not gpt-3.5-turbo.
-          // This makes the AI obey the prompt instructions better, which is important for custom instructions.
-          // After a bunch of testing, it doesn't seem to cause the AI any confusion, even if you ask it things
-          // like "what's the last thing I wrote?".
-          newPromptBody = `${promptPrefix}${messageString}${promptBody}`;
-        }
-
-        const tokenCountForMessage = this.getTokenCount(messageString);
-        const newTokenCount = currentTokenCount + tokenCountForMessage;
-        if (newTokenCount > maxTokenCount) {
-          if (promptBody) {
-            // This message would put us over the token limit, so don't add it.
-            return false;
-          }
-          // This is the first message, so we can't add it. Just throw an error.
-          throw new Error(
-            `Prompt is too long. Max token count is ${maxTokenCount}, but prompt is ${newTokenCount} tokens long.`
-          );
-        }
-        promptBody = newPromptBody;
-        currentTokenCount = newTokenCount;
-        // wait for next tick to avoid blocking the event loop
-        await new Promise((resolve) => setTimeout(resolve, 0));
-        return buildPromptBody();
-      }
-      return true;
-    };
-
-    await buildPromptBody();
-
-    // const prompt = `${promptBody}${promptSuffix}`;
-    const prompt = promptBody;
-    if (isChatGptModel) {
-      messagePayload.content = prompt;
-      // Add 2 tokens for metadata after all messages have been counted.
-      currentTokenCount += 2;
-    }
-
-    if (this.isGpt3 && messagePayload.content.length > 0) {
-      const context = `Chat History:\n`;
-      messagePayload.content = `${context}${prompt}`;
-      currentTokenCount += this.getTokenCount(context);
-    }
-
-    // Use up to `this.maxContextTokens` tokens (prompt + response), but try to leave `this.maxTokens` tokens for the response.
-    this.modelOptions.max_tokens = Math.min(
-      this.maxContextTokens - currentTokenCount,
-      this.maxResponseTokens
-    );
-
-    if (this.isGpt3 && !completionMode) {
-      messagePayload.content += promptSuffix;
-      return [instructionsPayload, messagePayload];
-    }
-
-    if (isChatGptModel) {
-      const result = [messagePayload, instructionsPayload];
-      return result.filter((message) => message.content.length > 0);
-    }
-
-    this.completionPromptTokens = currentTokenCount;
-    return prompt;
-  }
-
-  getTokenCount(text) {
-    return this.gptEncoder.encode(text, 'all').length;
-  }
-
-  /**
-   * Algorithm adapted from "6. Counting tokens for chat API calls" of
-   * https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
-   *
-   * An additional 2 tokens need to be added for metadata after all messages have been counted.
-   *
-   * @param {*} message
-   */
-  getTokenCountForMessage(message) {
-    // Map each property of the message to the number of tokens it contains
-    const propertyTokenCounts = Object.entries(message).map(([key, value]) => {
-      // Count the number of tokens in the property value
-      const numTokens = this.getTokenCount(value);
-
-      // Subtract 1 token if the property key is 'name'
-      const adjustment = key === 'name' ? 1 : 0;
-      return numTokens - adjustment;
-    });
-
-    // Sum the number of tokens in all properties and add 4 for metadata
-    return propertyTokenCounts.reduce((a, b) => a + b, 4);
-  }
-
-  /**
-   * Iterate through messages, building an array based on the parentMessageId.
-   * Each message has an id and a parentMessageId. The parentMessageId is the id of the message that this message is a reply to.
-   * @param messages
-   * @param parentMessageId
-   * @returns {*[]} An array containing the messages in the order they should be displayed, starting with the root message.
-   */
-  static getMessagesForConversation(messages, parentMessageId) {
-    const orderedMessages = [];
-    let currentMessageId = parentMessageId;
-    while (currentMessageId) {
-      // eslint-disable-next-line no-loop-func
-      const message = messages.find((m) => m.messageId === currentMessageId);
-      if (!message) {
-        break;
-      }
-      orderedMessages.unshift(message);
-      currentMessageId = message.parentMessageId;
-    }
-
-    if (orderedMessages.length === 0) {
-      return [];
-    }
-
-    return orderedMessages.map((msg) => ({
-      messageId: msg.messageId,
-      parentMessageId: msg.parentMessageId,
-      role: msg.isCreatedByUser ? 'User' : 'ChatGPT',
-      text: msg.text
-    }));
-  }
-
-  /**
-   * Extracts the action tool values from the intermediate steps array.
-   * Each step object in the array contains an action object with a tool property.
-   * This function returns an array of tool values.
-   *
-   * @param {Object[]} intermediateSteps - An array of intermediate step objects.
-   * @returns {string} An string of action tool values from each step.
-   */
-  extractToolValues(intermediateSteps) {
-    const tools = intermediateSteps.map((step) => step.action.tool);
-
-    if (tools.length === 0) {
-      return '';
-    }
-
-    const uniqueTools = [...new Set(tools)];
-
-    if (tools.length === 1) {
-      return tools[0] + ' plugin';
-    }
-
-    return uniqueTools.join(' plugin, ');
-  }
-}
-
-module.exports = ChatAgent;

api/app/langchain/ChatAgent.test.js

@@ -1,92 +0,0 @@
-const mongoose = require('mongoose');
-const ChatAgent = require('./ChatAgent');
-const connectDb = require('../../lib/db/connectDb');
-const Conversation = require('../../models/Conversation');
-
-describe('ChatAgent', () => {
-  let TestAgent;
-  let options = {
-    tools: [],
-    modelOptions: {
-      model: 'gpt-3.5-turbo',
-      temperature: 0,
-      max_tokens: 2
-    },
-    agentOptions: {
-      model: 'gpt-3.5-turbo',
-    }
-  };
-  let parentMessageId;
-  let conversationId;
-  const userMessage = 'Hello, ChatGPT!';
-  const apiKey = process.env.OPENAI_API_KEY;
-
-  beforeAll(async () => {
-    await connectDb();
-  });
-
-  beforeEach(() => {
-    TestAgent = new ChatAgent(apiKey, options);
-  });
-
-  afterAll(async () => {
-    // Delete the messages and conversation created by the test
-    await Conversation.deleteConvos(null, { conversationId });
-    await mongoose.connection.close();
-  });
-
-  test('initializes ChatAgent without crashing', () => {
-    expect(TestAgent).toBeInstanceOf(ChatAgent);
-  });
-
-  test('check setOptions function', () => {
-    expect(TestAgent.agentIsGpt3).toBe(true);
-  });
-
-  describe('sendMessage', () => {
-    test('sendMessage should return a response message', async () => {
-      const expectedResult = expect.objectContaining({
-        sender: 'ChatGPT',
-        text: expect.any(String),
-        isCreatedByUser: false,
-        messageId: expect.any(String),
-        parentMessageId: expect.any(String),
-        conversationId: expect.any(String)
-      });
-
-      const response = await TestAgent.sendMessage(userMessage);
-      console.log(response);
-      parentMessageId = response.messageId;
-      conversationId = response.conversationId;
-      expect(response).toEqual(expectedResult);
-    });
-
-    test('sendMessage should work with provided conversationId and parentMessageId', async () => {
-      const userMessage = 'Second message in the conversation';
-      const opts = {
-        conversationId,
-        parentMessageId
-      };
-
-      const expectedResult = expect.objectContaining({
-        sender: 'ChatGPT',
-        text: expect.any(String),
-        isCreatedByUser: false,
-        messageId: expect.any(String),
-        parentMessageId: expect.any(String),
-        conversationId: opts.conversationId
-      });
-
-      const response = await TestAgent.sendMessage(userMessage, opts);
-      parentMessageId = response.messageId;
-      expect(response.conversationId).toEqual(conversationId);
-      expect(response).toEqual(expectedResult);
-    });
-
-    test('should return chat history', async () => {
-      const chatMessages = await TestAgent.loadHistory(conversationId, parentMessageId);
-      expect(TestAgent.currentMessages).toHaveLength(4);
-      expect(chatMessages[0].text).toEqual(userMessage);
-    });
-  });
-});

api/app/langchain/agents/PlanAndExecute/initializePAEAgent.js

@@ -1,77 +0,0 @@
-const {
-  ChainStepExecutor,
-  LLMPlanner,
-  PlanOutputParser,
-  PlanAndExecuteAgentExecutor
-} = require('langchain/experimental/plan_and_execute');
-const { LLMChain } = require('langchain/chains');
-const { ChatAgent, AgentExecutor } = require('langchain/agents');
-const { BufferMemory, ChatMessageHistory } = require('langchain/memory');
-const {
-  ChatPromptTemplate,
-  SystemMessagePromptTemplate,
-  HumanMessagePromptTemplate
-} = require('langchain/prompts');
-
-const DEFAULT_STEP_EXECUTOR_HUMAN_CHAT_MESSAGE_TEMPLATE = `{chat_history}
-
-Previous steps: {previous_steps}
-Current objective: {current_step}
-{agent_scratchpad}
-You may extract and combine relevant data from your previous steps when responding to me.`;
-
-const PLANNER_SYSTEM_PROMPT_MESSAGE_TEMPLATE = [
-  `Let's first understand the problem and devise a plan to solve the problem.`,
-  `Please output the plan starting with the header "Plan:"`,
-  `and then followed by a numbered list of steps.`,
-  `Please make the plan the minimum number of steps required`,
-  `to answer the query or complete the task accurately and precisely.`,
-  `Your steps should be general, and should not require a specific method to solve a step. If the task is a question,`,
-  `the final step in the plan must be the following: "Given the above steps taken,`,
-  `please respond to the original query."`,
-  `At the end of your plan, say "<END_OF_PLAN>"`
-].join(' ');
-
-const PLANNER_CHAT_PROMPT = /* #__PURE__ */ ChatPromptTemplate.fromPromptMessages([
-  /* #__PURE__ */ SystemMessagePromptTemplate.fromTemplate(PLANNER_SYSTEM_PROMPT_MESSAGE_TEMPLATE),
-  /* #__PURE__ */ HumanMessagePromptTemplate.fromTemplate(`{input}`)
-]);
-
-const initializePAEAgent = async ({ tools: _tools, model: llm, pastMessages, ...rest }) => {
-  //removed currentDateString
-  const tools = _tools.filter((tool) => tool.name !== 'self-reflection');
-
-  const memory = new BufferMemory({
-    chatHistory: new ChatMessageHistory(pastMessages),
-    // returnMessages: true, // commenting this out retains memory
-    memoryKey: 'chat_history',
-    humanPrefix: 'User',
-    aiPrefix: 'Assistant',
-    inputKey: 'input',
-    outputKey: 'output'
-  });
-
-  const plannerLlmChain = new LLMChain({
-    llm,
-    prompt: PLANNER_CHAT_PROMPT,
-    memory
-  });
-  const planner = new LLMPlanner(plannerLlmChain, new PlanOutputParser());
-
-  const agent = ChatAgent.fromLLMAndTools(llm, tools, {
-    humanMessageTemplate: DEFAULT_STEP_EXECUTOR_HUMAN_CHAT_MESSAGE_TEMPLATE
-  });
-
-  const stepExecutor = new ChainStepExecutor(
-    AgentExecutor.fromAgentAndTools({ agent, tools, memory, ...rest })
-  );
-
-  return new PlanAndExecuteAgentExecutor({
-    planner,
-    stepExecutor
-  });
-};
-
-module.exports = {
-  initializePAEAgent
-};

api/app/langchain/demos/demo-aiplugin.js

@@ -1,31 +0,0 @@
-require('dotenv').config();
-const { ChatOpenAI } = require( "langchain/chat_models/openai");
-const { initializeAgentExecutorWithOptions } = require( "langchain/agents");
-const HttpRequestTool = require('../tools/HttpRequestTool');
-const AIPluginTool = require('../tools/AIPluginTool');
-
-const run = async () => {
-  const openAIApiKey = process.env.OPENAI_API_KEY;
-  const tools = [
-    new HttpRequestTool(),
-    await AIPluginTool.fromPluginUrl(
-      "https://www.klarna.com/.well-known/ai-plugin.json", new ChatOpenAI({ temperature: 0, openAIApiKey })
-    ),
-  ];
-  const agent = await initializeAgentExecutorWithOptions(
-    tools,
-    new ChatOpenAI({ temperature: 0, openAIApiKey }),
-    { agentType: "chat-zero-shot-react-description", verbose: true }
-  );
-
-  const result = await agent.call({
-    input: "what t shirts are available in klarna?",
-  });
-
-  console.log({ result });
-};
-
-(async () => {
-  await run();
-})();
-

api/app/langchain/demos/demo-yaml.js

@@ -1,47 +0,0 @@
-require('dotenv').config();
-
-const fs = require( "fs");
-const yaml = require( "js-yaml");
-const { OpenAI } = require( "langchain/llms/openai");
-const { JsonSpec } = require( "langchain/tools");
-const { createOpenApiAgent, OpenApiToolkit } = require( "langchain/agents");
-
-const run = async () => {
-  let data;
-  try {
-    const yamlFile = fs.readFileSync("./app/langchain/demos/klarna.yaml", "utf8");
-    data = yaml.load(yamlFile);
-    if (!data) {
-      throw new Error("Failed to load OpenAPI spec");
-    }
-  } catch (e) {
-    console.error(e);
-    return;
-  }
-
-  const headers = {
-    "Content-Type": "application/json",
-    // Authorization: `Bearer ${process.env.OPENAI_API_KEY}`,
-  };
-  const model = new OpenAI({ temperature: 0 });
-  const toolkit = new OpenApiToolkit(new JsonSpec(data), model, headers);
-  const executor = createOpenApiAgent(model, toolkit, { verbose: true });
-
-  const input = `Find me some medium sized blue shirts`;
-  console.log(`Executing with input "${input}"...`);
-
-  const result = await executor.call({ input });
-  console.log(`Got output ${result.output}`);
-
-  console.log(
-    `Got intermediate steps ${JSON.stringify(
-      result.intermediateSteps,
-      null,
-      2
-    )}`
-  );
-};
-
-(async () => {
-  await run();
-})();

api/app/langchain/demos/klarna.yaml

@@ -1,79 +0,0 @@
-openapi: 3.0.1
-servers:
-  - url: https://www.klarna.com/us/shopping
-info:
-  title: Open AI Klarna product Api
-  version: v0
-  x-apisguru-categories:
-    - ecommerce
-  x-logo:
-    url: https://www.klarna.com/static/img/social-prod-imagery-blinds-beauty-default.jpg
-  x-origin:
-    - format: openapi
-      url: https://www.klarna.com/us/shopping/public/openai/v0/api-docs/
-      version: "3.0"
-  x-providerName: klarna.com
-  x-serviceName: openai
-tags:
-  - description: Open AI Product Endpoint. Query for products.
-    name: open-ai-product-endpoint
-paths:
-  /public/openai/v0/products:
-    get:
-      deprecated: false
-      operationId: productsUsingGET
-      parameters:
-        - description: A precise query that matches one very small category or product that needs to be searched for to find the products the user is looking for. If the user explicitly stated what they want, use that as a query. The query is as specific as possible to the product name or category mentioned by the user in its singular form, and don't contain any clarifiers like latest, newest, cheapest, budget, premium, expensive or similar. The query is always taken from the latest topic, if there is a new topic a new query is started.
-          in: query
-          name: q
-          required: true
-          schema:
-            type: string
-        - description: number of products returned
-          in: query
-          name: size
-          required: false
-          schema:
-            type: integer
-        - description: maximum price of the matching product in local currency, filters results
-          in: query
-          name: budget
-          required: false
-          schema:
-            type: integer
-      responses:
-        "200":
-          content:
-            application/json:
-              schema:
-                $ref: "#/components/schemas/ProductResponse"
-          description: Products found
-        "503":
-          description: one or more services are unavailable
-      summary: API for fetching Klarna product information
-      tags:
-        - open-ai-product-endpoint
-components:
-  schemas:
-    Product:
-      properties:
-        attributes:
-          items:
-            type: string
-          type: array
-        name:
-          type: string
-        price:
-          type: string
-        url:
-          type: string
-      title: Product
-      type: object
-    ProductResponse:
-      properties:
-        products:
-          items:
-            $ref: "#/components/schemas/Product"
-          type: array
-      title: ProductResponse
-      type: object

api/app/langchain/demos/planExecutor.js

@@ -1,32 +0,0 @@
-require('dotenv').config();
-const { Calculator } = require('langchain/tools/calculator');
-const { SerpAPI } = require('langchain/tools');
-const { ChatOpenAI } = require('langchain/chat_models/openai');
-const { PlanAndExecuteAgentExecutor } = require('langchain/experimental/plan_and_execute');
-
-const tools = [
-  new Calculator(),
-  new SerpAPI(process.env.SERPAPI_API_KEY || '', {
-    location: 'Austin,Texas,United States',
-    hl: 'en',
-    gl: 'us'
-  })
-];
-const model = new ChatOpenAI({
-  temperature: 0,
-  modelName: 'gpt-3.5-turbo',
-  verbose: true,
-  openAIApiKey: process.env.OPENAI_API_KEY
-});
-const executor = PlanAndExecuteAgentExecutor.fromLLMAndTools({
-  llm: model,
-  tools
-});
-
-(async () => {
-  const result = await executor.call({
-    input: `Who is the current president of the United States? What is their current age raised to the second power?`
-  });
-
-  console.log({ result });
-})();

api/app/langchain/tools/index.js

@@ -1,10 +0,0 @@
-const SelfReflectionTool = require('./SelfReflection');
-const availableTools = require('./manifest.json');
-const { validateTools, loadTools } = require('./handleTools');
-
-module.exports = {
-  validateTools,
-  loadTools,
-  availableTools,
-  SelfReflectionTool
-};

api/app/titleConvo.js

@@ -1,21 +1,6 @@
-// const { Configuration, OpenAIApi } = require('openai');
+
 const _ = require('lodash');
-const { genAzureChatCompletion } = require('../utils/genAzureEndpoints');
-
-// const proxyEnvToAxiosProxy = (proxyString) => {
-//   if (!proxyString) return null;
-
-//   const regex = /^([^:]+):\/\/(?:([^:@]*):?([^:@]*)@)?([^:]+)(?::(\d+))?/;
-//   const [, protocol, username, password, host, port] = proxyString.match(regex);
-//   const proxyConfig = {
-//     protocol,
-//     host,
-//     port: port ? parseInt(port) : undefined,
-//     auth: username && password ? { username, password } : undefined
-//   };
-
-//   return proxyConfig;
-// };
+const { genAzureChatCompletion, getAzureCredentials } = require('../utils/');
 
 const titleConvo = async ({ text, response, oaiApiKey }) => {
   let title = 'New Chat';
@@ -34,7 +19,7 @@ const titleConvo = async ({ text, response, oaiApiKey }) => {
     ||>Title:`
     };
 
-    const azure = process.env.AZURE_OPENAI_API_KEY ? true : false;
+    const azure = process.env.AZURE_API_KEY ? true : false;
     const options = {
       azure,
       reverseProxyUrl: process.env.OPENAI_REVERSE_PROXY || null,
@@ -53,12 +38,8 @@ const titleConvo = async ({ text, response, oaiApiKey }) => {
     let apiKey = oaiApiKey || process.env.OPENAI_API_KEY;
 
     if (azure) {
-      apiKey = process.env.AZURE_OPENAI_API_KEY;
-      titleGenClientOptions.reverseProxyUrl = genAzureChatCompletion({
-        azureOpenAIApiInstanceName: process.env.AZURE_OPENAI_API_INSTANCE_NAME,
-        azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME,
-        azureOpenAIApiVersion: process.env.AZURE_OPENAI_API_VERSION
-      });
+      apiKey = process.env.AZURE_API_KEY;
+      titleGenClientOptions.reverseProxyUrl = genAzureChatCompletion(getAzureCredentials());
     }
 
     const titleGenClient = new ChatGPTClient(apiKey, titleGenClientOptions);

api/models/Message.js

@@ -14,6 +14,7 @@ module.exports = {
     error,
     unfinished,
     cancelled,
+    tokenCount = null,
     plugin = null,
     model = null,
   }) {
@@ -31,6 +32,7 @@ module.exports = {
           error,
           unfinished,
           cancelled,
+          tokenCount,
           plugin,
           model
         },
@@ -43,14 +45,41 @@ module.exports = {
         parentMessageId,
         sender,
         text,
-        isCreatedByUser
+        isCreatedByUser,
+        tokenCount,
       };
     } catch (err) {
       console.error(`Error saving message: ${err}`);
       throw new Error('Failed to save message.');
     }
   },
+  async updateMessage(message) {
+    try {
+      const { messageId, ...update } = message;
+      const updatedMessage = await Message.findOneAndUpdate(
+        { messageId },
+        update,
+        { new: true }
+      );
 
+      if (!updatedMessage) {
+        throw new Error('Message not found.');
+      }
+
+      return {
+        messageId: updatedMessage.messageId,
+        conversationId: updatedMessage.conversationId,
+        parentMessageId: updatedMessage.parentMessageId,
+        sender: updatedMessage.sender,
+        text: updatedMessage.text,
+        isCreatedByUser: updatedMessage.isCreatedByUser,
+        tokenCount: updatedMessage.tokenCount,
+      };
+    } catch (err) {
+      console.error(`Error updating message: ${err}`);
+      throw new Error('Failed to update message.');
+    }
+  },
   async deleteMessagesSince({ messageId, conversationId }) {
     try {
       const message = await Message.findOne({ messageId }).exec();

api/models/User.js

@@ -25,7 +25,7 @@ const userSchema = mongoose.Schema(
       type: String,
       lowercase: true,
       required: [true, "can't be blank"],
-      match: [/^[a-zA-Z0-9_]+$/, 'is invalid'],
+      match: [/^[a-zA-Z0-9_-]+$/, 'is invalid'],
       index: true
     },
     email: {
@@ -45,7 +45,7 @@ const userSchema = mongoose.Schema(
       type: String,
       trim: true,
       minlength: 8,
-      maxlength: 60
+      maxlength: 128
     },
     avatar: {
       type: String,
@@ -65,6 +65,16 @@ const userSchema = mongoose.Schema(
       unique: true,
       sparse: true
     },
+    openidId: {
+      type: String,
+      unique: true,
+      sparse: true
+    },
+    githubId: {
+      type: String,
+      unique: true,
+      sparse: true
+    },
     plugins: {
       type: Array,
       default: []
@@ -157,9 +167,9 @@ module.exports.validateUser = (user) => {
     username: Joi.string()
       .min(2)
       .max(80)
-      .regex(/^[a-zA-Z0-9_]+$/)
+      .regex(/^[a-zA-Z0-9_-]+$/)
       .required(),
-    password: Joi.string().min(8).max(60).allow('').allow(null)
+    password: Joi.string().min(8).max(128).allow('').allow(null)
   };
 
   return schema.validate(user);

api/models/index.js

@@ -1,10 +1,11 @@
-const { getMessages, saveMessage, deleteMessagesSince, deleteMessages } = require('./Message');
+const { getMessages, saveMessage, updateMessage, deleteMessagesSince, deleteMessages } = require('./Message');
 const { getConvoTitle, getConvo, saveConvo } = require('./Conversation');
 const { getPreset, getPresets, savePreset, deletePresets } = require('./Preset');
 
 module.exports = {
   getMessages,
   saveMessage,
+  updateMessage,
   deleteMessagesSince,
   deleteMessages,
 

api/models/schema/messageSchema.js

@@ -31,6 +31,12 @@ const messageSchema = mongoose.Schema(
       type: String
       // required: true
     },
+    tokenCount: {
+      type: Number
+    },
+    refinedTokenCount: {
+      type: Number
+    },
     sender: {
       type: String,
       required: true,
@@ -41,6 +47,9 @@ const messageSchema = mongoose.Schema(
       required: true,
       meiliIndex: true
     },
+    refinedMessageText: {
+      type: String
+    },
     isCreatedByUser: {
       type: Boolean,
       required: true,

api/nodemon.json

@@ -1,6 +0,0 @@
-{
-  "ignore": [
-    "api/data/",
-    "data"
-  ]
-}

api/package.json

@@ -1,18 +1,12 @@
 {
-  "name": "chat-backend",
-  "version": "0.5.0",
+  "name": "@librechat/backend",
+  "version": "0.5.3",
   "description": "",
   "scripts": {
     "start": "echo 'please run this from the root directory'",
     "server-dev": "echo 'please run this from the root directory'",
     "test": "cross-env NODE_ENV=test jest",
-    "test:ci": "jest --ci",
-    "test2": "node --inspect app/langchain/test2.js",
-    "test3": "node --inspect app/langchain/test3.js",
-    "test4": "node --inspect app/langchain/test4.js",
-    "test5": "node --inspect app/langchain/test5.js",
-    "test8": "node --inspect app/langchain/test8.js",
-    "langchain": "node app/langchain/test2.js"
+    "test:ci": "jest --ci"
   },
   "repository": {
     "type": "git",
@@ -38,6 +32,7 @@
     "dotenv": "^16.0.3",
     "eslint": "^8.41.0",
     "express": "^4.18.2",
+    "express-session": "^1.17.3",
     "googleapis": "^118.0.0",
     "handlebars": "^4.7.7",
     "html": "^1.0.0",
@@ -46,12 +41,13 @@
     "jsonwebtoken": "^9.0.0",
     "keyv": "^4.5.2",
     "keyv-file": "^0.2.0",
-    "langchain": "^0.0.92",
+    "langchain": "^0.0.103",
     "lodash": "^4.17.21",
     "meilisearch": "^0.33.0",
     "mongoose": "^7.1.1",
     "nodemailer": "^6.9.1",
     "openai": "^3.2.1",
+    "openid-client": "^5.4.2",
     "passport": "^0.6.0",
     "passport-facebook": "^3.0.0",
     "passport-google-oauth20": "^2.0.0",
@@ -64,6 +60,7 @@
   "devDependencies": {
     "jest": "^29.5.0",
     "nodemon": "^2.0.20",
-    "path": "^0.12.7"
+    "path": "^0.12.7",
+    "supertest": "^6.3.3"
   }
 }

api/server/controllers/PluginController.js

@@ -25,7 +25,7 @@ const isPluginAuthenticated = (plugin) => {
 const getAvailablePluginsController = async (req, res) => {
   try {
     fs.readFile(
-      path.join(__dirname, '..', '..', 'app', 'langchain', 'tools', 'manifest.json'),
+      path.join(__dirname, '..', '..', 'app', 'clients', 'tools', 'manifest.json'),
       'utf8',
       (err, data) => {
         if (err) {

api/server/index.js

@@ -1,11 +1,12 @@
 const express = require('express');
+const session = require('express-session');
 const connectDb = require('../lib/db/connectDb');
 const migrateDb = require('../lib/db/migrateDb');
 const indexSync = require('../lib/db/indexSync');
 const path = require('path');
 const cors = require('cors');
 const routes = require('./routes');
-const errorController = require('./controllers/error.controller');
+const errorController = require('./controllers/ErrorController');
 const passport = require('passport');
 const port = process.env.PORT || 3080;
 const host = process.env.HOST || 'localhost';
@@ -41,6 +42,20 @@ config.validate(); // Validate the config
   if (process.env.FACEBOOK_CLIENT_ID && process.env.FACEBOOK_CLIENT_SECRET) {
     require('../strategies/facebookStrategy');
   }
+  if (process.env.GITHUB_CLIENT_ID && process.env.GITHUB_CLIENT_SECRET) {
+    require('../strategies/githubStrategy');
+  }
+  if (process.env.OPENID_CLIENT_ID && process.env.OPENID_CLIENT_SECRET &&
+      process.env.OPENID_ISSUER && process.env.OPENID_SCOPE &&
+      process.env.OPENID_SESSION_SECRET) {
+    app.use(session({
+      secret: process.env.OPENID_SESSION_SECRET,
+      resave: false,
+      saveUninitialized: false
+    }));
+    app.use(passport.session());
+    require('../strategies/openidStrategy');
+  }
   app.use('/oauth', routes.oauth);
   // api endpoint
   app.use('/api/auth', routes.auth);
@@ -54,6 +69,7 @@ config.validate(); // Validate the config
   app.use('/api/tokenizer', routes.tokenizer);
   app.use('/api/endpoints', routes.endpoints);
   app.use('/api/plugins', routes.plugins);
+  app.use('/api/config', routes.config);
 
   // static files
   app.get('/*', function (req, res) {

api/server/routes/__tests__/config.spec.js

@@ -0,0 +1,56 @@
+const request = require('supertest');
+const express = require('express');
+const routes = require('../');
+const app = express();
+app.use('/api/config', routes.config);
+
+afterEach(() => {
+  delete process.env.APP_TITLE;
+  delete process.env.GOOGLE_CLIENT_ID;
+  delete process.env.GOOGLE_CLIENT_SECRET;
+  delete process.env.OPENID_CLIENT_ID;
+  delete process.env.OPENID_CLIENT_SECRET;
+  delete process.env.OPENID_ISSUER;
+  delete process.env.OPENID_SESSION_SECRET;
+  delete process.env.OPENID_BUTTON_LABEL;
+  delete process.env.OPENID_AUTH_URL;
+  delete process.env.GITHUB_CLIENT_ID;
+  delete process.env.GITHUB_CLIENT_SECRET;
+  delete process.env.DOMAIN_SERVER;
+  delete process.env.ALLOW_REGISTRATION;
+});
+
+//TODO: This works/passes locally but http request tests fail with 404 in CI. Need to figure out why.
+
+// eslint-disable-next-line jest/no-disabled-tests
+describe.skip('GET /', () => {
+  it('should return 200 and the correct body', async () => {
+    process.env.APP_TITLE = 'Test Title';
+    process.env.GOOGLE_CLIENT_ID = 'Test Google Client Id';
+    process.env.GOOGLE_CLIENT_SECRET = 'Test Google Client Secret';
+    process.env.OPENID_CLIENT_ID= 'Test OpenID Id';
+    process.env.OPENID_CLIENT_SECRET= 'Test OpenID Secret';
+    process.env.OPENID_ISSUER= 'Test OpenID Issuer';
+    process.env.OPENID_SESSION_SECRET= 'Test Secret';
+    process.env.OPENID_BUTTON_LABEL= 'Test OpenID';
+    process.env.OPENID_AUTH_URL= 'http://test-server.com';
+    process.env.GITHUB_CLIENT_ID = 'Test Github client Id';
+    process.env.GITHUB_CLIENT_SECRET= 'Test Github client Secret';
+    process.env.DOMAIN_SERVER = 'http://test-server.com';
+    process.env.ALLOW_REGISTRATION = 'true';
+
+    const response = await request(app).get('/');
+
+    expect(response.statusCode).toBe(200);
+    expect(response.body).toEqual({
+      appTitle: 'Test Title',
+      googleLoginEnabled: true,
+      openidLoginEnabled: true,
+      openidLabel: 'Test OpenID',
+      openidImageUrl: 'http://test-server.com',
+      githubLoginEnabled: true,
+      serverDomain: 'http://test-server.com',
+      registrationEnabled: 'true',
+    });
+  });
+});

api/server/routes/ask/askChatGPTBrowser.js

@@ -1,7 +1,7 @@
 const express = require('express');
 const crypto = require('crypto');
 const router = express.Router();
-const { getChatGPTBrowserModels } = require('../endpoints');
+// const { getChatGPTBrowserModels } = require('../endpoints');
 const { browserClient } = require('../../../app/');
 const { saveMessage, getConvoTitle, saveConvo, getConvo } = require('../../../models');
 const { handleError, sendMessage, createOnProgress, handleText } = require('./handlers');
@@ -38,9 +38,9 @@ router.post('/', requireJwtAuth, async (req, res) => {
     token: req.body?.token ?? null
   };
 
-  const availableModels = getChatGPTBrowserModels();
-  if (availableModels.find((model) => model === endpointOption.model) === undefined)
-    return handleError(res, { text: 'Illegal request: model' });
+  // const availableModels = getChatGPTBrowserModels();
+  // if (availableModels.find((model) => model === endpointOption.model) === undefined)
+  //   return handleError(res, { text: 'Illegal request: model' });
 
   console.log('ask log', {
     userMessage,

api/server/routes/ask/askOpenAI.js

@@ -1,286 +0,0 @@
-const express = require('express');
-const crypto = require('crypto');
-const router = express.Router();
-const addToCache = require('./addToCache');
-const { getOpenAIModels } = require('../endpoints');
-const { titleConvo, askClient } = require('../../../app/');
-const { saveMessage, getConvoTitle, saveConvo, getConvo } = require('../../../models');
-const { handleError, sendMessage, createOnProgress, handleText } = require('./handlers');
-const requireJwtAuth = require('../../../middleware/requireJwtAuth');
-
-const abortControllers = new Map();
-
-router.post('/abort', requireJwtAuth, async (req, res) => {
-  const { abortKey } = req.body;
-  console.log(`req.body`, req.body);
-  if (!abortControllers.has(abortKey)) {
-    return res.status(404).send('Request not found');
-  }
-
-  const { abortController } = abortControllers.get(abortKey);
-
-  abortControllers.delete(abortKey);
-  const ret = await abortController.abortAsk();
-  console.log('Aborted request', abortKey);
-  console.log('Aborted message:', ret);
-
-  res.send(JSON.stringify(ret));
-});
-
-router.post('/', requireJwtAuth, async (req, res) => {
-  const {
-    endpoint,
-    text,
-    overrideParentMessageId = null,
-    parentMessageId,
-    conversationId: oldConversationId
-  } = req.body;
-  if (text.length === 0) return handleError(res, { text: 'Prompt empty or too short' });
-  if (endpoint !== 'openAI') return handleError(res, { text: 'Illegal request' });
-
-  // build user message
-  const conversationId = oldConversationId || crypto.randomUUID();
-  const isNewConversation = !oldConversationId;
-  const userMessageId = crypto.randomUUID();
-  const userParentMessageId = parentMessageId || '00000000-0000-0000-0000-000000000000';
-  const userMessage = {
-    messageId: userMessageId,
-    sender: 'User',
-    text,
-    parentMessageId: userParentMessageId,
-    conversationId,
-    isCreatedByUser: true
-  };
-
-  // build endpoint option
-  const endpointOption = {
-    model: req.body?.model ?? 'gpt-3.5-turbo',
-    chatGptLabel: req.body?.chatGptLabel ?? null,
-    promptPrefix: req.body?.promptPrefix ?? null,
-    temperature: req.body?.temperature ?? 1,
-    top_p: req.body?.top_p ?? 1,
-    presence_penalty: req.body?.presence_penalty ?? 0,
-    frequency_penalty: req.body?.frequency_penalty ?? 0
-  };
-
-  const availableModels = getOpenAIModels();
-  if (availableModels.find((model) => model === endpointOption.model) === undefined)
-    return handleError(res, { text: 'Illegal request: model' });
-
-  console.log('ask log', {
-    userMessage,
-    endpointOption,
-    conversationId
-  });
-
-  if (!overrideParentMessageId) {
-    await saveMessage(userMessage);
-    await saveConvo(req.user.id, {
-      ...userMessage,
-      ...endpointOption,
-      conversationId,
-      endpoint
-    });
-  }
-
-  // eslint-disable-next-line no-use-before-define
-  return await ask({
-    isNewConversation,
-    userMessage,
-    endpointOption,
-    conversationId,
-    preSendRequest: true,
-    overrideParentMessageId,
-    req,
-    res
-  });
-});
-
-const ask = async ({
-  isNewConversation,
-  userMessage,
-  endpointOption,
-  conversationId,
-  preSendRequest = true,
-  overrideParentMessageId = null,
-  req,
-  res
-}) => {
-  let { text, parentMessageId: userParentMessageId, messageId: userMessageId } = userMessage;
-  const userId = req.user.id;
-  let responseMessageId = crypto.randomUUID();
-
-  res.writeHead(200, {
-    Connection: 'keep-alive',
-    'Content-Type': 'text/event-stream',
-    'Cache-Control': 'no-cache, no-transform',
-    'Access-Control-Allow-Origin': '*',
-    'X-Accel-Buffering': 'no'
-  });
-
-  if (preSendRequest) sendMessage(res, { message: userMessage, created: true });
-
-  try {
-    let lastSavedTimestamp = 0;
-    const { onProgress: progressCallback, getPartialText } = createOnProgress({
-      onProgress: ({ text }) => {
-        const currentTimestamp = Date.now();
-        if (currentTimestamp - lastSavedTimestamp > 500) {
-          lastSavedTimestamp = currentTimestamp;
-          saveMessage({
-            messageId: responseMessageId,
-            sender: endpointOption?.chatGptLabel || 'ChatGPT',
-            conversationId,
-            parentMessageId: overrideParentMessageId || userMessageId,
-            text: text,
-            unfinished: true,
-            cancelled: false,
-            error: false
-          });
-        }
-      }
-    });
-
-    let abortController = new AbortController();
-    abortController.abortAsk = async function () {
-      this.abort();
-
-      const responseMessage = {
-        messageId: responseMessageId,
-        sender: endpointOption?.chatGptLabel || 'ChatGPT',
-        conversationId,
-        parentMessageId: overrideParentMessageId || userMessageId,
-        text: getPartialText(),
-        unfinished: false,
-        cancelled: true,
-        error: false
-      };
-
-      saveMessage(responseMessage);
-      await addToCache({ endpoint: 'openAI', endpointOption, userMessage, responseMessage });
-
-      return {
-        title: await getConvoTitle(req.user.id, conversationId),
-        final: true,
-        conversation: await getConvo(req.user.id, conversationId),
-        requestMessage: userMessage,
-        responseMessage: responseMessage
-      };
-    };
-    const abortKey = conversationId;
-    abortControllers.set(abortKey, { abortController, ...endpointOption });
-    const oaiApiKey = req.body?.token ?? null;
-
-    let response = await askClient({
-      text,
-      parentMessageId: userParentMessageId,
-      conversationId,
-      oaiApiKey,
-      ...endpointOption,
-      onProgress: progressCallback.call(null, {
-        res,
-        text,
-        parentMessageId: overrideParentMessageId || userMessageId
-      }),
-      abortController,
-      userId
-    });
-
-    abortControllers.delete(abortKey);
-    console.log('CLIENT RESPONSE', response);
-
-    const newConversationId = response.conversationId || conversationId;
-    const newUserMessageId = response.parentMessageId || userMessageId;
-    const newResponseMessageId = response.messageId;
-
-    // STEP1 generate response message
-    response.text = response.response || '**ChatGPT refused to answer.**';
-
-    let responseMessage = {
-      conversationId: newConversationId,
-      messageId: responseMessageId,
-      newMessageId: newResponseMessageId,
-      parentMessageId: overrideParentMessageId || newUserMessageId,
-      text: await handleText(response),
-      sender: endpointOption?.chatGptLabel || 'ChatGPT',
-      unfinished: false,
-      cancelled: false,
-      error: false
-    };
-
-    await saveMessage(responseMessage);
-    responseMessage.messageId = newResponseMessageId;
-
-    // STEP2 update the conversation
-    let conversationUpdate = { conversationId: newConversationId, endpoint: 'openAI' };
-    if (conversationId != newConversationId)
-      if (isNewConversation) {
-        // change the conversationId to new one
-        conversationUpdate = {
-          ...conversationUpdate,
-          conversationId: conversationId,
-          newConversationId: newConversationId
-        };
-      } else {
-        // create new conversation
-        conversationUpdate = {
-          ...conversationUpdate,
-          ...endpointOption
-        };
-      }
-
-    await saveConvo(req.user.id, conversationUpdate);
-    conversationId = newConversationId;
-
-    // STEP3 update the user message
-    userMessage.conversationId = newConversationId;
-    userMessage.messageId = newUserMessageId;
-
-    // If response has parentMessageId, the fake userMessage.messageId should be updated to the real one.
-    if (!overrideParentMessageId)
-      await saveMessage({
-        ...userMessage,
-        messageId: userMessageId,
-        newMessageId: newUserMessageId
-      });
-    userMessageId = newUserMessageId;
-
-    sendMessage(res, {
-      title: await getConvoTitle(req.user.id, conversationId),
-      final: true,
-      conversation: await getConvo(req.user.id, conversationId),
-      requestMessage: userMessage,
-      responseMessage: responseMessage
-    });
-    res.end();
-
-    if (userParentMessageId == '00000000-0000-0000-0000-000000000000') {
-      const title = await titleConvo({
-        endpoint: endpointOption?.endpoint,
-        text,
-        response: responseMessage,
-        oaiApiKey
-      });
-      await saveConvo(req.user.id, {
-        conversationId: conversationId,
-        title
-      });
-    }
-  } catch (error) {
-    console.error(error);
-    const errorMessage = {
-      messageId: responseMessageId,
-      sender: endpointOption?.chatGptLabel || 'ChatGPT',
-      conversationId,
-      parentMessageId: overrideParentMessageId || userMessageId,
-      unfinished: false,
-      cancelled: false,
-      error: true,
-      text: error.message
-    };
-    await saveMessage(errorMessage);
-    handleError(res, errorMessage);
-  }
-};
-
-module.exports = router;

api/server/routes/ask/google.js

@@ -1,8 +1,8 @@
 const express = require('express');
 const router = express.Router();
 const crypto = require('crypto');
-const { titleConvo } = require('../../../app/');
-const GoogleClient = require('../../../app/google/GoogleClient');
+const { titleConvo, GoogleClient } = require('../../../app');
+// const GoogleClient = require('../../../app/google/GoogleClient');
 const { saveMessage, getConvoTitle, saveConvo, getConvo } = require('../../../models');
 const { handleError, sendMessage, createOnProgress } = require('./handlers');
 const requireJwtAuth = require('../../../middleware/requireJwtAuth');
@@ -27,7 +27,7 @@ router.post('/', requireJwtAuth, async (req, res) => {
     }
   };
 
-  const availableModels = ['chat-bison', 'text-bison'];
+  const availableModels = ['chat-bison', 'text-bison', 'codechat-bison'];
   if (availableModels.find((model) => model === endpointOption.modelOptions.model) === undefined) {
     return handleError(res, { text: `Illegal request: model` });
   }

api/server/routes/ask/gptPlugins.js

@@ -1,9 +1,7 @@
 const express = require('express');
 const router = express.Router();
-const { titleConvo } = require('../../../app/');
-const { getOpenAIModels } = require('../endpoints');
-const ChatAgent = require('../../../app/langchain/ChatAgent');
-const { validateTools } = require('../../../app/langchain/tools');
+const { titleConvo, validateTools, PluginsClient } = require('../../../app');
+const { abortMessage, getAzureCredentials } = require('../../../utils');
 const { saveMessage, getConvoTitle, saveConvo, getConvo } = require('../../../models');
 const {
   handleError,
@@ -17,20 +15,7 @@ const requireJwtAuth = require('../../../middleware/requireJwtAuth');
 const abortControllers = new Map();
 
 router.post('/abort', requireJwtAuth, async (req, res) => {
-  const { abortKey } = req.body;
-  console.log(`req.body`, req.body);
-  if (!abortControllers.has(abortKey)) {
-    return res.status(404).send('Request not found');
-  }
-
-  const { abortController } = abortControllers.get(abortKey);
-
-  abortControllers.delete(abortKey);
-  const ret = await abortController.abortAsk();
-  console.log('Aborted request', abortKey);
-  console.log('Aborted message:', ret);
-
-  res.send(JSON.stringify(ret));
+  return await abortMessage(req, res, abortControllers);
 });
 
 router.post('/', requireJwtAuth, async (req, res) => {
@@ -39,14 +24,15 @@ router.post('/', requireJwtAuth, async (req, res) => {
   if (endpoint !== 'gptPlugins') return handleError(res, { text: 'Illegal request' });
 
   const agentOptions = req.body?.agentOptions ?? {
+    agent: 'functions',
+    skipCompletion: true,
     model: 'gpt-3.5-turbo',
-    // model: 'gpt-4', // for agent model
     temperature: 0,
     // top_p: 1,
     // presence_penalty: 0,
     // frequency_penalty: 0
   };
-  
+
   const tools = req.body?.tools.map((tool) => tool.pluginKey) ?? [];
   // build endpoint option
   const endpointOption = {
@@ -60,26 +46,19 @@ router.post('/', requireJwtAuth, async (req, res) => {
       presence_penalty: req.body?.presence_penalty ?? 0,
       frequency_penalty: req.body?.frequency_penalty ?? 0
     },
-    agentOptions
+    agentOptions: {
+      ...agentOptions,
+      // agent: 'functions'
+    }
   };
 
-  const availableModels = getOpenAIModels();
-  if (availableModels.find((model) => model === endpointOption.modelOptions.model) === undefined) {
-    return handleError(res, { text: `Illegal request: model` });
-  }
-
-  // console.log('ask log', {
-  //   text,
-  //   conversationId,
-  //   endpointOption
-  // });
-
   console.log('ask log');
   console.dir({ text, conversationId, endpointOption }, { depth: null });
 
   // eslint-disable-next-line no-use-before-define
   return await ask({
     text,
+    endpoint,
     endpointOption,
     conversationId,
     parentMessageId,
@@ -88,7 +67,7 @@ router.post('/', requireJwtAuth, async (req, res) => {
   });
 });
 
-const ask = async ({ text, endpointOption, parentMessageId = null, conversationId, req, res }) => {
+const ask = async ({ text, endpoint, endpointOption, parentMessageId = null, conversationId, req, res }) => {
   res.writeHead(200, {
     Connection: 'keep-alive',
     'Content-Type': 'text/event-stream',
@@ -182,21 +161,23 @@ const ask = async ({ text, endpointOption, parentMessageId = null, conversationI
     endpointOption.tools = await validateTools(user, endpointOption.tools);
     const clientOptions = {
       debug: true,
+      endpoint,
       reverseProxyUrl: process.env.OPENAI_REVERSE_PROXY || null,
       proxy: process.env.PROXY || null,
       ...endpointOption
     };
 
-    if (process.env.AZURE_OPENAI_API_KEY) {
-      clientOptions.azure = {
-        azureOpenAIApiKey: process.env.AZURE_OPENAI_API_KEY,
-        azureOpenAIApiInstanceName: process.env.AZURE_OPENAI_API_INSTANCE_NAME,
-        azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME,
-        azureOpenAIApiVersion: process.env.AZURE_OPENAI_API_VERSION
-      };
+    let oaiApiKey = req.body?.token ?? process.env.OPENAI_API_KEY;
+    if (process.env.PLUGINS_USE_AZURE) {
+      clientOptions.azure = getAzureCredentials();
+      oaiApiKey = clientOptions.azure.azureOpenAIApiKey;
     }
 
-    const chatAgent = new ChatAgent(process.env.OPENAI_API_KEY, clientOptions);
+    if (oaiApiKey && oaiApiKey.includes('azure') && !clientOptions.azure) {
+      clientOptions.azure = JSON.parse(req.body?.token) ?? getAzureCredentials();
+      oaiApiKey = clientOptions.azure.azureOpenAIApiKey;
+    }
+    const chatAgent = new PluginsClient(oaiApiKey, clientOptions);
 
     const onAgentAction = (action) => {
       const formattedAction = formatAction(action);
@@ -225,6 +206,7 @@ const ask = async ({ text, endpointOption, parentMessageId = null, conversationI
       onAgentAction,
       onChainEnd,
       onStart,
+      ...endpointOption,
       onProgress: progressCallback.call(null, {
         res,
         text,
@@ -238,8 +220,8 @@ const ask = async ({ text, endpointOption, parentMessageId = null, conversationI
       response.parentMessageId = overrideParentMessageId;
     }
 
-    // console.log('CLIENT RESPONSE');
-    // console.dir(response, { depth: null });
+    console.log('CLIENT RESPONSE');
+    console.dir(response, { depth: null });
     response.plugin = { ...plugin, loading: false };
     await saveMessage(response);
 

api/server/routes/ask/handlers.js

@@ -91,19 +91,22 @@ const handleText = async (response, bing = false) => {
   return text;
 };
 
+const isObject = (item) => item && typeof item === 'object' && !Array.isArray(item);
+const getString = (input) => isObject(input) ? JSON.stringify(input) : input ;
+
 function formatSteps(steps) {
   let output = '';
 
   for (let i = 0; i < steps.length; i++) {
     const step = steps[i];
-    const actionInput = step.action.toolInput;
+    const actionInput = getString(step.action.toolInput);
     const observation = step.observation;
 
     if (actionInput === 'N/A' || observation?.trim()?.length === 0) {
       continue;
     }
 
-    output += `Input: ${actionInput}\nOutput: ${observation}`;
+    output += `Input: ${actionInput}\nOutput: ${getString(observation)}`;
 
     if (steps.length > 1 && i !== steps.length - 1) {
       output += '\n---\n';
@@ -128,12 +131,14 @@ function formatAction(action) {
 
   const formattedAction = {
     plugin: capitalizeWords(action.tool) || action.tool,
-    input: action.toolInput,
+    input: getString(action.toolInput),
     thought: action.log.includes('Thought: ')
       ? action.log.split('\n')[0].replace('Thought: ', '')
       : action.log.split('\n')[0]
   };
 
+  formattedAction.thought = getString(formattedAction.thought);
+
   if (action.tool.toLowerCase() === 'self-reflection' || formattedAction.plugin === 'N/A') {
     formattedAction.inputStr = `{\n\tthought: ${formattedAction.input}${
       !formattedAction.thought.includes(formattedAction.input)
@@ -142,7 +147,9 @@ function formatAction(action) {
     }\n}`;
     formattedAction.inputStr = formattedAction.inputStr.replace('N/A - ', '');
   } else {
-    formattedAction.inputStr = `{\n\tplugin: ${formattedAction.plugin}\n\tinput: ${formattedAction.input}\n\tthought: ${formattedAction.thought}\n}`;
+    const hasThought = formattedAction.thought.length > 0;
+    const thought = hasThought ? `\n\tthought: ${formattedAction.thought}` : '';
+    formattedAction.inputStr = `{\n\tplugin: ${formattedAction.plugin}\n\tinput: ${formattedAction.input}\n${thought}}`;
   }
 
   return formattedAction;

api/server/routes/ask/index.js

@@ -1,17 +1,18 @@
 const express = require('express');
 const router = express.Router();
 // const askAzureOpenAI = require('./askAzureOpenAI';)
-const askOpenAI = require('./askOpenAI');
-const askGoogle = require('./askGoogle');
+// const askOpenAI = require('./askOpenAI');
+const openAI = require('./openAI');
+const google = require('./google');
 const askBingAI = require('./askBingAI');
+const gptPlugins = require('./gptPlugins');
 const askChatGPTBrowser = require('./askChatGPTBrowser');
-const askGPTPlugins = require('./askGPTPlugins');
 
 // router.use('/azureOpenAI', askAzureOpenAI);
-router.use('/openAI', askOpenAI);
-router.use('/google', askGoogle);
+router.use(['/azureOpenAI', '/openAI'], openAI);
+router.use('/google', google);
 router.use('/bingAI', askBingAI);
 router.use('/chatGPTBrowser', askChatGPTBrowser);
-router.use('/gptPlugins', askGPTPlugins);
+router.use('/gptPlugins', gptPlugins);
 
 module.exports = router;

api/server/routes/ask/openAI.js

@@ -0,0 +1,211 @@
+const express = require('express');
+const router = express.Router();
+const { titleConvo, OpenAIClient } = require('../../../app');
+const { getAzureCredentials, abortMessage } = require('../../../utils');
+const { saveMessage, getConvoTitle, saveConvo, getConvo } = require('../../../models');
+const {
+  handleError,
+  sendMessage,
+  createOnProgress,
+} = require('./handlers');
+const requireJwtAuth = require('../../../middleware/requireJwtAuth');
+
+const abortControllers = new Map();
+
+router.post('/abort', requireJwtAuth, async (req, res) => {
+  return await abortMessage(req, res, abortControllers);
+});
+
+router.post('/', requireJwtAuth, async (req, res) => {
+  const { endpoint, text, parentMessageId, conversationId } = req.body;
+  if (text.length === 0) return handleError(res, { text: 'Prompt empty or too short' });
+  const isOpenAI = endpoint === 'openAI' || endpoint === 'azureOpenAI';
+  if (!isOpenAI) return handleError(res, { text: 'Illegal request' });
+
+  // build endpoint option
+  const endpointOption = {
+    chatGptLabel: req.body?.chatGptLabel ?? null,
+    promptPrefix: req.body?.promptPrefix ?? null,
+    modelOptions: {
+      model: req.body?.model ?? 'gpt-3.5-turbo',
+      temperature: req.body?.temperature ?? 1,
+      top_p: req.body?.top_p ?? 1,
+      presence_penalty: req.body?.presence_penalty ?? 0,
+      frequency_penalty: req.body?.frequency_penalty ?? 0
+    }
+  };
+
+  console.log('ask log');
+  console.dir({ text, conversationId, endpointOption }, { depth: null });
+
+  // eslint-disable-next-line no-use-before-define
+  return await ask({
+    text,
+    endpointOption,
+    conversationId,
+    parentMessageId,
+    endpoint,
+    req,
+    res
+  });
+});
+
+const ask = async ({ text, endpointOption, parentMessageId = null, endpoint, conversationId, req, res }) => {
+  res.writeHead(200, {
+    Connection: 'keep-alive',
+    'Content-Type': 'text/event-stream',
+    'Cache-Control': 'no-cache, no-transform',
+    'Access-Control-Allow-Origin': '*',
+    'X-Accel-Buffering': 'no'
+  });
+  let userMessage;
+  let userMessageId;
+  let responseMessageId;
+  let lastSavedTimestamp = 0;
+  const newConvo = !conversationId;
+  const { overrideParentMessageId = null } = req.body;
+  const user = req.user.id;
+
+  const getIds = (data) => {
+    userMessage = data.userMessage;
+    userMessageId = userMessage.messageId;
+    responseMessageId = data.responseMessageId;
+    if (!conversationId) {
+      conversationId = data.conversationId;
+    }
+  };
+
+  const { onProgress: progressCallback, getPartialText } = createOnProgress({
+    onProgress: ({ text: partialText }) => {
+      const currentTimestamp = Date.now();
+
+      if (currentTimestamp - lastSavedTimestamp > 500) {
+        lastSavedTimestamp = currentTimestamp;
+        saveMessage({
+          messageId: responseMessageId,
+          sender: 'ChatGPT',
+          conversationId,
+          parentMessageId: overrideParentMessageId || userMessageId,
+          text: partialText,
+          model: endpointOption.modelOptions.model,
+          unfinished: false,
+          cancelled: true,
+          error: false
+        });
+      }
+    }
+  });
+
+  const abortController = new AbortController();
+  abortController.abortAsk = async function () {
+    this.abort();
+
+    const responseMessage = {
+      messageId: responseMessageId,
+      sender: endpointOption?.chatGptLabel || 'ChatGPT',
+      conversationId,
+      parentMessageId: overrideParentMessageId || userMessageId,
+      text: getPartialText(),
+      model: endpointOption.modelOptions.model,
+      unfinished: false,
+      cancelled: true,
+      error: false,
+    };
+
+    saveMessage(responseMessage);
+
+    return {
+      title: await getConvoTitle(req.user.id, conversationId),
+      final: true,
+      conversation: await getConvo(req.user.id, conversationId),
+      requestMessage: userMessage,
+      responseMessage: responseMessage
+    };
+  };
+
+  const onStart = (userMessage) => {
+    sendMessage(res, { message: userMessage, created: true });
+    abortControllers.set(userMessage.conversationId, { abortController, ...endpointOption });
+  };
+
+  try {
+    const clientOptions = {
+      // debug: true,
+      // contextStrategy: 'refine',
+      reverseProxyUrl: process.env.OPENAI_REVERSE_PROXY || null,
+      proxy: process.env.PROXY || null,
+      endpoint,
+      ...endpointOption
+    };
+
+    let oaiApiKey = req.body?.token ?? process.env.OPENAI_API_KEY;
+
+    if (process.env.AZURE_API_KEY && endpoint === 'azureOpenAI') {
+      clientOptions.azure = JSON.parse(req.body?.token) ?? getAzureCredentials();
+      // clientOptions.reverseProxyUrl = process.env.AZURE_REVERSE_PROXY ?? genAzureChatCompletion({ ...clientOptions.azure });
+      oaiApiKey = clientOptions.azure.azureOpenAIApiKey;
+    }
+
+    const client = new OpenAIClient(oaiApiKey, clientOptions);
+
+    let response = await client.sendMessage(text, {
+      user,
+      parentMessageId,
+      conversationId,
+      overrideParentMessageId,
+      getIds,
+      onStart,
+      onProgress: progressCallback.call(null, {
+        res,
+        text,
+        parentMessageId: overrideParentMessageId || userMessageId
+      }),
+      abortController
+    });
+
+    if (overrideParentMessageId) {
+      response.parentMessageId = overrideParentMessageId;
+    }
+
+    console.log('promptTokens, completionTokens:', response.promptTokens, response.completionTokens);
+    await saveMessage(response);
+
+    sendMessage(res, {
+      title: await getConvoTitle(req.user.id, conversationId),
+      final: true,
+      conversation: await getConvo(req.user.id, conversationId),
+      requestMessage: userMessage,
+      responseMessage: response
+    });
+    res.end();
+
+    if (parentMessageId == '00000000-0000-0000-0000-000000000000' && newConvo) {
+      const title = await titleConvo({ text, response });
+      await saveConvo(req.user.id, {
+        conversationId,
+        title
+      });
+    }
+  } catch (error) {
+    console.error(error);
+    const partialText = getPartialText();
+    if (partialText?.length > 2) {
+      return await abortMessage(req, res, abortControllers);
+    } else {
+      const errorMessage = {
+        messageId: responseMessageId,
+        sender: 'ChatGPT',
+        conversationId,
+        parentMessageId: userMessageId,
+        unfinished: false,
+        cancelled: false,
+        error: true,
+        text: error.message
+      };
+      await saveMessage(errorMessage);
+      handleError(res, errorMessage);
+    }
+  }
+};
+
+module.exports = router;

api/server/routes/auth.js

@@ -4,9 +4,9 @@ const {
   resetPasswordController,
   // refreshController,
   registrationController
-} = require('../controllers/auth.controller');
-const { loginController } = require('../controllers/auth/login.controller');
-const { logoutController } = require('../controllers/auth/logout.controller');
+} = require('../controllers/AuthController');
+const { loginController } = require('../controllers/auth/LoginController');
+const { logoutController } = require('../controllers/auth/LogoutController');
 const requireJwtAuth = require('../../middleware/requireJwtAuth');
 const requireLocalAuth = require('../../middleware/requireLocalAuth');
 

api/server/routes/config.js

@@ -0,0 +1,25 @@
+const express = require('express');
+const router = express.Router();
+
+router.get('/', async function (req, res) {
+  try {
+    const appTitle = process.env.APP_TITLE || 'LibreChat';
+    const googleLoginEnabled = !!process.env.GOOGLE_CLIENT_ID && !!process.env.GOOGLE_CLIENT_SECRET;
+    const openidLoginEnabled = !!process.env.OPENID_CLIENT_ID 
+      && !!process.env.OPENID_CLIENT_SECRET 
+      && !!process.env.OPENID_ISSUER 
+      && !!process.env.OPENID_SESSION_SECRET;
+    const openidLabel = process.env.OPENID_BUTTON_LABEL || 'Login with OpenID';
+    const openidImageUrl = process.env.OPENID_IMAGE_URL;
+    const githubLoginEnabled = !!process.env.GITHUB_CLIENT_ID && !!process.env.GITHUB_CLIENT_SECRET;
+    const serverDomain = process.env.DOMAIN_SERVER || 'http://localhost:3080';
+    const registrationEnabled = process.env.ALLOW_REGISTRATION === 'true';
+    
+    return res.status(200).send({appTitle, googleLoginEnabled, openidLoginEnabled, openidLabel, openidImageUrl, githubLoginEnabled, serverDomain, registrationEnabled});
+  } catch (err) {
+    console.error(err);
+    return res.status(500).send({error: err.message});
+  }
+});
+
+module.exports = router;

api/server/routes/endpoints.js

@@ -1,10 +1,11 @@
 const express = require('express');
 const router = express.Router();
-const { availableTools } = require('../../app/langchain/tools');
+const { availableTools } = require('../../app/clients/tools');
 
-const getOpenAIModels = () => {
-  let models = ['gpt-4', 'text-davinci-003', 'gpt-3.5-turbo', 'gpt-3.5-turbo-0301'];
-  if (process.env.OPENAI_MODELS) models = String(process.env.OPENAI_MODELS).split(',');
+const getOpenAIModels = (opts = { azure: false }) => {
+  let models = ['gpt-4', 'gpt-4-0613', 'gpt-3.5-turbo', 'gpt-3.5-turbo-16k', 'gpt-3.5-turbo-0613', 'gpt-3.5-turbo-0301', 'text-davinci-003' ];
+  const key = opts.azure ? 'AZURE_OPENAI_MODELS' : 'OPENAI_MODELS';
+  if (process.env[key]) models = String(process.env[key]).split(',');
 
   return models;
 };
@@ -16,6 +17,13 @@ const getChatGPTBrowserModels = () => {
   return models;
 };
 
+const getPluginModels = () => {
+  let models = ['gpt-4', 'gpt-4-0613', 'gpt-3.5-turbo', 'gpt-3.5-turbo-16k', 'gpt-3.5-turbo-0613', 'gpt-3.5-turbo-0301'];
+  if (process.env.PLUGIN_MODELS) models = String(process.env.PLUGIN_MODELS).split(',');
+
+  return models;
+};
+
 let i = 0;
 router.get('/', async function (req, res) {
   let key, palmUser;
@@ -23,7 +31,7 @@ router.get('/', async function (req, res) {
     key = require('../../data/auth.json');
   } catch (e) {
     if (i === 0) {
-      console.log("No 'auth.json' file (service account key) found in /api/data/ for PaLM models");
+      console.log('No \'auth.json\' file (service account key) found in /api/data/ for PaLM models');
       i++;
     }
   }
@@ -38,15 +46,19 @@ router.get('/', async function (req, res) {
 
   const google =
     key || palmUser
-      ? { userProvide: palmUser, availableModels: ['chat-bison', 'text-bison'] }
+      ? { userProvide: palmUser, availableModels: ['chat-bison', 'text-bison', 'codechat-bison'] }
       : false;
-  const azureOpenAI = !!process.env.AZURE_OPENAI_API_KEY;
-  const apiKey = process.env.OPENAI_API_KEY || process.env.AZURE_OPENAI_API_KEY;
-  const openAI = apiKey
-    ? { availableModels: getOpenAIModels(), userProvide: apiKey === 'user_provided' }
+  const openAIApiKey = process.env.OPENAI_API_KEY;
+  const azureOpenAIApiKey = process.env.AZURE_API_KEY;
+  const userProvidedOpenAI = openAIApiKey ? openAIApiKey === 'user_provided' : azureOpenAIApiKey === 'user_provided';
+  const openAI = openAIApiKey
+    ? { availableModels: getOpenAIModels(), userProvide: openAIApiKey === 'user_provided' }
     : false;
-  const gptPlugins = apiKey
-    ? { availableModels: ['gpt-4', 'gpt-3.5-turbo', 'gpt-3.5-turbo-0301'], availableTools }
+  const azureOpenAI = azureOpenAIApiKey
+    ? { availableModels: getOpenAIModels({ azure: true}), userProvide: azureOpenAIApiKey === 'user_provided' }
+    : false;
+  const gptPlugins = openAIApiKey || azureOpenAIApiKey
+    ? { availableModels: getPluginModels(), availableTools, availableAgents: ['classic', 'functions'], userProvide: userProvidedOpenAI }
     : false;
   const bingAI = process.env.BINGAI_TOKEN
     ? { userProvide: process.env.BINGAI_TOKEN == 'user_provided' }

api/server/routes/index.js

@@ -10,6 +10,7 @@ const oauth = require('./oauth');
 const { router: endpoints } = require('./endpoints');
 const plugins = require('./plugins');
 const user = require('./user');
+const config = require('./config');
 
 module.exports = {
   search,
@@ -23,5 +24,6 @@ module.exports = {
   user,
   tokenizer,
   endpoints,
-  plugins
+  plugins,
+  config
 };

api/server/routes/oauth.js

@@ -62,4 +62,57 @@ router.get(
   }
 );
 
+router.get(
+  '/openid',
+  passport.authenticate('openid', {
+    session: false
+  })
+);
+
+router.get(
+  '/openid/callback',
+  passport.authenticate('openid', {
+    failureRedirect: `${domains.client}/login`,
+    failureMessage: true,
+    session: false
+  }),
+  (req, res) => {
+    const token = req.user.generateToken();
+    res.cookie('token', token, {
+      expires: new Date(Date.now() + eval(process.env.SESSION_EXPIRY)),
+      httpOnly: false,
+      secure: isProduction
+    });
+    res.redirect(domains.client);
+  }
+);
+
+
+router.get(
+  '/github',
+  passport.authenticate('github', {
+    scope: ['user:email', 'read:user'],
+    session: false
+  })
+);
+
+router.get(
+  '/github/callback',
+  passport.authenticate('github', {
+    failureRedirect: `${domains.client}/login`,
+    failureMessage: true,
+    session: false,
+    scope: ['user:email', 'read:user']
+  }),
+  (req, res) => {
+    const token = req.user.generateToken();
+    res.cookie('token', token, {
+      expires: new Date(Date.now() + eval(process.env.SESSION_EXPIRY)),
+      httpOnly: false,
+      secure: isProduction
+    });
+    res.redirect(domains.client);
+  }
+);
+
 module.exports = router;

api/server/services/PluginService.js

@@ -1,5 +1,5 @@
 const PluginAuth = require('../../models/schema/pluginAuthSchema');
-const { encrypt, decrypt } = require('../../utils/crypto');
+const { encrypt, decrypt } = require('../../utils/');
 
 const getUserPluginAuthValue = async (user, authField) => {
   try {

api/server/services/auth.service.js

@@ -1,19 +1,18 @@
 const User = require('../../models/User');
 const Token = require('../../models/schema/tokenSchema');
-const sendEmail = require('../../utils/sendEmail');
 const crypto = require('crypto');
 const bcrypt = require('bcryptjs');
 const { registerSchema } = require('../../strategies/validators');
-const migrateDataToFirstUser = require('../../utils/migrateDataToFirstUser');
+const { sendEmail } = require('../../utils');
 const config = require('../../../config/loader');
 const domains = config.domains;
 
 /**
  * Logout user
  *
- * @param {Object} user 
- * @param {*} refreshToken 
- * @returns 
+ * @param {Object} user
+ * @param {*} refreshToken
+ * @returns
  */
 const logoutUser = async (user, refreshToken) => {
   try {
@@ -38,7 +37,7 @@ const logoutUser = async (user, refreshToken) => {
  * Register a new user
  *
  * @param {Object} user <email, password, name, username>
- * @returns 
+ * @returns
  */
 const registerUser = async (user) => {
   const { error } = registerSchema.validate(user);
@@ -63,7 +62,7 @@ const registerUser = async (user) => {
         { name: 'Request params:', value: user },
         { name: 'Existing user:', value: existingUser }
       );
-      
+
       // Sleep for 1 second
       await new Promise((resolve) => setTimeout(resolve, 1000));
 
@@ -92,20 +91,17 @@ const registerUser = async (user) => {
     newUser.password = hash;
     newUser.save();
 
-    if (isFirstRegisteredUser) {
-      migrateDataToFirstUser(newUser);
-    }
     return { status: 200, user: newUser };
   } catch (err) {
     return { status: 500, message: err?.message || 'Something went wrong' };
   }
 };
- 
+
 /**
  * Request password reset
  *
- * @param {String} email 
- * @returns 
+ * @param {String} email
+ * @returns
  */
 const requestPasswordReset = async (email) => {
   const user = await User.findOne({ email });
@@ -142,10 +138,10 @@ const requestPasswordReset = async (email) => {
 /**
  * Reset Password
  *
- * @param {*} userId 
- * @param {String} token 
- * @param {String} password 
- * @returns 
+ * @param {*} userId
+ * @param {String} token
+ * @param {String} password
+ * @returns
  */
 const resetPassword = async (userId, token, password) => {
   let passwordResetToken = await Token.findOne({ userId });

api/strategies/githubStrategy.js

@@ -0,0 +1,47 @@
+const passport = require('passport');
+const { Strategy: GitHubStrategy } = require('passport-github2');
+const config = require('../../config/loader');
+const domains = config.domains;
+
+const User = require('../models/User');
+
+// GitHub strategy
+const githubLogin = new GitHubStrategy(
+  {
+    clientID: process.env.GITHUB_CLIENT_ID,
+    clientSecret: process.env.GITHUB_CLIENT_SECRET,
+    callbackURL: `${domains.server}${process.env.GITHUB_CALLBACK_URL}`,
+    proxy: false,
+    scope: ['user:email'] // Request email scope
+  },
+  async (accessToken, refreshToken, profile, cb) => {
+    try {
+      let email;
+      if (profile.emails && profile.emails.length > 0) {
+        email = profile.emails[0].value;
+      }
+
+      const oldUser = await User.findOne({ email });
+      if (oldUser) {
+        return cb(null, oldUser);
+      }
+
+      const newUser = await new User({
+        provider: 'github',
+        githubId: profile.id,
+        username: profile.username,
+        email,
+        emailVerified: profile.emails[0].verified,
+        name: profile.displayName,
+        avatar: profile.photos[0].value        
+      }).save();
+
+      cb(null, newUser);
+    } catch (err) {
+      console.error(err);
+      cb(err);
+    }
+  }
+);
+
+passport.use(githubLogin);

api/strategies/openidStrategy.js

@@ -0,0 +1,123 @@
+const passport = require('passport');
+const jwt = require('jsonwebtoken');
+const { Issuer, Strategy: OpenIDStrategy } = require('openid-client');
+const axios = require('axios');
+const fs = require('fs');
+const path = require('path');
+const config = require('../../config/loader');
+const domains = config.domains;
+
+const User = require('../models/User');
+
+let crypto;
+try {
+  crypto = require('node:crypto');
+} catch (err) {
+  console.error('crypto support is disabled!');
+}
+
+const downloadImage = async (url, imagePath, accessToken) => {
+  try {
+    const response = await axios.get(url, {
+      headers: {
+        'Authorization': `Bearer ${accessToken}`
+      },
+      responseType: 'arraybuffer'
+    });
+    
+    fs.mkdirSync(path.dirname(imagePath), { recursive: true });
+    fs.writeFileSync(imagePath, response.data);
+
+    const fileName = path.basename(imagePath);
+
+    return `/images/openid/${fileName}`;
+  } catch (error) {
+    console.error(`Error downloading image at URL "${url}": ${error}`);
+    return '';
+  }
+};
+
+Issuer.discover(process.env.OPENID_ISSUER)
+  .then(issuer => {
+    const client = new issuer.Client({
+      client_id: process.env.OPENID_CLIENT_ID,
+      client_secret: process.env.OPENID_CLIENT_SECRET,
+      redirect_uris: [domains.server + process.env.OPENID_CALLBACK_URL]
+    });
+
+    const openidLogin = new OpenIDStrategy(
+      {
+        client,
+        params: {
+          scope: process.env.OPENID_SCOPE
+        }
+      },
+      async (tokenset, userinfo, done) => {
+        try {
+          let user = await User.findOne({ openidId: userinfo.sub });
+
+          if (!user) {
+            user = await User.findOne({ email: userinfo.email });
+          }
+
+          let fullName = '';
+          if (userinfo.given_name && userinfo.family_name) {
+            fullName = userinfo.given_name + ' ' + userinfo.family_name;
+          } else if (userinfo.given_name) {
+            fullName = userinfo.given_name;
+          } else if (userinfo.family_name) {
+            fullName = userinfo.family_name;
+          }
+          
+          if (!user) {
+            user = new User({
+              provider: 'openid',
+              openidId: userinfo.sub,
+              username: userinfo.given_name || '',
+              email: userinfo.email || '',
+              emailVerified: userinfo.email_verified || false,
+              name: fullName
+            });
+          } else {
+            user.provider = 'openid';
+            user.openidId = userinfo.sub;
+            user.username = userinfo.given_name || '';
+            user.name = fullName;
+          }
+
+          if (userinfo.picture) {
+            const imageUrl = userinfo.picture;
+
+            let fileName;
+            if (crypto) {
+              const hash = crypto.createHash('sha256');
+              hash.update(userinfo.sub);
+              fileName = hash.digest('hex') + '.png';
+            } else {
+              fileName = userinfo.sub + '.png';
+            }
+
+            const imagePath = path.join(__dirname, '..', '..', 'client', 'public', 'images', 'openid', fileName);
+
+            const imagePathOrEmpty = await downloadImage(imageUrl, imagePath, tokenset.access_token);
+
+            user.avatar = imagePathOrEmpty;
+          } else {
+            user.avatar = '';
+          }
+          
+          await user.save();
+          
+          done(null, user);
+        } catch (err) {
+          done(err);
+        }
+      }
+    );
+
+    passport.use('openid', openidLogin);
+
+  })
+  .catch(err => {
+    console.error(err);
+  });

api/strategies/validators.js

@@ -2,7 +2,7 @@ const Joi = require('joi');
 
 const loginSchema = Joi.object().keys({
   email: Joi.string().trim().email().required(),
-  password: Joi.string().trim().min(6).max(20).required()
+  password: Joi.string().trim().min(8).max(128).required()
 });
 
 const registerSchema = Joi.object().keys({
@@ -11,11 +11,11 @@ const registerSchema = Joi.object().keys({
     .trim()
     .min(2)
     .max(20)
-    .regex(/^[a-zA-Z0-9_]+$/)
+    .regex(/^[a-zA-Z0-9_-]+$/)
     .required(),
   email: Joi.string().trim().email().required(),
-  password: Joi.string().trim().min(6).max(20).required(),
-  confirm_password: Joi.string().trim().min(6).max(20).required()
+  password: Joi.string().trim().min(8).max(128).required(),
+  confirm_password: Joi.string().trim().min(8).max(128).required()
 });
 
 module.exports = {

api/utils/abortMessage.js

@@ -0,0 +1,18 @@
+async function abortMessage(req, res, abortControllers) {
+  const { abortKey } = req.body;
+  console.log(`req.body`, req.body);
+  if (!abortControllers.has(abortKey)) {
+    return res.status(404).send('Request not found');
+  }
+
+  const { abortController } = abortControllers.get(abortKey);
+
+  abortControllers.delete(abortKey);
+  const ret = await abortController.abortAsk();
+  console.log('Aborted request', abortKey);
+  console.log('Aborted message:', ret);
+
+  res.send(JSON.stringify(ret));
+}
+
+module.exports = abortMessage;

api/utils/azureUtils.js

@@ -0,0 +1,22 @@
+const genAzureEndpoint = ({ azureOpenAIApiInstanceName, azureOpenAIApiDeploymentName }) => {
+  return `https://${azureOpenAIApiInstanceName}.openai.azure.com/openai/deployments/${azureOpenAIApiDeploymentName}`;
+}
+
+const genAzureChatCompletion = ({
+  azureOpenAIApiInstanceName,
+  azureOpenAIApiDeploymentName,
+  azureOpenAIApiVersion
+}) => {
+  return `https://${azureOpenAIApiInstanceName}.openai.azure.com/openai/deployments/${azureOpenAIApiDeploymentName}/chat/completions?api-version=${azureOpenAIApiVersion}`;
+}
+
+const getAzureCredentials = () => {
+  return {
+    azureOpenAIApiKey: process.env.AZURE_API_KEY ?? process.env.AZURE_OPENAI_API_KEY,
+    azureOpenAIApiInstanceName: process.env.AZURE_OPENAI_API_INSTANCE_NAME,
+    azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME,
+    azureOpenAIApiVersion: process.env.AZURE_OPENAI_API_VERSION
+  }
+}
+
+module.exports = { genAzureEndpoint, genAzureChatCompletion, getAzureCredentials };