Add offline Docker build support with embedded models and cache

- Add offline Dockerfile with tiktoken cache
- Create GitHub workflow for offline builds
- Update dockerignore for cleaner builds
- Exclude dev dirs from package setup
- Remove tiktoken volume from compose

.dockerignore

@@ -28,6 +28,12 @@ Makefile
 # Exclude other projects
 /tests
 /scripts
+/data
+/dickens
+/reproduce
+/output_complete
+/rag_storage
+/inputs
 
 # Python version manager file
 .python-version

.github/workflows/docker-build-offline.yml

@@ -0,0 +1,77 @@
+name: Build Offline Docker Image
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  packages: write
+
+jobs:
+  build-and-push-offline:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Get latest tag
+        id: get_tag
+        run: |
+          LATEST_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
+          if [ -z "$LATEST_TAG" ]; then
+            LATEST_TAG="sha-$(git rev-parse --short HEAD)"
+            echo "No tags found, using commit SHA: $LATEST_TAG"
+          else
+            echo "Latest tag found: $LATEST_TAG"
+          fi
+          echo "tag=$LATEST_TAG" >> $GITHUB_OUTPUT
+
+      - name: Prepare offline tag
+        id: offline_tag
+        run: |
+          OFFLINE_TAG="${{ steps.get_tag.outputs.tag }}-offline"
+          echo "Offline image tag: $OFFLINE_TAG"
+          echo "offline_tag=$OFFLINE_TAG" >> $GITHUB_OUTPUT
+
+      - name: Update version in __init__.py
+        run: |
+          sed -i "s/__version__ = \".*\"/__version__ = \"${{ steps.get_tag.outputs.tag }}\"/" lightrag/__init__.py
+          cat lightrag/__init__.py | grep __version__
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/${{ github.repository }}
+          tags: |
+            type=raw,value=${{ steps.offline_tag.outputs.offline_tag }}
+
+      - name: Build and push offline Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./Dockerfile.offline
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Output image details
+        run: |
+          echo "Offline Docker image built and pushed successfully!"
+          echo "Image tag: ghcr.io/${{ github.repository }}:${{ steps.offline_tag.outputs.offline_tag }}"
+          echo "Base Git tag used: ${{ steps.get_tag.outputs.tag }}"

Dockerfile.offline

@@ -0,0 +1,87 @@
+# Frontend build stage
+FROM oven/bun:1 AS frontend-builder
+
+WORKDIR /app
+
+# Copy frontend source code
+COPY lightrag_webui/ ./lightrag_webui/
+
+# Build frontend assets for inclusion in the API package
+RUN cd lightrag_webui \
+    && bun install --frozen-lockfile \
+    && bun run build
+
+# Python build stage
+FROM python:3.12-slim AS builder
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+WORKDIR /app
+
+# Upgrade packaging tools and install system deps (Rust is required by some wheels)
+RUN pip install --upgrade pip setuptools wheel \
+    && apt-get update \
+    && apt-get install -y --no-install-recommends \
+        curl \
+        build-essential \
+        pkg-config \
+    && rm -rf /var/lib/apt/lists/* \
+    && curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
+
+ENV PATH="/root/.cargo/bin:/root/.local/bin:${PATH}"
+
+# Copy project metadata and sources
+COPY pyproject.toml .
+COPY setup.py .
+COPY requirements-offline*.txt ./
+COPY lightrag/ ./lightrag/
+
+# Include pre-built frontend assets from the previous stage
+COPY --from=frontend-builder /app/lightrag/api/webui ./lightrag/api/webui
+
+# Install LightRAG with API extras and all offline dependencies
+RUN pip install --user --no-cache-dir --use-pep517 .[api]
+RUN pip install --user --no-cache-dir -r requirements-offline.txt
+
+# Prepare offline cache directory and pre-populate tiktoken data
+RUN mkdir -p /app/data/tiktoken \
+    && lightrag-download-cache --cache-dir /app/data/tiktoken || status=$?; \
+    if [ -n "${status:-}" ] && [ "$status" -ne 0 ] && [ "$status" -ne 2 ]; then exit "$status"; fi
+
+# Final stage
+FROM python:3.12-slim
+
+WORKDIR /app
+
+RUN pip install --upgrade pip setuptools wheel
+
+# Copy installed packages and application code
+COPY --from=builder /root/.local /root/.local
+COPY --from=builder /app/lightrag ./lightrag
+COPY pyproject.toml .
+COPY setup.py .
+COPY requirements-offline*.txt ./
+
+# Ensure the installed scripts are on PATH
+ENV PATH=/root/.local/bin:$PATH
+
+# Install editable package for runtime (re-using cached wheels) and verify extras
+# IMPORTANT: Must be done BEFORE creating data/ directory to avoid setuptools error
+RUN pip install --no-cache-dir --use-pep517 ".[api]"
+RUN pip install --no-cache-dir -r requirements-offline.txt
+
+# Create persistent data directories AFTER package installation
+RUN mkdir -p /app/data/rag_storage /app/data/inputs /app/data/tiktoken
+
+# Copy offline cache into the newly created directory
+COPY --from=builder /app/data/tiktoken /app/data/tiktoken
+
+# Point to the prepared cache
+ENV TIKTOKEN_CACHE_DIR=/app/data/tiktoken
+ENV WORKING_DIR=/app/data/rag_storage
+ENV INPUT_DIR=/app/data/inputs
+
+# Expose API port
+EXPOSE 9621
+
+ENTRYPOINT ["python", "-m", "lightrag.api.lightrag_server"]

docker-compose.yml

@@ -12,9 +12,9 @@ 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
+      # - ./data/tiktoken:/app/data/tiktoken
     env_file:
       - .env
     environment:

pyproject.toml

@@ -130,6 +130,7 @@ Repository = "https://github.com/HKUDS/LightRAG"
 
 [tool.setuptools.packages.find]
 include = ["lightrag*"]
+exclude = ["data*", "tests*", "scripts*", "examples*", "dickens*", "reproduce*", "output_complete*", "rag_storage*", "inputs*"]
 
 [tool.setuptools]
 include-package-data = true