Merge branch 'main' into remove-dotenv

2025-10-17 15:06:34 +08:00 · 2025-10-17 15:06:34 +08:00 · 06ed2d06a9
commit 06ed2d06a9
parent 532400412e c18762e34a
22 changed files with 4706 additions and 444 deletions
--- a/.github/workflows/docker-build-offline.yml
+++ b/.github/workflows/docker-build-offline.yml
@ -1,14 +1,20 @@
-name: Build Offline Docker Image
+name: Build Lite Docker Image

 on:
  workflow_dispatch:
+    inputs:
+      _notes_:
+        description: '⚠️ Create lite Docker images only after non-trivial version releases.'
+        required: false
+        type: boolean
+        default: false

 permissions:
  contents: read
  packages: write

 jobs:
-  build-and-push-offline:
+  build-and-push-lite:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
@ -28,12 +34,12 @@ jobs:
          fi
          echo "tag=$LATEST_TAG" >> $GITHUB_OUTPUT

-      - name: Prepare offline tag
-        id: offline_tag
+      - name: Prepare lite tag
+        id: lite_tag
        run: |
-          OFFLINE_TAG="${{ steps.get_tag.outputs.tag }}-offline"
-          echo "Offline image tag: $OFFLINE_TAG"
-          echo "offline_tag=$OFFLINE_TAG" >> $GITHUB_OUTPUT
+          LITE_TAG="${{ steps.get_tag.outputs.tag }}-lite"
+          echo "Lite image tag: $LITE_TAG"
+          echo "lite_tag=$LITE_TAG" >> $GITHUB_OUTPUT

      - name: Update version in __init__.py
        run: |
@ -56,23 +62,23 @@ jobs:
        with:
          images: ghcr.io/${{ github.repository }}
          tags: |
-            type=raw,value=${{ steps.offline_tag.outputs.offline_tag }}
-            type=raw,value=offline
+            type=raw,value=${{ steps.lite_tag.outputs.lite_tag }}
+            type=raw,value=lite

-      - name: Build and push offline Docker image
+      - name: Build and push lite Docker image
        uses: docker/build-push-action@v5
        with:
          context: .
-          file: ./Dockerfile.offline
+          file: ./Dockerfile.lite
          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
+          cache-to: type=gha,mode=min

      - 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 "Lite Docker image built and pushed successfully!"
+          echo "Image tag: ghcr.io/${{ github.repository }}:${{ steps.lite_tag.outputs.lite_tag }}"
          echo "Base Git tag used: ${{ steps.get_tag.outputs.tag }}"
--- a/.github/workflows/docker-build-manual.yml
+++ b/.github/workflows/docker-build-manual.yml
@ -2,6 +2,12 @@ name: Build Test Docker Image manually

 on:
  workflow_dispatch:
+    inputs:
+      _notes_:
+        description: '⚠️ Please create a new git tag before building the docker image.'
+        required: false
+        type: boolean
+        default: false

 permissions:
  contents: read
@ -58,6 +64,7 @@ jobs:
        uses: docker/build-push-action@v5
        with:
          context: .
+          file: ./Dockerfile
          platforms: linux/amd64,linux/arm64
          push: true
          tags: ${{ steps.meta.outputs.tags }}
--- a/.github/workflows/docker-publish.yml
+++ b/.github/workflows/docker-publish.yml
@ -66,6 +66,7 @@ jobs:
        uses: docker/build-push-action@v5
        with:
          context: .
+          file: ./Dockerfile
          platforms: linux/amd64,linux/arm64
          push: true
          tags: ${{ steps.meta.outputs.tags }}
--- a/100
+++ b/100
@ -6,74 +6,96 @@ WORKDIR /app
 # Copy frontend source code
 COPY lightrag_webui/ ./lightrag_webui/

-# Build frontend
-RUN cd lightrag_webui && \
-    bun install --frozen-lockfile && \
-    bun run build
+# 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
+# Python build stage - using uv for faster package installation
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS builder
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV UV_SYSTEM_PYTHON=1
+ENV UV_COMPILE_BYTECODE=1

 WORKDIR /app

-# Upgrade pip、setuptools and wheel to the latest version
-RUN pip install --upgrade pip setuptools wheel
-
-# Install Rust and required build dependencies
-RUN apt-get update && apt-get install -y \
-    curl \
-    build-essential \
-    pkg-config \
+# Install system deps (Rust is required by some wheels)
+RUN 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 \
-    && . $HOME/.cargo/env
+    && curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y

-# Copy pyproject.toml and source code for dependency installation
+ENV PATH="/root/.cargo/bin:/root/.local/bin:${PATH}"
+
+# Ensure shared data directory exists for uv caches
+RUN mkdir -p /root/.local/share/uv
+
+# Copy project metadata and sources
 COPY pyproject.toml .
 COPY setup.py .
+COPY uv.lock .
+
+# Install base, API, and offline extras without the project to improve caching
+RUN uv sync --frozen --no-dev --extra api --extra offline --no-install-project --no-editable
+
+# Copy project sources after dependency layer
 COPY lightrag/ ./lightrag/

-# Copy frontend build output from frontend-builder stage
+# Include pre-built frontend assets from the previous stage
 COPY --from=frontend-builder /app/lightrag/api/webui ./lightrag/api/webui

-# Install dependencies
-ENV PATH="/root/.cargo/bin:${PATH}"
-RUN pip install --user --no-cache-dir --use-pep517 .
-RUN pip install --user --no-cache-dir --use-pep517 .[api]
+# Sync project in non-editable mode and ensure pip is available for runtime installs
+RUN uv sync --frozen --no-dev --extra api --extra offline --no-editable \
+    && /app/.venv/bin/python -m ensurepip --upgrade

-# Install depndencies for default storage
-RUN pip install --user --no-cache-dir nano-vectordb networkx
-# Install depndencies for default LLM
-RUN pip install --user --no-cache-dir openai ollama tiktoken
-# Install depndencies for default document loader
-RUN pip install --user --no-cache-dir pypdf2 python-docx python-pptx openpyxl
+# Prepare offline cache directory and pre-populate tiktoken data
+# Use uv run to execute commands from the virtual environment
+RUN mkdir -p /app/data/tiktoken \
+    && uv run 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

-# Upgrade pip and setuptools
-RUN pip install --upgrade pip setuptools wheel
+# Install uv for package management
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv

-# Copy only necessary files from builder
+ENV UV_SYSTEM_PYTHON=1
+
+# Copy installed packages and application code
 COPY --from=builder /root/.local /root/.local
+COPY --from=builder /app/.venv /app/.venv
 COPY --from=builder /app/lightrag ./lightrag
+COPY pyproject.toml .
 COPY setup.py .
+COPY uv.lock .

-RUN pip install --use-pep517 ".[api]"
-# Make sure scripts in .local are usable
-ENV PATH=/root/.local/bin:$PATH
+# Ensure the installed scripts are on PATH
+ENV PATH=/app/.venv/bin:/root/.local/bin:$PATH

-# Create necessary directories
-RUN mkdir -p /app/data/rag_storage /app/data/inputs
+# Install dependencies with uv sync (uses locked versions from uv.lock)
+# And ensure pip is available for runtime installs
+RUN uv sync --frozen --no-dev --extra api --extra offline --no-editable \
+    && /app/.venv/bin/python -m ensurepip --upgrade

-# Docker data directories
+# 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 the default port
+# Expose API port
 EXPOSE 9621

-# Set entrypoint
 ENTRYPOINT ["python", "-m", "lightrag.api.lightrag_server"]
--- a/Dockerfile.offline
+++ b/Dockerfile.offline
@ -11,16 +11,17 @@ RUN cd lightrag_webui \
    && bun install --frozen-lockfile \
    && bun run build

-# Python build stage
-FROM python:3.12-slim AS builder
+# Python build stage - using uv for package installation
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS builder

 ENV DEBIAN_FRONTEND=noninteractive
+ENV UV_SYSTEM_PYTHON=1
+ENV UV_COMPILE_BYTECODE=1

 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 \
+# Install system dependencies required by some wheels
+RUN apt-get update \
    && apt-get install -y --no-install-recommends \
        curl \
        build-essential \
@ -30,27 +31,31 @@ RUN pip install --upgrade pip setuptools wheel \

 ENV PATH="/root/.cargo/bin:/root/.local/bin:${PATH}"

+# Ensure shared data directory exists for uv caches
+RUN mkdir -p /root/.local/share/uv
+
 # Copy project metadata and sources
 COPY pyproject.toml .
 COPY setup.py .
-COPY requirements-offline*.txt ./
-COPY constraints-offline.txt .
+COPY uv.lock .
+
+# Install project dependencies (base + API extras) without the project to improve caching
+RUN uv sync --frozen --no-dev --extra api --no-install-project --no-editable
+
+# Copy project sources after dependency layer
 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 in a single step
-# This prevents version conflicts from multiple installation passes
-# Use constraints file for reproducible builds with exact versions
-RUN pip install --user --no-cache-dir --use-pep517 \
-    --upgrade-strategy=only-if-needed \
-    --constraint constraints-offline.txt \
-    .[api] -r requirements-offline.txt
+# Sync project in non-editable mode and ensure pip is available for runtime installs
+RUN uv sync --frozen --no-dev --extra api --no-editable \
+    && /app/.venv/bin/python -m ensurepip --upgrade

-# Prepare offline cache directory and pre-populate tiktoken data
+# Prepare tiktoken cache directory and pre-populate tokenizer data
+# Ignore exit code 2 which indicates assets already cached
 RUN mkdir -p /app/data/tiktoken \
-    && lightrag-download-cache --cache-dir /app/data/tiktoken || status=$?; \
+    && uv run lightrag-download-cache --cache-dir /app/data/tiktoken || status=$?; \
    if [ -n "${status:-}" ] && [ "$status" -ne 0 ] && [ "$status" -ne 2 ]; then exit "$status"; fi

 # Final stage
@ -58,34 +63,34 @@ FROM python:3.12-slim

 WORKDIR /app

-RUN pip install --upgrade pip setuptools wheel
+# Install uv for package management
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
+
+ENV UV_SYSTEM_PYTHON=1

 # Copy installed packages and application code
 COPY --from=builder /root/.local /root/.local
+COPY --from=builder /app/.venv /app/.venv
 COPY --from=builder /app/lightrag ./lightrag
 COPY pyproject.toml .
 COPY setup.py .
-COPY requirements-offline*.txt ./
-COPY constraints-offline.txt .
+COPY uv.lock .

 # Ensure the installed scripts are on PATH
-ENV PATH=/root/.local/bin:$PATH
+ENV PATH=/app/.venv/bin:/root/.local/bin:$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
-# Use single installation to prevent version conflicts with exact version constraints
-RUN pip install --no-cache-dir --use-pep517 \
-    --upgrade-strategy=only-if-needed \
-    --constraint constraints-offline.txt \
-    ".[api]" -r requirements-offline.txt
+# Sync dependencies inside the final image using uv
+# And ensure pip is available for runtime installs
+RUN uv sync --frozen --no-dev --extra api --no-editable \
+    && /app/.venv/bin/python -m ensurepip --upgrade

-# Create persistent data directories AFTER package installation
+# Create persistent data directories
 RUN mkdir -p /app/data/rag_storage /app/data/inputs /app/data/tiktoken

-# Copy offline cache into the newly created directory
+# Copy cached tokenizer assets prepared in the builder stage
 COPY --from=builder /app/data/tiktoken /app/data/tiktoken

-# Point to the prepared cache
+# Docker data directories
 ENV TIKTOKEN_CACHE_DIR=/app/data/tiktoken
 ENV WORKING_DIR=/app/data/rag_storage
 ENV INPUT_DIR=/app/data/inputs
@ -93,4 +98,5 @@ ENV INPUT_DIR=/app/data/inputs
 # Expose API port
 EXPOSE 9621

+# Set entrypoint
 ENTRYPOINT ["python", "-m", "lightrag.api.lightrag_server"]
--- a/constraints-offline.txt
+++ b/constraints-offline.txt
@ -1,160 +0,0 @@
-# Exact version constraints based on successful local installation with uv pip install ".[offline]"
-# Generated: 2025-10-15
-# Use with: pip install --constraint constraints-offline.txt -r requirements-offline.txt
-
-accelerate==1.10.1
-
-# AWS/Boto packages
-aioboto3==15.2.0
-aiobotocore==2.24.2
-
-# Utility packages
-aioitertools==0.12.0
-aiolimiter==1.2.1
-aiosqlite==0.21.0
-anthropic==0.69.0
-antlr4-python3-runtime==4.9.3
-asyncpg
-beautifulsoup4==4.14.2
-boto3==1.40.18
-botocore==1.40.18
-cachetools==6.2.1
-colorama==0.4.6
-colorlog==6.9.0
-dataclasses-json==0.6.7
-defusedxml==0.7.1
-deprecated==1.2.18
-dill==0.4.0
-dirtyjson==1.0.8
-dnspython==2.8.0
-
-# Document processing packages
-docling==2.57.0
-docling-core==2.48.4
-docling-ibm-models==3.9.1
-docling-parse==4.5.0
-docstring-parser==0.17.0
-faker==37.11.0
-filetype==1.2.0
-fsspec==2025.9.0
-greenlet==3.2.4
-griffe==1.14.0
-grpcio==1.75.1
-h2==4.3.0
-hpack==4.1.0
-huggingface-hub==0.35.3
-hyperframe==6.1.0
-jinja2==3.1.6
-jmespath==1.0.1
-joblib==1.5.2
-jsonlines==3.1.0
-jsonpatch==1.33
-jsonpointer==3.0.0
-jsonref==1.1.0
-jsonschema==4.25.1
-jsonschema-specifications==2025.9.1
-langchain-core==0.3.79
-langchain-text-splitters==0.3.11
-langsmith==0.4.35
-latex2mathml==3.78.1
-llama-cloud==0.1.35
-llama-cloud-services==0.6.54
-
-# LlamaIndex packages
-llama-index==0.14.4
-llama-index-cli==0.5.3
-llama-index-core==0.14.4
-llama-index-embeddings-openai==0.5.1
-llama-index-indices-managed-llama-cloud==0.9.4
-llama-index-instrumentation==0.4.2
-llama-index-llms-openai==0.6.4
-llama-index-readers-file==0.5.4
-llama-index-readers-llama-parse==0.5.1
-llama-index-workflows==2.8.0
-llama-parse==0.6.54
-lxml==5.4.0
-markdown-it-py==4.0.0
-marko==2.2.1
-markupsafe==3.0.3
-marshmallow==3.26.1
-mdurl==0.1.2
-mpire==2.10.2
-mpmath==1.3.0
-multiprocess==0.70.18
-mypy-extensions==1.1.1
-neo4j==6.0.2
-nest-asyncio==1.6.0
-
-# NLP packages
-nltk==3.9.2
-numpy
-ollama==0.6.0
-omegaconf==2.3.0
-
-# LLM Provider packages
-openai==1.109.1
-
-# Computer vision
-opencv-python==4.11.0.86
-opencv-python-headless==4.11.0.86
-openpyxl==3.1.5
-orjson==3.11.3
-
-# Data processing
-pandas==2.2.3
-pillow==11.3.0
-pluggy==1.6.0
-polyfactory==2.22.2
-portalocker==3.2.0
-protobuf==6.32.1
-pyclipper==1.3.0.post6
-pydantic-settings==2.11.0
-pygments==2.19.2
-
-# Authentication
-pyjwt==2.8.0
-pylatexenc==2.10
-pymilvus==2.6.2
-pymongo==4.15.3
-pypdf==6.1.1
-pypdfium2==4.30.0
-python-docx==1.2.0
-python-pptx==1.0.2
-qdrant-client==1.15.1
-rapidocr==3.4.2
-
-# Storage backends
-redis==6.4.0
-referencing==0.37.0
-requests-toolbelt==1.0.0
-rich==14.2.0
-rpds-py==0.27.1
-rtree==1.4.1
-s3transfer==0.13.1
-safetensors==0.6.2
-scipy==1.16.2
-semchunk==2.2.2
-shapely==2.1.2
-shellingham==1.5.4
-soupsieve==2.8
-sqlalchemy==2.0.44
-striprtf==0.0.26
-sympy==1.14.0
-tabulate==0.9.0
-tokenizers==0.22.1
-# Core ML/AI packages
-torch==2.2.2
-torchvision==0.17.2
-transformers==4.57.1
-typer==0.19.2
-typing-inspect==0.9.0
-ujson==5.11.0
-voyageai==0.3.5
-wrapt==1.17.3
-zhipuai==2.1.5.20250825
-zstandard==0.25.0
-
-# Special packages (platform-specific)
-# Note: These may not be available on all platforms
-# ocrmac==1.0.0  # macOS only
-# pyobjc-* packages are macOS only
--- a/docker-build-push.sh
+++ b/docker-build-push.sh
@ -0,0 +1,77 @@
+#!/bin/bash
+set -e
+
+# Configuration
+IMAGE_NAME="ghcr.io/hkuds/lightrag"
+DOCKERFILE="Dockerfile"
+TAG="latest"
+
+# Get version from git tags
+VERSION=$(git describe --tags --abbrev=0 2>/dev/null || echo "dev")
+
+echo "=================================="
+echo "  Multi-Architecture Docker Build"
+echo "=================================="
+echo "Image: ${IMAGE_NAME}:${TAG}"
+echo "Version: ${VERSION}"
+echo "Platforms: linux/amd64, linux/arm64"
+echo "=================================="
+echo ""
+
+# Check Docker login status (skip if CR_PAT is set for CI/CD)
+if [ -z "$CR_PAT" ]; then
+    if ! docker info 2>/dev/null | grep -q "Username"; then
+        echo "⚠️  Warning: Not logged in to Docker registry"
+        echo "Please login first: docker login ghcr.io"
+        echo "Or set CR_PAT environment variable for automated login"
+        echo ""
+        read -p "Continue anyway? (y/n) " -n 1 -r
+        echo
+        if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+            exit 1
+        fi
+    fi
+else
+    echo "Using CR_PAT environment variable for authentication"
+fi
+
+# Check if buildx builder exists, create if not
+if ! docker buildx ls | grep -q "desktop-linux"; then
+    echo "Creating buildx builder..."
+    docker buildx create --name desktop-linux --use
+    docker buildx inspect --bootstrap
+else
+    echo "Using existing buildx builder: desktop-linux"
+    docker buildx use desktop-linux
+fi
+
+echo ""
+echo "Building and pushing multi-architecture image..."
+echo ""
+
+# Build and push
+docker buildx build \
+  --platform linux/amd64,linux/arm64 \
+  --file ${DOCKERFILE} \
+  --tag ${IMAGE_NAME}:${TAG} \
+  --tag ${IMAGE_NAME}:${VERSION} \
+  --push \
+  .
+
+echo ""
+echo "✓ Build and push complete!"
+echo ""
+echo "Images pushed:"
+echo "  - ${IMAGE_NAME}:${TAG}"
+echo "  - ${IMAGE_NAME}:${VERSION}"
+echo ""
+echo "Verifying multi-architecture manifest..."
+echo ""
+
+# Verify
+docker buildx imagetools inspect ${IMAGE_NAME}:${TAG}
+
+echo ""
+echo "✓ Verification complete!"
+echo ""
+echo "Pull with: docker pull ${IMAGE_NAME}:${TAG}"
--- a/docker-compose.yml
+++ b/docker-compose.yml
@ -14,11 +14,8 @@ services:
      - ./data/inputs:/app/data/inputs
      - ./config.ini:/app/config.ini
      - ./.env:/app/.env
-      # - ./data/tiktoken:/app/data/tiktoken
    env_file:
      - .env
-    environment:
-      - TIKTOKEN_CACHE_DIR=/app/data/tiktoken
    restart: unless-stopped
    extra_hosts:
      - "host.docker.internal:host-gateway"
--- a/docs/DockerDeployment.md
+++ b/docs/DockerDeployment.md
@ -1,17 +1,11 @@
-# LightRAG
+# LightRAG Docker Deployment

 A lightweight Knowledge Graph Retrieval-Augmented Generation system with multiple LLM backend support.

-## 🚀 Installation
+## 🚀 Preparation

-### Prerequisites
- Python 3.10+
- Git
- Docker (optional for Docker deployment)
+### Clone the repository:

-### Native Installation
-
-1. Clone the repository:
 ```bash
 # Linux/MacOS
 git clone https://github.com/HKUDS/LightRAG.git
@ -23,7 +17,8 @@ git clone https://github.com/HKUDS/LightRAG.git
 cd LightRAG
 ```

-2. Configure your environment:
+### Configure your environment:
+
 ```bash
 # Linux/MacOS
 cp .env.example .env
@ -35,141 +30,92 @@ Copy-Item .env.example .env
 # Edit .env with your preferred configuration
 ```

-3. Create and activate virtual environment:
-```bash
-# Linux/MacOS
-python -m venv venv
-source venv/bin/activate
-```
-```powershell
-# Windows PowerShell
-python -m venv venv
-.\venv\Scripts\Activate
-```
+LightRAG can be configured using environment variables in the `.env` file:

-4. Install dependencies:
-```bash
-# Both platforms
-pip install -r requirements.txt
-```
+**Server Configuration**
+
+- `HOST`: Server host (default: 0.0.0.0)
+- `PORT`: Server port (default: 9621)
+
+**LLM Configuration**
+
+- `LLM_BINDING`: LLM backend to use (lollms/ollama/openai)
+- `LLM_BINDING_HOST`: LLM server host URL
+- `LLM_MODEL`: Model name to use
+
+**Embedding Configuration**
+
+- `EMBEDDING_BINDING`: Embedding backend (lollms/ollama/openai)
+- `EMBEDDING_BINDING_HOST`: Embedding server host URL
+- `EMBEDDING_MODEL`: Embedding model name
+
+**RAG Configuration**
+
+- `MAX_ASYNC`: Maximum async operations
+- `MAX_TOKENS`: Maximum token size
+- `EMBEDDING_DIM`: Embedding dimensions

 ## 🐳 Docker Deployment

 Docker instructions work the same on all platforms with Docker Desktop installed.

-1. Build and start the container:
+### Start LightRAG  server:
+
 ```bash
 docker-compose up -d
 ```

-### Configuration Options
+LightRAG Server uses the following paths for data storage:

-LightRAG can be configured using environment variables in the `.env` file:
-
-#### Server Configuration
- `HOST`: Server host (default: 0.0.0.0)
- `PORT`: Server port (default: 9621)
-
-#### LLM Configuration
- `LLM_BINDING`: LLM backend to use (lollms/ollama/openai)
- `LLM_BINDING_HOST`: LLM server host URL
- `LLM_MODEL`: Model name to use
-
-#### Embedding Configuration
- `EMBEDDING_BINDING`: Embedding backend (lollms/ollama/openai)
- `EMBEDDING_BINDING_HOST`: Embedding server host URL
- `EMBEDDING_MODEL`: Embedding model name
-
-#### RAG Configuration
- `MAX_ASYNC`: Maximum async operations
- `MAX_TOKENS`: Maximum token size
- `EMBEDDING_DIM`: Embedding dimensions
-
-#### Security
- `LIGHTRAG_API_KEY`: API key for authentication
-
-### Data Storage Paths
-
-The system uses the following paths for data storage:
 ```
 data/
 ├── rag_storage/    # RAG data persistence
 └── inputs/         # Input documents
 ```

-### Example Deployments
-
-1. Using with Ollama:
-```env
-LLM_BINDING=ollama
-LLM_BINDING_HOST=http://host.docker.internal:11434
-LLM_MODEL=mistral
-EMBEDDING_BINDING=ollama
-EMBEDDING_BINDING_HOST=http://host.docker.internal:11434
-EMBEDDING_MODEL=bge-m3
-```
-
-you can't just use localhost from docker, that's why you need to use host.docker.internal which is defined in the docker compose file and should allow you to access the localhost services.
-
-2. Using with OpenAI:
-```env
-LLM_BINDING=openai
-LLM_MODEL=gpt-3.5-turbo
-EMBEDDING_BINDING=openai
-EMBEDDING_MODEL=text-embedding-ada-002
-OPENAI_API_KEY=your-api-key
-```
-
-### API Usage
-
-Once deployed, you can interact with the API at `http://localhost:9621`
-
-Example query using PowerShell:
-```powershell
-$headers = @{
-    "X-API-Key" = "your-api-key"
-    "Content-Type" = "application/json"
-}
-$body = @{
-    query = "your question here"
-} | ConvertTo-Json
-
-Invoke-RestMethod -Uri "http://localhost:9621/query" -Method Post -Headers $headers -Body $body
-```
-
-Example query using curl:
-```bash
-curl -X POST "http://localhost:9621/query" \
-     -H "X-API-Key: your-api-key" \
-     -H "Content-Type: application/json" \
-     -d '{"query": "your question here"}'
-```
-
-## 🔒 Security
-
-Remember to:
-1. Set a strong API key in production
-2. Use SSL in production environments
-3. Configure proper network security
-
-## 📦 Updates
+### Updates

 To update the Docker container:
 ```bash
 docker-compose pull
-docker-compose up -d --build
+docker-compose down
+docker-compose up
 ```

-To update native installation:
+### Offline deployment
+
+Software packages requiring `transformers`, `torch`, or `cuda` will is not preinstalled in the dokcer images. Consequently, document extraction tools such as Docling, as well as local LLM models like Hugging Face and LMDeploy, can not be used in an off line enviroment. These high-compute-resource-demanding services should not be integrated into LightRAG. Docling will be decoupled and deployed as a standalone service.
+
+## 📦 Build Docker Images
+
+### For local development and testing
+
 ```bash
-# Linux/MacOS
-git pull
-source venv/bin/activate
-pip install -r requirements.txt
+# Build and run with docker-compose
+docker compose up --build
 ```
-```powershell
-# Windows PowerShell
-git pull
-.\venv\Scripts\Activate
-pip install -r requirements.txt
+
+### For production release
+
+ **multi-architecture build and push**:
+
+```bash
+# Use the provided build script
+./docker-build-push.sh
 ```
+
+**The build script will**:
+
+- Check Docker registry login status
+- Create/use buildx builder automatically
+- Build for both AMD64 and ARM64 architectures
+- Push to GitHub Container Registry (ghcr.io)
+- Verify the multi-architecture manifest
+
+**Prerequisites**:
+
+Before building multi-architecture images, ensure you have:
+
+- Docker 20.10+ with Buildx support
+- Sufficient disk space (20GB+ recommended for offline image)
+- Registry access credentials (if pushing images)
--- a/docs/OfflineDeployment.md
+++ b/docs/OfflineDeployment.md
@ -2,6 +2,10 @@

 This guide provides comprehensive instructions for deploying LightRAG in offline environments where internet access is limited or unavailable.

+If you deploy LightRAG using Docker, there is no need to refer to this document, as the LightRAG Docker image is pre-configured for offline operation.
+
+> Software packages requiring `transformers`, `torch`, or `cuda` will not be included in the offline dependency group. Consequently, document extraction tools such as Docling, as well as local LLM models like Hugging Face and LMDeploy, are outside the scope of offline installation support. These high-compute-resource-demanding services should not be integrated into LightRAG. Docling will be decoupled and deployed as a standalone service.
+
 ## Table of Contents

 - [Overview](#overview)
@ -76,6 +80,8 @@ LightRAG provides flexible dependency groups for different use cases:
 | `offline-llm` | LLM providers | OpenAI, Anthropic, Ollama, etc. |
 | `offline` | All of the above | Complete offline deployment |

+> Software packages requiring `transformers`, `torch`, or `cuda` will not be included in the offline dependency group.
+
 ### Installation Examples

 ```bash
--- a/docs/UV_LOCK_GUIDE.md
+++ b/docs/UV_LOCK_GUIDE.md
@ -0,0 +1,170 @@
+# uv.lock Update Guide
+
+## What is uv.lock?
+
+`uv.lock` is uv's lock file. It captures the exact version of every dependency, including transitive ones, much like:
+- Node.js `package-lock.json`
+- Rust `Cargo.lock`
+- Python Poetry `poetry.lock`
+
+Keeping `uv.lock` in version control guarantees that everyone installs the same dependency set.
+
+## When does uv.lock change?
+
+### Situations where it does *not* change automatically
+
+- Running `uv sync --frozen`
+- Building Docker images that call `uv sync --frozen`
+- Editing source code without touching dependency metadata
+
+### Situations where it will change
+
+1. **`uv lock` or `uv lock --upgrade`**
+
+   ```bash
+   uv lock                # Resolve according to current constraints
+   uv lock --upgrade      # Re-resolve and upgrade to the newest compatible releases
+   ```
+
+   Use these commands after modifying `pyproject.toml`, when you want fresh dependency versions, or if the lock file was deleted or corrupted.
+
+2. **`uv add`**
+
+   ```bash
+    uv add requests           # Adds the dependency and updates both files
+    uv add --dev pytest       # Adds a dev dependency
+   ```
+
+   `uv add` edits `pyproject.toml` and refreshes `uv.lock` in one step.
+
+3. **`uv remove`**
+
+   ```bash
+   uv remove requests
+   ```
+
+   This removes the dependency from `pyproject.toml` and rewrites `uv.lock`.
+
+4. **`uv sync` without `--frozen`**
+
+   ```bash
+   uv sync
+   ```
+
+   Normally this only installs what is already locked. However, if `pyproject.toml` and `uv.lock` disagree or the lock file is missing, uv will regenerate and update `uv.lock`. In CI and production builds you should prefer `uv sync --frozen` to prevent unintended updates.
+
+## Example workflows
+
+### Scenario 1: Add a new dependency
+
+```bash
+# Recommended: let uv handle both files
+uv add fastapi
+git add pyproject.toml uv.lock
+git commit -m "Add fastapi dependency"
+
+# Manual alternative
+# 1. Edit pyproject.toml
+# 2. Regenerate the lock file
+uv lock
+git add pyproject.toml uv.lock
+git commit -m "Add fastapi dependency"
+```
+
+### Scenario 2: Relax or tighten a version constraint
+
+```bash
+# 1. Edit the requirement in pyproject.toml,
+#    e.g. openai>=1.0.0,<2.0.0 -> openai>=1.5.0,<2.0.0
+
+# 2. Re-resolve the lock file
+uv lock
+
+# 3. Commit both files
+git add pyproject.toml uv.lock
+git commit -m "Update openai to >=1.5.0"
+```
+
+### Scenario 3: Upgrade everything to the newest compatible versions
+
+```bash
+uv lock --upgrade
+git diff uv.lock
+git add uv.lock
+git commit -m "Upgrade dependencies to latest compatible versions"
+```
+
+### Scenario 4: Teammate syncing the project
+
+```bash
+git pull               # Fetch latest code and lock file
+uv sync --frozen       # Install exactly what uv.lock specifies
+```
+
+## Using uv.lock in Docker
+
+```dockerfile
+RUN uv sync --frozen --no-dev --extra api
+```
+
+`--frozen` guarantees reproducible builds because uv will refuse to deviate from the locked versions.
+`--extra api` install API server
+
+## Generating a lock file that includes offline dependencies
+
+If you need `uv.lock` to capture the optional offline stacks, regenerate it with the relevant extras enabled:
+
+```bash
+uv lock --extra api --extra offline
+```
+
+This command resolves the base project requirements plus both the `api` and `offline` optional dependency sets, ensuring downstream `uv sync --frozen --extra api --extra offline` installs work without further resolution.
+
+## Frequently asked questions
+
+- **`uv.lock` is almost 1 MB. Does that matter?**
+  No. The file is read only during dependency resolution.
+
+- **Should we commit `uv.lock`?**
+  Yes. Commit it so collaborators and CI jobs share the same dependency graph.
+
+- **Deleted the lock file by accident?**
+  Run `uv lock` to regenerate it from `pyproject.toml`.
+
+- **Can `uv.lock` and `requirements.txt` coexist?**
+  They can, but maintaining both is redundant. Prefer relying on `uv.lock` alone whenever possible.
+
+- **How do I inspect locked versions?**
+  ```bash
+  uv tree
+  grep -A5 'name = "openai"' uv.lock
+  ```
+
+## Best practices
+
+### Recommended
+
+1. Commit `uv.lock` alongside `pyproject.toml`.
+2. Use `uv sync --frozen` in CI, Docker, and other reproducible environments.
+3. Use plain `uv sync` during local development if you want uv to reconcile the lock for you.
+4. Run `uv lock --upgrade` periodically to pick up the latest compatible releases.
+5. Regenerate the lock file immediately after changing dependency constraints.
+
+### Avoid
+
+1. Running `uv sync` without `--frozen` in CI or production pipelines.
+2. Editing `uv.lock` by hand—uv will overwrite manual edits.
+3. Ignoring lock file diffs in code reviews—unexpected dependency changes can break builds.
+
+## Summary
+
+| Command               | Updates `uv.lock` | Typical use                               |
+|-----------------------|-------------------|-------------------------------------------|
+| `uv lock`             | ✅ Yes            | After editing constraints                 |
+| `uv lock --upgrade`   | ✅ Yes            | Upgrade to the newest compatible versions |
+| `uv add <pkg>`        | ✅ Yes            | Add a dependency                          |
+| `uv remove <pkg>`     | ✅ Yes            | Remove a dependency                       |
+| `uv sync`             | ⚠️ Maybe          | Local development; can regenerate the lock |
+| `uv sync --frozen`    | ❌ No             | CI/CD, Docker, reproducible builds        |
+
+Remember: `uv.lock` only changes when you run a command that tells it to. Keep it in sync with your project and commit it whenever it changes.
--- a/env.example
+++ b/env.example
@ -23,7 +23,7 @@ WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
 # WORKING_DIR=<absolute_path_for_working_dir>

 ### Tiktoken cache directory (Store cached files in this folder for offline deployment)
-# TIKTOKEN_CACHE_DIR=./temp/tiktoken
+# TIKTOKEN_CACHE_DIR=/app/data/tiktoken

 ### Ollama Emulating Model and Tag
 # OLLAMA_EMULATING_MODEL_NAME=lightrag
--- a/lightrag/init.py
+++ b/lightrag/init.py
@ -1,5 +1,5 @@
 from .lightrag import LightRAG as LightRAG, QueryParam as QueryParam

-__version__ = "1.4.9.3"
+__version__ = "1.4.9.4"
 __author__ = "Zirui Guo"
 __url__ = "https://github.com/HKUDS/LightRAG"
--- a/lightrag/api/README-zh.md
+++ b/lightrag/api/README-zh.md
@ -118,36 +118,10 @@ lightrag-gunicorn --workers 4

 ### 使用 Docker 启动 LightRAG 服务器

-* 配置 .env 文件：
-    通过复制示例文件 [`env.example`](env.example) 创建个性化的 .env 文件，并根据实际需求设置 LLM 及 Embedding 参数。
-* 创建一个名为 docker-compose.yml 的文件：
-
-```yaml
-services:
-  lightrag:
-    container_name: lightrag
-    image: ghcr.io/hkuds/lightrag:latest
-    build:
-      context: .
-      dockerfile: Dockerfile
-      tags:
-        - ghcr.io/hkuds/lightrag:latest
-    ports:
-      - "${PORT:-9621}:9621"
-    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"
-```
+使用 Docker Compose 是部署和运行 LightRAG Server 最便捷的方式。
+- 创建一个项目目录。
+- 将 LightRAG 仓库中的 `docker-compose.yml` 文件复制到您的项目目录中。
+- 准备 `.env` 文件：复制示例文件 [`env.example`](https://ai.znipower.com:5013/c/env.example) 创建自定义的 `.env` 文件，并根据您的具体需求配置 LLM 和嵌入参数。

 * 通过以下命令启动 LightRAG 服务器：

@ -155,11 +129,11 @@ services:
 docker compose up
 # 如果希望启动后让程序退到后台运行，需要在命令的最后添加 -d 参数
 ```
-> 可以通过以下链接获取官方的docker compose文件：[docker-compose.yml]( https://raw.githubusercontent.com/HKUDS/LightRAG/refs/heads/main/docker-compose.yml) 。如需获取LightRAG的历史版本镜像，可以访问以下链接: [LightRAG Docker Images]( https://github.com/HKUDS/LightRAG/pkgs/container/lightrag)
+> 可以通过以下链接获取官方的docker compose文件：[docker-compose.yml]( https://raw.githubusercontent.com/HKUDS/LightRAG/refs/heads/main/docker-compose.yml) 。如需获取LightRAG的历史版本镜像，可以访问以下链接: [LightRAG Docker Images]( https://github.com/HKUDS/LightRAG/pkgs/container/lightrag). 如需获取更多关于docker部署的信息，请参阅 [DockerDeployment.md](./../../docs/DockerDeployment.md).

 ### 离线部署

-对于离线或隔离环境，请参阅[离线部署指南](./../../docs/OfflineDeployment.md)，了解如何预先安装所有依赖项和缓存文件。
+官方的 LightRAG Docker 镜像完全兼容离线或隔离网络环境。如需搭建自己的离线部署环境，请参考 [离线部署指南](./../../docs/OfflineDeployment.md)。

 ### 启动多个LightRAG实例

--- a/lightrag/api/README.md
+++ b/lightrag/api/README.md
@ -119,37 +119,13 @@ During startup, configurations in the `.env` file can be overridden by command-l

 ### Launching LightRAG Server with Docker

-* Prepare the .env file:
-    Create a personalized .env file by copying the sample file [`env.example`](env.example). Configure the LLM and embedding parameters according to your requirements.
+Using Docker Compose is the most convenient way to deploy and run the LightRAG Server.

-* Create a file named `docker-compose.yml`:
+* Create a project directory.

-```yaml
-services:
-  lightrag:
-    container_name: lightrag
-    image: ghcr.io/hkuds/lightrag:latest
-    build:
-      context: .
-      dockerfile: Dockerfile
-      tags:
-        - ghcr.io/hkuds/lightrag:latest
-    ports:
-      - "${PORT:-9621}:9621"
-    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"
-```
+* Copy the `docker-compose.yml` file from the LightRAG repository into your project directory.
+
+* Prepare the `.env` file: Duplicate the sample file [`env.example`](https://ai.znipower.com:5013/c/env.example)to create a customized `.env` file, and configure the LLM and embedding parameters according to your specific requirements.

 * Start the LightRAG Server with the following command:

@ -158,11 +134,11 @@ docker compose up
 # If you want the program to run in the background after startup, add the -d parameter at the end of the command.
 ```

-> You can get the official docker compose file from here: [docker-compose.yml](https://raw.githubusercontent.com/HKUDS/LightRAG/refs/heads/main/docker-compose.yml). For historical versions of LightRAG docker images, visit this link: [LightRAG Docker Images](https://github.com/HKUDS/LightRAG/pkgs/container/lightrag)
+You can get the official docker compose file from here: [docker-compose.yml](https://raw.githubusercontent.com/HKUDS/LightRAG/refs/heads/main/docker-compose.yml). For historical versions of LightRAG docker images, visit this link: [LightRAG Docker Images](https://github.com/HKUDS/LightRAG/pkgs/container/lightrag). For more details about docker deployment, please refer to [DockerDeployment.md](./../../docs/DockerDeployment.md).

 ### Offline Deployment

- For offline or air-gapped environments, see the [Offline Deployment Guide](./../../docs/OfflineDeployment.md) for instructions on pre-installing all dependencies and cache files.
+Official LightRAG Docker images are fully compatible with offline or air-gapped environments. If you want to build up you own  offline enviroment, please refer to [Offline Deployment Guide](./../../docs/OfflineDeployment.md).

 ### Starting Multiple LightRAG Instances

--- a/lightrag/api/lightrag_server.py
+++ b/lightrag/api/lightrag_server.py
@ -908,7 +908,9 @@ def create_app(args):
        async def get_response(self, path: str, scope):
            response = await super().get_response(path, scope)

-            if path.endswith(".html"):
+            is_html = path.endswith(".html") or response.media_type == "text/html"
+
+            if is_html:
                response.headers["Cache-Control"] = (
                    "no-cache, no-store, must-revalidate"
                )
--- a/lightrag/operate.py
+++ b/lightrag/operate.py
@ -3332,7 +3332,11 @@ async def _build_query_context(
        query_embedding=search_result["query_embedding"],
    )

-    if not merged_chunks:
+    if (
+        not merged_chunks
+        and not truncation_result["entities_context"]
+        and not truncation_result["relations_context"]
+    ):
        return None

    # Stage 4: Build final LLM context with dynamic token processing
--- a/pyproject.toml
+++ b/pyproject.toml
@ -80,7 +80,6 @@ api = [
 # Offline deployment dependencies (layered design for flexibility)
 offline-docs = [
    # Document processing dependencies
-    "docling>=1.0.0,<3.0.0",
    "pypdf2>=3.0.0",
    "python-docx>=0.8.11,<2.0.0",
    "python-pptx>=0.6.21,<2.0.0",
@ -106,8 +105,6 @@ offline-llm = [
    "aioboto3>=12.0.0,<16.0.0",
    "voyageai>=0.2.0,<1.0.0",
    "llama-index>=0.9.0,<1.0.0",
-    "transformers>=4.30.0,<5.0.0",
-    "torch>=2.0.0,<2.3.0",
 ]

 offline = [
--- a/requirements-offline-docs.txt
+++ b/requirements-offline-docs.txt
@ -8,7 +8,6 @@
 # Or use constraints: pip install --constraint constraints-offline.txt -r requirements-offline-docs.txt

 # Document processing dependencies (with version constraints matching pyproject.toml)
-docling>=1.0.0,<3.0.0
 openpyxl>=3.0.0,<4.0.0
 pypdf2>=3.0.0
 python-docx>=0.8.11,<2.0.0
--- a/requirements-offline-llm.txt
+++ b/requirements-offline-llm.txt
@ -13,7 +13,5 @@ anthropic>=0.18.0,<1.0.0
 llama-index>=0.9.0,<1.0.0
 ollama>=0.1.0,<1.0.0
 openai>=1.0.0,<2.0.0
-torch>=2.0.0,<2.3.0
-transformers>=4.30.0,<5.0.0
 voyageai>=0.2.0,<1.0.0
 zhipuai>=2.0.0,<3.0.0
--- a/requirements-offline.txt
+++ b/requirements-offline.txt
@ -15,7 +15,6 @@ anthropic>=0.18.0,<1.0.0
 asyncpg>=0.29.0,<1.0.0

 # Document processing dependencies
-docling>=1.0.0,<3.0.0
 llama-index>=0.9.0,<1.0.0
 neo4j>=5.0.0,<7.0.0
 ollama>=0.1.0,<1.0.0
@ -28,7 +27,5 @@ python-docx>=0.8.11,<2.0.0
 python-pptx>=0.6.21,<2.0.0
 qdrant-client>=1.7.0,<2.0.0
 redis>=5.0.0,<7.0.0
-torch>=2.0.0,<2.3.0
-transformers>=4.30.0,<5.0.0
 voyageai>=0.2.0,<1.0.0
 zhipuai>=2.0.0,<3.0.0
--- a/uv.lock
+++ b/uv.lock