mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-17 19:22:55 +08:00
Bump infinity to v0.6.11. Requires python>=3.11 (#11814)
### What problem does this PR solve? Bump infinity to v0.6.11. Requires python>=3.11 ### Type of change - [x] Refactoring
This commit is contained in:
1
.github/copilot-instructions.md
vendored
Normal file
1
.github/copilot-instructions.md
vendored
Normal file
@ -0,0 +1 @@
|
|||||||
|
Refer to [AGENTS.MD](../AGENTS.md) for all repo instructions.
|
||||||
21
.github/workflows/release.yml
vendored
21
.github/workflows/release.yml
vendored
@ -3,11 +3,12 @@ name: release
|
|||||||
on:
|
on:
|
||||||
schedule:
|
schedule:
|
||||||
- cron: '0 13 * * *' # This schedule runs every 13:00:00Z(21:00:00+08:00)
|
- cron: '0 13 * * *' # This schedule runs every 13:00:00Z(21:00:00+08:00)
|
||||||
|
# https://github.com/orgs/community/discussions/26286?utm_source=chatgpt.com#discussioncomment-3251208
|
||||||
|
# "The create event does not support branch filter and tag filter."
|
||||||
# The "create tags" trigger is specifically focused on the creation of new tags, while the "push tags" trigger is activated when tags are pushed, including both new tag creations and updates to existing tags.
|
# The "create tags" trigger is specifically focused on the creation of new tags, while the "push tags" trigger is activated when tags are pushed, including both new tag creations and updates to existing tags.
|
||||||
create:
|
push:
|
||||||
tags:
|
tags:
|
||||||
- "v*.*.*" # normal release
|
- "v*.*.*" # normal release
|
||||||
- "nightly" # the only one mutable tag
|
|
||||||
|
|
||||||
# https://docs.github.com/en/actions/using-jobs/using-concurrency
|
# https://docs.github.com/en/actions/using-jobs/using-concurrency
|
||||||
concurrency:
|
concurrency:
|
||||||
@ -21,9 +22,9 @@ jobs:
|
|||||||
- name: Ensure workspace ownership
|
- name: Ensure workspace ownership
|
||||||
run: echo "chown -R ${USER} ${GITHUB_WORKSPACE}" && sudo chown -R ${USER} ${GITHUB_WORKSPACE}
|
run: echo "chown -R ${USER} ${GITHUB_WORKSPACE}" && sudo chown -R ${USER} ${GITHUB_WORKSPACE}
|
||||||
|
|
||||||
# https://github.com/actions/checkout/blob/v3/README.md
|
# https://github.com/actions/checkout/blob/v6/README.md
|
||||||
- name: Check out code
|
- name: Check out code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v6
|
||||||
with:
|
with:
|
||||||
token: ${{ secrets.GITHUB_TOKEN }} # Use the secret as an environment variable
|
token: ${{ secrets.GITHUB_TOKEN }} # Use the secret as an environment variable
|
||||||
fetch-depth: 0
|
fetch-depth: 0
|
||||||
@ -31,12 +32,12 @@ jobs:
|
|||||||
|
|
||||||
- name: Prepare release body
|
- name: Prepare release body
|
||||||
run: |
|
run: |
|
||||||
if [[ ${GITHUB_EVENT_NAME} == "create" ]]; then
|
if [[ ${GITHUB_EVENT_NAME} != "schedule" ]]; then
|
||||||
RELEASE_TAG=${GITHUB_REF#refs/tags/}
|
RELEASE_TAG=${GITHUB_REF#refs/tags/}
|
||||||
if [[ ${RELEASE_TAG} == "nightly" ]]; then
|
if [[ ${RELEASE_TAG} == v* ]]; then
|
||||||
PRERELEASE=true
|
|
||||||
else
|
|
||||||
PRERELEASE=false
|
PRERELEASE=false
|
||||||
|
else
|
||||||
|
PRERELEASE=true
|
||||||
fi
|
fi
|
||||||
echo "Workflow triggered by create tag: ${RELEASE_TAG}"
|
echo "Workflow triggered by create tag: ${RELEASE_TAG}"
|
||||||
else
|
else
|
||||||
@ -55,7 +56,7 @@ jobs:
|
|||||||
git fetch --tags
|
git fetch --tags
|
||||||
if [[ ${GITHUB_EVENT_NAME} == "schedule" ]]; then
|
if [[ ${GITHUB_EVENT_NAME} == "schedule" ]]; then
|
||||||
# Determine if a given tag exists and matches a specific Git commit.
|
# Determine if a given tag exists and matches a specific Git commit.
|
||||||
# actions/checkout@v4 fetch-tags doesn't work when triggered by schedule
|
# actions/checkout@v6 fetch-tags doesn't work when triggered by schedule
|
||||||
if [ "$(git rev-parse -q --verify "refs/tags/${RELEASE_TAG}")" = "${GITHUB_SHA}" ]; then
|
if [ "$(git rev-parse -q --verify "refs/tags/${RELEASE_TAG}")" = "${GITHUB_SHA}" ]; then
|
||||||
echo "mutable tag ${RELEASE_TAG} exists and matches ${GITHUB_SHA}"
|
echo "mutable tag ${RELEASE_TAG} exists and matches ${GITHUB_SHA}"
|
||||||
else
|
else
|
||||||
@ -88,7 +89,7 @@ jobs:
|
|||||||
- name: Build and push image
|
- name: Build and push image
|
||||||
run: |
|
run: |
|
||||||
sudo docker login --username infiniflow --password-stdin <<< ${{ secrets.DOCKERHUB_TOKEN }}
|
sudo docker login --username infiniflow --password-stdin <<< ${{ secrets.DOCKERHUB_TOKEN }}
|
||||||
sudo docker build --build-arg NEED_MIRROR=1 -t infiniflow/ragflow:${RELEASE_TAG} -f Dockerfile .
|
sudo docker build --build-arg NEED_MIRROR=1 --build-arg HTTPS_PROXY=${HTTPS_PROXY} --build-arg HTTP_PROXY=${HTTP_PROXY} -t infiniflow/ragflow:${RELEASE_TAG} -f Dockerfile .
|
||||||
sudo docker tag infiniflow/ragflow:${RELEASE_TAG} infiniflow/ragflow:latest
|
sudo docker tag infiniflow/ragflow:${RELEASE_TAG} infiniflow/ragflow:latest
|
||||||
sudo docker push infiniflow/ragflow:${RELEASE_TAG}
|
sudo docker push infiniflow/ragflow:${RELEASE_TAG}
|
||||||
sudo docker push infiniflow/ragflow:latest
|
sudo docker push infiniflow/ragflow:latest
|
||||||
|
|||||||
11
.github/workflows/tests.yml
vendored
11
.github/workflows/tests.yml
vendored
@ -34,9 +34,6 @@ jobs:
|
|||||||
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && contains(github.event.pull_request.labels.*.name, 'ci')) }}
|
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && contains(github.event.pull_request.labels.*.name, 'ci')) }}
|
||||||
runs-on: [ "self-hosted", "ragflow-test" ]
|
runs-on: [ "self-hosted", "ragflow-test" ]
|
||||||
steps:
|
steps:
|
||||||
# https://github.com/hmarr/debug-action
|
|
||||||
#- uses: hmarr/debug-action@v2
|
|
||||||
|
|
||||||
- name: Ensure workspace ownership
|
- name: Ensure workspace ownership
|
||||||
run: |
|
run: |
|
||||||
echo "Workflow triggered by ${{ github.event_name }}"
|
echo "Workflow triggered by ${{ github.event_name }}"
|
||||||
@ -44,7 +41,7 @@ jobs:
|
|||||||
|
|
||||||
# https://github.com/actions/checkout/issues/1781
|
# https://github.com/actions/checkout/issues/1781
|
||||||
- name: Check out code
|
- name: Check out code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v6
|
||||||
with:
|
with:
|
||||||
ref: ${{ (github.event_name == 'pull_request' || github.event_name == 'pull_request_target') && format('refs/pull/{0}/merge', github.event.pull_request.number) || github.sha }}
|
ref: ${{ (github.event_name == 'pull_request' || github.event_name == 'pull_request_target') && format('refs/pull/{0}/merge', github.event.pull_request.number) || github.sha }}
|
||||||
fetch-depth: 0
|
fetch-depth: 0
|
||||||
@ -129,7 +126,7 @@ jobs:
|
|||||||
|
|
||||||
- name: Run unit test
|
- name: Run unit test
|
||||||
run: |
|
run: |
|
||||||
uv sync --python 3.10 --group test --frozen
|
uv sync --python 3.11 --group test --frozen
|
||||||
source .venv/bin/activate
|
source .venv/bin/activate
|
||||||
which pytest || echo "pytest not in PATH"
|
which pytest || echo "pytest not in PATH"
|
||||||
echo "Start to run unit test"
|
echo "Start to run unit test"
|
||||||
@ -141,7 +138,7 @@ jobs:
|
|||||||
RAGFLOW_IMAGE=infiniflow/ragflow:${GITHUB_RUN_ID}
|
RAGFLOW_IMAGE=infiniflow/ragflow:${GITHUB_RUN_ID}
|
||||||
echo "RAGFLOW_IMAGE=${RAGFLOW_IMAGE}" >> ${GITHUB_ENV}
|
echo "RAGFLOW_IMAGE=${RAGFLOW_IMAGE}" >> ${GITHUB_ENV}
|
||||||
sudo docker pull ubuntu:22.04
|
sudo docker pull ubuntu:22.04
|
||||||
sudo DOCKER_BUILDKIT=1 docker build --build-arg NEED_MIRROR=1 -f Dockerfile -t ${RAGFLOW_IMAGE} .
|
sudo DOCKER_BUILDKIT=1 docker build --build-arg NEED_MIRROR=1 --build-arg HTTPS_PROXY=${HTTPS_PROXY} --build-arg HTTP_PROXY=${HTTP_PROXY} -f Dockerfile -t ${RAGFLOW_IMAGE} .
|
||||||
if [[ ${GITHUB_EVENT_NAME} == "schedule" ]]; then
|
if [[ ${GITHUB_EVENT_NAME} == "schedule" ]]; then
|
||||||
export HTTP_API_TEST_LEVEL=p3
|
export HTTP_API_TEST_LEVEL=p3
|
||||||
else
|
else
|
||||||
@ -201,7 +198,7 @@ jobs:
|
|||||||
echo "HOST_ADDRESS=http://host.docker.internal:${SVR_HTTP_PORT}" >> ${GITHUB_ENV}
|
echo "HOST_ADDRESS=http://host.docker.internal:${SVR_HTTP_PORT}" >> ${GITHUB_ENV}
|
||||||
|
|
||||||
sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} up -d
|
sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} up -d
|
||||||
uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python --group test
|
uv sync --python 3.11 --only-group test --no-default-groups --frozen && uv pip install sdk/python --group test
|
||||||
|
|
||||||
- name: Run sdk tests against Elasticsearch
|
- name: Run sdk tests against Elasticsearch
|
||||||
run: |
|
run: |
|
||||||
|
|||||||
110
AGENTS.md
Normal file
110
AGENTS.md
Normal file
@ -0,0 +1,110 @@
|
|||||||
|
# RAGFlow Project Instructions for GitHub Copilot
|
||||||
|
|
||||||
|
This file provides context, build instructions, and coding standards for the RAGFlow project.
|
||||||
|
It is structured to follow GitHub Copilot's [customization guidelines](https://docs.github.com/en/copilot/concepts/prompting/response-customization).
|
||||||
|
|
||||||
|
## 1. Project Overview
|
||||||
|
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It is a full-stack application with a Python backend and a React/TypeScript frontend.
|
||||||
|
|
||||||
|
- **Backend**: Python 3.10+ (Flask/Quart)
|
||||||
|
- **Frontend**: TypeScript, React, UmiJS
|
||||||
|
- **Architecture**: Microservices based on Docker.
|
||||||
|
- `api/`: Backend API server.
|
||||||
|
- `rag/`: Core RAG logic (indexing, retrieval).
|
||||||
|
- `deepdoc/`: Document parsing and OCR.
|
||||||
|
- `web/`: Frontend application.
|
||||||
|
|
||||||
|
## 2. Directory Structure
|
||||||
|
- `api/`: Backend API server (Flask/Quart).
|
||||||
|
- `apps/`: API Blueprints (Knowledge Base, Chat, etc.).
|
||||||
|
- `db/`: Database models and services.
|
||||||
|
- `rag/`: Core RAG logic.
|
||||||
|
- `llm/`: LLM, Embedding, and Rerank model abstractions.
|
||||||
|
- `deepdoc/`: Document parsing and OCR modules.
|
||||||
|
- `agent/`: Agentic reasoning components.
|
||||||
|
- `web/`: Frontend application (React + UmiJS).
|
||||||
|
- `docker/`: Docker deployment configurations.
|
||||||
|
- `sdk/`: Python SDK.
|
||||||
|
- `test/`: Backend tests.
|
||||||
|
|
||||||
|
## 3. Build Instructions
|
||||||
|
|
||||||
|
### Backend (Python)
|
||||||
|
The project uses **uv** for dependency management.
|
||||||
|
|
||||||
|
1. **Setup Environment**:
|
||||||
|
```bash
|
||||||
|
uv sync --python 3.11 --all-extras
|
||||||
|
uv run download_deps.py
|
||||||
|
```
|
||||||
|
|
||||||
|
2. **Run Server**:
|
||||||
|
- **Pre-requisite**: Start dependent services (MySQL, ES/Infinity, Redis, MinIO).
|
||||||
|
```bash
|
||||||
|
docker compose -f docker/docker-compose-base.yml up -d
|
||||||
|
```
|
||||||
|
- **Launch**:
|
||||||
|
```bash
|
||||||
|
source .venv/bin/activate
|
||||||
|
export PYTHONPATH=$(pwd)
|
||||||
|
bash docker/launch_backend_service.sh
|
||||||
|
```
|
||||||
|
|
||||||
|
### Frontend (TypeScript/React)
|
||||||
|
Located in `web/`.
|
||||||
|
|
||||||
|
1. **Install Dependencies**:
|
||||||
|
```bash
|
||||||
|
cd web
|
||||||
|
npm install
|
||||||
|
```
|
||||||
|
|
||||||
|
2. **Run Dev Server**:
|
||||||
|
```bash
|
||||||
|
npm run dev
|
||||||
|
```
|
||||||
|
Runs on port 8000 by default.
|
||||||
|
|
||||||
|
### Docker Deployment
|
||||||
|
To run the full stack using Docker:
|
||||||
|
```bash
|
||||||
|
cd docker
|
||||||
|
docker compose -f docker-compose.yml up -d
|
||||||
|
```
|
||||||
|
|
||||||
|
## 4. Testing Instructions
|
||||||
|
|
||||||
|
### Backend Tests
|
||||||
|
- **Run All Tests**:
|
||||||
|
```bash
|
||||||
|
uv run pytest
|
||||||
|
```
|
||||||
|
- **Run Specific Test**:
|
||||||
|
```bash
|
||||||
|
uv run pytest test/test_api.py
|
||||||
|
```
|
||||||
|
|
||||||
|
### Frontend Tests
|
||||||
|
- **Run Tests**:
|
||||||
|
```bash
|
||||||
|
cd web
|
||||||
|
npm run test
|
||||||
|
```
|
||||||
|
|
||||||
|
## 5. Coding Standards & Guidelines
|
||||||
|
- **Python Formatting**: Use `ruff` for linting and formatting.
|
||||||
|
```bash
|
||||||
|
ruff check
|
||||||
|
ruff format
|
||||||
|
```
|
||||||
|
- **Frontend Linting**:
|
||||||
|
```bash
|
||||||
|
cd web
|
||||||
|
npm run lint
|
||||||
|
```
|
||||||
|
- **Pre-commit**: Ensure pre-commit hooks are installed.
|
||||||
|
```bash
|
||||||
|
pre-commit install
|
||||||
|
pre-commit run --all-files
|
||||||
|
```
|
||||||
|
|
||||||
@ -45,7 +45,7 @@ RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on d
|
|||||||
### Backend Development
|
### Backend Development
|
||||||
```bash
|
```bash
|
||||||
# Install Python dependencies
|
# Install Python dependencies
|
||||||
uv sync --python 3.10 --all-extras
|
uv sync --python 3.11 --all-extras
|
||||||
uv run download_deps.py
|
uv run download_deps.py
|
||||||
pre-commit install
|
pre-commit install
|
||||||
|
|
||||||
|
|||||||
20
Dockerfile
20
Dockerfile
@ -49,20 +49,24 @@ RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
|
|||||||
apt install -y libatk-bridge2.0-0 && \
|
apt install -y libatk-bridge2.0-0 && \
|
||||||
apt install -y libpython3-dev libgtk-4-1 libnss3 xdg-utils libgbm-dev && \
|
apt install -y libpython3-dev libgtk-4-1 libnss3 xdg-utils libgbm-dev && \
|
||||||
apt install -y libjemalloc-dev && \
|
apt install -y libjemalloc-dev && \
|
||||||
apt install -y python3-pip pipx nginx unzip curl wget git vim less && \
|
apt install -y nginx unzip curl wget git vim less && \
|
||||||
apt install -y ghostscript && \
|
apt install -y ghostscript && \
|
||||||
apt install -y pandoc && \
|
apt install -y pandoc && \
|
||||||
apt install -y texlive
|
apt install -y texlive
|
||||||
|
|
||||||
RUN if [ "$NEED_MIRROR" == "1" ]; then \
|
# Install uv
|
||||||
pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && \
|
RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/,target=/deps \
|
||||||
pip3 config set global.trusted-host pypi.tuna.tsinghua.edu.cn; \
|
if [ "$NEED_MIRROR" == "1" ]; then \
|
||||||
mkdir -p /etc/uv && \
|
mkdir -p /etc/uv && \
|
||||||
echo "[[index]]" > /etc/uv/uv.toml && \
|
echo 'python-install-mirror = "https://registry.npmmirror.com/-/binary/python-build-standalone/"' > /etc/uv/uv.toml && \
|
||||||
|
echo '[[index]]' >> /etc/uv/uv.toml && \
|
||||||
echo 'url = "https://pypi.tuna.tsinghua.edu.cn/simple"' >> /etc/uv/uv.toml && \
|
echo 'url = "https://pypi.tuna.tsinghua.edu.cn/simple"' >> /etc/uv/uv.toml && \
|
||||||
echo "default = true" >> /etc/uv/uv.toml; \
|
echo 'default = true' >> /etc/uv/uv.toml; \
|
||||||
fi; \
|
fi; \
|
||||||
pipx install uv
|
tar xzf /deps/uv-x86_64-unknown-linux-gnu.tar.gz \
|
||||||
|
&& cp uv-x86_64-unknown-linux-gnu/* /usr/local/bin/ \
|
||||||
|
&& rm -rf uv-x86_64-unknown-linux-gnu \
|
||||||
|
&& uv python install 3.11
|
||||||
|
|
||||||
ENV PYTHONDONTWRITEBYTECODE=1 DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1
|
ENV PYTHONDONTWRITEBYTECODE=1 DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1
|
||||||
ENV PATH=/root/.local/bin:$PATH
|
ENV PATH=/root/.local/bin:$PATH
|
||||||
@ -147,7 +151,7 @@ RUN --mount=type=cache,id=ragflow_uv,target=/root/.cache/uv,sharing=locked \
|
|||||||
else \
|
else \
|
||||||
sed -i 's|pypi.tuna.tsinghua.edu.cn|pypi.org|g' uv.lock; \
|
sed -i 's|pypi.tuna.tsinghua.edu.cn|pypi.org|g' uv.lock; \
|
||||||
fi; \
|
fi; \
|
||||||
uv sync --python 3.10 --frozen
|
uv sync --python 3.11 --frozen
|
||||||
|
|
||||||
COPY web web
|
COPY web web
|
||||||
COPY docs docs
|
COPY docs docs
|
||||||
|
|||||||
@ -3,7 +3,7 @@
|
|||||||
FROM scratch
|
FROM scratch
|
||||||
|
|
||||||
# Copy resources downloaded via download_deps.py
|
# Copy resources downloaded via download_deps.py
|
||||||
COPY chromedriver-linux64-121-0-6167-85 chrome-linux64-121-0-6167-85 cl100k_base.tiktoken libssl1.1_1.1.1f-1ubuntu2_amd64.deb libssl1.1_1.1.1f-1ubuntu2_arm64.deb tika-server-standard-3.0.0.jar tika-server-standard-3.0.0.jar.md5 libssl*.deb /
|
COPY chromedriver-linux64-121-0-6167-85 chrome-linux64-121-0-6167-85 cl100k_base.tiktoken libssl1.1_1.1.1f-1ubuntu2_amd64.deb libssl1.1_1.1.1f-1ubuntu2_arm64.deb tika-server-standard-3.0.0.jar tika-server-standard-3.0.0.jar.md5 libssl*.deb uv-x86_64-unknown-linux-gnu.tar.gz /
|
||||||
|
|
||||||
COPY nltk_data /nltk_data
|
COPY nltk_data /nltk_data
|
||||||
|
|
||||||
|
|||||||
@ -314,7 +314,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/infiniflow/ragflow.git
|
git clone https://github.com/infiniflow/ragflow.git
|
||||||
cd ragflow/
|
cd ragflow/
|
||||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
uv sync --python 3.11 # install RAGFlow dependent python modules
|
||||||
uv run download_deps.py
|
uv run download_deps.py
|
||||||
pre-commit install
|
pre-commit install
|
||||||
```
|
```
|
||||||
|
|||||||
@ -288,7 +288,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/infiniflow/ragflow.git
|
git clone https://github.com/infiniflow/ragflow.git
|
||||||
cd ragflow/
|
cd ragflow/
|
||||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
uv sync --python 3.11 # install RAGFlow dependent python modules
|
||||||
uv run download_deps.py
|
uv run download_deps.py
|
||||||
pre-commit install
|
pre-commit install
|
||||||
```
|
```
|
||||||
|
|||||||
@ -288,7 +288,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/infiniflow/ragflow.git
|
git clone https://github.com/infiniflow/ragflow.git
|
||||||
cd ragflow/
|
cd ragflow/
|
||||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
uv sync --python 3.11 # install RAGFlow dependent python modules
|
||||||
uv run download_deps.py
|
uv run download_deps.py
|
||||||
pre-commit install
|
pre-commit install
|
||||||
```
|
```
|
||||||
|
|||||||
@ -283,7 +283,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/infiniflow/ragflow.git
|
git clone https://github.com/infiniflow/ragflow.git
|
||||||
cd ragflow/
|
cd ragflow/
|
||||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
uv sync --python 3.11 # install RAGFlow dependent python modules
|
||||||
uv run download_deps.py
|
uv run download_deps.py
|
||||||
pre-commit install
|
pre-commit install
|
||||||
```
|
```
|
||||||
|
|||||||
@ -305,7 +305,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/infiniflow/ragflow.git
|
git clone https://github.com/infiniflow/ragflow.git
|
||||||
cd ragflow/
|
cd ragflow/
|
||||||
uv sync --python 3.10 # instala os módulos Python dependentes do RAGFlow
|
uv sync --python 3.11 # instala os módulos Python dependentes do RAGFlow
|
||||||
uv run download_deps.py
|
uv run download_deps.py
|
||||||
pre-commit install
|
pre-commit install
|
||||||
```
|
```
|
||||||
|
|||||||
@ -315,7 +315,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/infiniflow/ragflow.git
|
git clone https://github.com/infiniflow/ragflow.git
|
||||||
cd ragflow/
|
cd ragflow/
|
||||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
uv sync --python 3.11 # install RAGFlow dependent python modules
|
||||||
uv run download_deps.py
|
uv run download_deps.py
|
||||||
pre-commit install
|
pre-commit install
|
||||||
```
|
```
|
||||||
|
|||||||
@ -315,7 +315,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
|
|||||||
```bash
|
```bash
|
||||||
git clone https://github.com/infiniflow/ragflow.git
|
git clone https://github.com/infiniflow/ragflow.git
|
||||||
cd ragflow/
|
cd ragflow/
|
||||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
uv sync --python 3.11 # install RAGFlow dependent python modules
|
||||||
uv run download_deps.py
|
uv run download_deps.py
|
||||||
pre-commit install
|
pre-commit install
|
||||||
```
|
```
|
||||||
|
|||||||
@ -56,7 +56,7 @@ async def async_request(
|
|||||||
method: str,
|
method: str,
|
||||||
url: str,
|
url: str,
|
||||||
*,
|
*,
|
||||||
timeout: float | httpx.Timeout | None = None,
|
request_timeout: float | httpx.Timeout | None = None,
|
||||||
follow_redirects: bool | None = None,
|
follow_redirects: bool | None = None,
|
||||||
max_redirects: Optional[int] = None,
|
max_redirects: Optional[int] = None,
|
||||||
headers: Optional[Dict[str, str]] = None,
|
headers: Optional[Dict[str, str]] = None,
|
||||||
@ -67,7 +67,7 @@ async def async_request(
|
|||||||
**kwargs: Any,
|
**kwargs: Any,
|
||||||
) -> httpx.Response:
|
) -> httpx.Response:
|
||||||
"""Lightweight async HTTP wrapper using httpx.AsyncClient with safe defaults."""
|
"""Lightweight async HTTP wrapper using httpx.AsyncClient with safe defaults."""
|
||||||
timeout = timeout if timeout is not None else DEFAULT_TIMEOUT
|
timeout = request_timeout if request_timeout is not None else DEFAULT_TIMEOUT
|
||||||
follow_redirects = (
|
follow_redirects = (
|
||||||
DEFAULT_FOLLOW_REDIRECTS if follow_redirects is None else follow_redirects
|
DEFAULT_FOLLOW_REDIRECTS if follow_redirects is None else follow_redirects
|
||||||
)
|
)
|
||||||
|
|||||||
@ -150,7 +150,7 @@ class MCPToolCallSession(ToolCallSession):
|
|||||||
except asyncio.CancelledError:
|
except asyncio.CancelledError:
|
||||||
break
|
break
|
||||||
|
|
||||||
async def _call_mcp_server(self, task_type: MCPTaskType, timeout: float | int = 8, **kwargs) -> Any:
|
async def _call_mcp_server(self, task_type: MCPTaskType, request_timeout: float | int = 8, **kwargs) -> Any:
|
||||||
if self._close:
|
if self._close:
|
||||||
raise ValueError("Session is closed")
|
raise ValueError("Session is closed")
|
||||||
|
|
||||||
@ -158,18 +158,18 @@ class MCPToolCallSession(ToolCallSession):
|
|||||||
await self._queue.put((task_type, kwargs, results))
|
await self._queue.put((task_type, kwargs, results))
|
||||||
|
|
||||||
try:
|
try:
|
||||||
result: CallToolResult | Exception = await asyncio.wait_for(results.get(), timeout=timeout)
|
result: CallToolResult | Exception = await asyncio.wait_for(results.get(), timeout=request_timeout)
|
||||||
if isinstance(result, Exception):
|
if isinstance(result, Exception):
|
||||||
raise result
|
raise result
|
||||||
return result
|
return result
|
||||||
except asyncio.TimeoutError:
|
except asyncio.TimeoutError:
|
||||||
raise asyncio.TimeoutError(f"MCP task '{task_type}' timeout after {timeout}s")
|
raise asyncio.TimeoutError(f"MCP task '{task_type}' timeout after {request_timeout}s")
|
||||||
except Exception:
|
except Exception:
|
||||||
raise
|
raise
|
||||||
|
|
||||||
async def _call_mcp_tool(self, name: str, arguments: dict[str, Any], timeout: float | int = 10) -> str:
|
async def _call_mcp_tool(self, name: str, arguments: dict[str, Any], request_timeout: float | int = 10) -> str:
|
||||||
result: CallToolResult = await self._call_mcp_server("tool_call", name=name, arguments=arguments,
|
result: CallToolResult = await self._call_mcp_server("tool_call", name=name, arguments=arguments,
|
||||||
timeout=timeout)
|
request_timeout=request_timeout)
|
||||||
|
|
||||||
if result.isError:
|
if result.isError:
|
||||||
return f"MCP server error: {result.content}"
|
return f"MCP server error: {result.content}"
|
||||||
@ -180,9 +180,9 @@ class MCPToolCallSession(ToolCallSession):
|
|||||||
else:
|
else:
|
||||||
return f"Unsupported content type {type(result.content)}"
|
return f"Unsupported content type {type(result.content)}"
|
||||||
|
|
||||||
async def _get_tools_from_mcp_server(self, timeout: float | int = 8) -> list[Tool]:
|
async def _get_tools_from_mcp_server(self, request_timeout: float | int = 8) -> list[Tool]:
|
||||||
try:
|
try:
|
||||||
result: ListToolsResult = await self._call_mcp_server("list_tools", timeout=timeout)
|
result: ListToolsResult = await self._call_mcp_server("list_tools", request_timeout=request_timeout)
|
||||||
return result.tools
|
return result.tools
|
||||||
except Exception:
|
except Exception:
|
||||||
raise
|
raise
|
||||||
@ -191,7 +191,7 @@ class MCPToolCallSession(ToolCallSession):
|
|||||||
if self._close:
|
if self._close:
|
||||||
raise ValueError("Session is closed")
|
raise ValueError("Session is closed")
|
||||||
|
|
||||||
future = asyncio.run_coroutine_threadsafe(self._get_tools_from_mcp_server(timeout=timeout), self._event_loop)
|
future = asyncio.run_coroutine_threadsafe(self._get_tools_from_mcp_server(request_timeout=timeout), self._event_loop)
|
||||||
try:
|
try:
|
||||||
return future.result(timeout=timeout)
|
return future.result(timeout=timeout)
|
||||||
except FuturesTimeoutError:
|
except FuturesTimeoutError:
|
||||||
|
|||||||
@ -72,7 +72,7 @@ services:
|
|||||||
infinity:
|
infinity:
|
||||||
profiles:
|
profiles:
|
||||||
- infinity
|
- infinity
|
||||||
image: infiniflow/infinity:v0.6.10
|
image: infiniflow/infinity:v0.6.11
|
||||||
volumes:
|
volumes:
|
||||||
- infinity_data:/var/infinity
|
- infinity_data:/var/infinity
|
||||||
- ./infinity_conf.toml:/infinity_conf.toml
|
- ./infinity_conf.toml:/infinity_conf.toml
|
||||||
|
|||||||
@ -1,5 +1,5 @@
|
|||||||
[general]
|
[general]
|
||||||
version = "0.6.10"
|
version = "0.6.11"
|
||||||
time_zone = "utc-8"
|
time_zone = "utc-8"
|
||||||
|
|
||||||
[network]
|
[network]
|
||||||
|
|||||||
@ -41,13 +41,19 @@ cd ragflow/
|
|||||||
pipx install uv
|
pipx install uv
|
||||||
```
|
```
|
||||||
|
|
||||||
2. Install Python dependencies:
|
2. Install RAGFlow service's Python dependencies:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
uv sync --python 3.11 --frozen
|
||||||
```
|
```
|
||||||
*A virtual environment named `.venv` is created, and all Python dependencies are installed into the new environment.*
|
*A virtual environment named `.venv` is created, and all Python dependencies are installed into the new environment.*
|
||||||
|
|
||||||
|
If you need to run tests against the RAGFlow service, install the test dependencies:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
uv sync --python 3.11 --group test --frozen && uv pip install sdk/python --group test
|
||||||
|
```
|
||||||
|
|
||||||
### Launch third-party services
|
### Launch third-party services
|
||||||
|
|
||||||
The following command launches the 'base' services (MinIO, Elasticsearch, Redis, and MySQL) using Docker Compose:
|
The following command launches the 'base' services (MinIO, Elasticsearch, Redis, and MySQL) using Docker Compose:
|
||||||
|
|||||||
@ -176,7 +176,7 @@ This section is contributed by our community contributor [yiminghub2024](https:/
|
|||||||
iii. Copy [docker/entrypoint.sh](https://github.com/infiniflow/ragflow/blob/main/docker/entrypoint.sh) locally.
|
iii. Copy [docker/entrypoint.sh](https://github.com/infiniflow/ragflow/blob/main/docker/entrypoint.sh) locally.
|
||||||
iv. Install the required dependencies using `uv`:
|
iv. Install the required dependencies using `uv`:
|
||||||
- Run `uv add mcp` or
|
- Run `uv add mcp` or
|
||||||
- Copy [pyproject.toml](https://github.com/infiniflow/ragflow/blob/main/pyproject.toml) locally and run `uv sync --python 3.10`.
|
- Copy [pyproject.toml](https://github.com/infiniflow/ragflow/blob/main/pyproject.toml) locally and run `uv sync --python 3.11`.
|
||||||
2. Edit **docker-compose.yml** to enable MCP (disabled by default).
|
2. Edit **docker-compose.yml** to enable MCP (disabled by default).
|
||||||
3. Launch the MCP server:
|
3. Launch the MCP server:
|
||||||
|
|
||||||
|
|||||||
@ -28,6 +28,7 @@ def get_urls(use_china_mirrors=False) -> list[Union[str, list[str]]]:
|
|||||||
"https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken",
|
"https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken",
|
||||||
["https://registry.npmmirror.com/-/binary/chrome-for-testing/121.0.6167.85/linux64/chrome-linux64.zip", "chrome-linux64-121-0-6167-85"],
|
["https://registry.npmmirror.com/-/binary/chrome-for-testing/121.0.6167.85/linux64/chrome-linux64.zip", "chrome-linux64-121-0-6167-85"],
|
||||||
["https://registry.npmmirror.com/-/binary/chrome-for-testing/121.0.6167.85/linux64/chromedriver-linux64.zip", "chromedriver-linux64-121-0-6167-85"],
|
["https://registry.npmmirror.com/-/binary/chrome-for-testing/121.0.6167.85/linux64/chromedriver-linux64.zip", "chromedriver-linux64-121-0-6167-85"],
|
||||||
|
"https://github.com/astral-sh/uv/releases/download/0.9.16/uv-x86_64-unknown-linux-gnu.tar.gz",
|
||||||
]
|
]
|
||||||
else:
|
else:
|
||||||
return [
|
return [
|
||||||
@ -38,6 +39,7 @@ def get_urls(use_china_mirrors=False) -> list[Union[str, list[str]]]:
|
|||||||
"https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken",
|
"https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken",
|
||||||
["https://storage.googleapis.com/chrome-for-testing-public/121.0.6167.85/linux64/chrome-linux64.zip", "chrome-linux64-121-0-6167-85"],
|
["https://storage.googleapis.com/chrome-for-testing-public/121.0.6167.85/linux64/chrome-linux64.zip", "chrome-linux64-121-0-6167-85"],
|
||||||
["https://storage.googleapis.com/chrome-for-testing-public/121.0.6167.85/linux64/chromedriver-linux64.zip", "chromedriver-linux64-121-0-6167-85"],
|
["https://storage.googleapis.com/chrome-for-testing-public/121.0.6167.85/linux64/chromedriver-linux64.zip", "chromedriver-linux64-121-0-6167-85"],
|
||||||
|
"https://github.com/astral-sh/uv/releases/download/0.9.16/uv-x86_64-unknown-linux-gnu.tar.gz",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@ -96,7 +96,7 @@ ragflow:
|
|||||||
infinity:
|
infinity:
|
||||||
image:
|
image:
|
||||||
repository: infiniflow/infinity
|
repository: infiniflow/infinity
|
||||||
tag: v0.6.10
|
tag: v0.6.11
|
||||||
pullPolicy: IfNotPresent
|
pullPolicy: IfNotPresent
|
||||||
pullSecrets: []
|
pullSecrets: []
|
||||||
storage:
|
storage:
|
||||||
|
|||||||
@ -5,7 +5,7 @@ description = "[RAGFlow](https://ragflow.io/) is an open-source RAG (Retrieval-A
|
|||||||
authors = [{ name = "Zhichang Yu", email = "yuzhichang@gmail.com" }]
|
authors = [{ name = "Zhichang Yu", email = "yuzhichang@gmail.com" }]
|
||||||
license-files = ["LICENSE"]
|
license-files = ["LICENSE"]
|
||||||
readme = "README.md"
|
readme = "README.md"
|
||||||
requires-python = ">=3.10,<3.13"
|
requires-python = ">=3.11,<3.15"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"datrie>=0.8.3,<0.9.0",
|
"datrie>=0.8.3,<0.9.0",
|
||||||
"akshare>=1.15.78,<2.0.0",
|
"akshare>=1.15.78,<2.0.0",
|
||||||
@ -49,7 +49,7 @@ dependencies = [
|
|||||||
"html-text==0.6.2",
|
"html-text==0.6.2",
|
||||||
"httpx[socks]>=0.28.1,<0.29.0",
|
"httpx[socks]>=0.28.1,<0.29.0",
|
||||||
"huggingface-hub>=0.25.0,<0.26.0",
|
"huggingface-hub>=0.25.0,<0.26.0",
|
||||||
"infinity-sdk==0.6.10",
|
"infinity-sdk==0.6.11",
|
||||||
"infinity-emb>=0.0.66,<0.0.67",
|
"infinity-emb>=0.0.66,<0.0.67",
|
||||||
"itsdangerous==2.1.2",
|
"itsdangerous==2.1.2",
|
||||||
"json-repair==0.35.0",
|
"json-repair==0.35.0",
|
||||||
@ -92,7 +92,7 @@ dependencies = [
|
|||||||
"ranx==0.3.20",
|
"ranx==0.3.20",
|
||||||
"readability-lxml==0.8.1",
|
"readability-lxml==0.8.1",
|
||||||
"valkey==6.0.2",
|
"valkey==6.0.2",
|
||||||
"requests==2.32.2",
|
"requests>=2.32.3,<3.0.0",
|
||||||
"replicate==0.31.0",
|
"replicate==0.31.0",
|
||||||
"roman-numbers==1.0.2",
|
"roman-numbers==1.0.2",
|
||||||
"ruamel-base==1.0.0",
|
"ruamel-base==1.0.0",
|
||||||
@ -101,7 +101,7 @@ dependencies = [
|
|||||||
"scikit-learn==1.5.0",
|
"scikit-learn==1.5.0",
|
||||||
"selenium==4.22.0",
|
"selenium==4.22.0",
|
||||||
"selenium-wire==5.1.0",
|
"selenium-wire==5.1.0",
|
||||||
"setuptools>=75.2.0,<76.0.0",
|
"setuptools>=78.1.1,<81.0.0",
|
||||||
"shapely==2.0.5",
|
"shapely==2.0.5",
|
||||||
"six==1.16.0",
|
"six==1.16.0",
|
||||||
"slack-sdk==3.37.0",
|
"slack-sdk==3.37.0",
|
||||||
|
|||||||
@ -443,6 +443,9 @@ class InfinityConnection(DocStoreConnection):
|
|||||||
del matchExpr.extra_options["similarity"]
|
del matchExpr.extra_options["similarity"]
|
||||||
logger.debug(f"INFINITY search MatchDenseExpr: {json.dumps(matchExpr.__dict__)}")
|
logger.debug(f"INFINITY search MatchDenseExpr: {json.dumps(matchExpr.__dict__)}")
|
||||||
elif isinstance(matchExpr, FusionExpr):
|
elif isinstance(matchExpr, FusionExpr):
|
||||||
|
if matchExpr.method == "weighted_sum":
|
||||||
|
# The default is "minmax" which gives a zero score for the last doc.
|
||||||
|
matchExpr.fusion_params["normalize"] = "atan"
|
||||||
logger.debug(f"INFINITY search FusionExpr: {json.dumps(matchExpr.__dict__)}")
|
logger.debug(f"INFINITY search FusionExpr: {json.dumps(matchExpr.__dict__)}")
|
||||||
|
|
||||||
order_by_expr_list = list()
|
order_by_expr_list = list()
|
||||||
|
|||||||
Reference in New Issue
Block a user