From 8dd30690050c3678d41fd1a26ffb6cd18eb8cefd Mon Sep 17 00:00:00 2001
From: yangdx <gzdaniel@me.com>
Date: Tue, 5 Aug 2025 14:22:19 +0800
Subject: [PATCH] feat: add tiktoken cache directory support for offline
 deployment

- Mount tiktoken cache volume in docker-compose
- Add TIKTOKEN_CACHE_DIR environment variable
- Update env.example with tiktoken cache configuration
- Added /data to gitignore
- Added tiktoken env example
---
 .gitignore         | 1 +
 docker-compose.yml | 3 +++
 env.example        | 3 +++
 3 files changed, 7 insertions(+)

diff --git a/.gitignore b/.gitignore
index a1b10a90..dc48605d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -50,6 +50,7 @@ rag_storage/
 examples/input/
 examples/output/
 output*/
+data/
 
 # Miscellaneous
 .DS_Store
diff --git a/docker-compose.yml b/docker-compose.yml
index da71faf8..2881b5c4 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -12,10 +12,13 @@ services:
     volumes:
       - ./data/rag_storage:/app/data/rag_storage
       - ./data/inputs:/app/data/inputs
+      - ./data/tiktoken:/app/data/tiktoken
       - ./config.ini:/app/config.ini
       - ./.env:/app/.env
     env_file:
       - .env
+    environment:
+      - TIKTOKEN_CACHE_DIR=/app/data/tiktoken
     restart: unless-stopped
     extra_hosts:
       - "host.docker.internal:host-gateway"
diff --git a/env.example b/env.example
index fae8122a..9de38d30 100644
--- a/env.example
+++ b/env.example
@@ -20,6 +20,9 @@ WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
 # INPUT_DIR=<absolute_path_for_doc_input_dir>
 # WORKING_DIR=<absolute_path_for_working_dir>
 
+### Tiktoken cache directory (Store cached files in this folder for offline deployment)
+# TIKTOKEN_CACHE_DIR=./temp/tiktoken
+
 ### Ollama Emulating Model and Tag
 # OLLAMA_EMULATING_MODEL_NAME=lightrag
 OLLAMA_EMULATING_MODEL_TAG=latest