AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-06-01 15:18:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated Launch service from source (#856)

Browse Source 
### What problem does this PR solve?

Some nitpicking editorial updates.

### Type of change

- [x] Documentation Update
This commit is contained in:
writinwaters 2024-05-21 16:43:58 +08:00 committed by GitHub
parent 250119e03a
commit fe4b2e4670
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 81 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

151
README.md
View File

@ -191,88 +191,99 @@ $ chmod +x ./entrypoint.sh
$ docker compose up -d $ docker compose up -d
``` ```
## 🛠️ Launch Service from Source ## 🛠️ Launch service from source
To launch the service from source, please follow these steps: To launch the service from source:
1. Clone the repository 1. Clone the repository:
```bash
$ git clone https://github.com/infiniflow/ragflow.git
$ cd ragflow/
```
2. Create a virtual environment (ensure Anaconda or Miniconda is installed) ```bash
```bash $ git clone https://github.com/infiniflow/ragflow.git
$ conda create -n ragflow python=3.11.0 $ cd ragflow/
$ conda activate ragflow ```
$ pip install -r requirements.txt
```
If CUDA version is greater than 12.0, execute the following additional commands:
```bash
$ pip uninstall -y onnxruntime-gpu
$ pip install onnxruntime-gpu --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/
```
3. Copy the entry script and configure environment variables 2. Create a virtual environment, ensuring that Anaconda or Miniconda is installed:
```bash
$ cp docker/entrypoint.sh .
$ vi entrypoint.sh
```
Use the following commands to obtain the Python path and the ragflow project path:
```bash
$ which python
$ pwd
```
Set the output of `which python` as the value for `PY` and the output of `pwd` as the value for `PYTHONPATH`. ```bash
$ conda create -n ragflow python=3.11.0
$ conda activate ragflow
$ pip install -r requirements.txt
```
```bash
# If your CUDA version is higher than 12.0, run the following additional commands:
$ pip uninstall -y onnxruntime-gpu
$ pip install onnxruntime-gpu --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/
```
If `LD_LIBRARY_PATH` is already configured, it can be commented out. 3. Copy the entry script and configure environment variables:
```bash ```bash
# Adjust configurations according to your actual situation; the two export commands are newly added. # Get the Python path:
PY=${PY} $ which python
export PYTHONPATH=${PYTHONPATH} # Get the ragflow project path:
# Optional: Add Hugging Face mirror $ pwd
export HF_ENDPOINT=https://hf-mirror.com ```
```
```bash
$ cp docker/entrypoint.sh .
$ vi entrypoint.sh
```
4. Start the base services ```bash
```bash # Adjust configurations according to your actual situation (the following two export commands are newly added):
$ cd docker # - Assign the result of `which python` to `PY`.
$ docker compose -f docker-compose-base.yml up -d # - Assign the result of `pwd` to `PYTHONPATH`.
``` # - Comment out `LD_LIBRARY_PATH`, if it is configured.
# - Optional: Add Hugging Face mirror.
PY=${PY}
export PYTHONPATH=${PYTHONPATH}
export HF_ENDPOINT=https://hf-mirror.com
```
5. Check the configuration files 4. Launch the third-party services (MinIO, Elasticsearch, Redis, and MySQL):
Ensure that the settings in **docker/.env** match those in **conf/service_conf.yaml**. The IP addresses and ports for related services in **service_conf.yaml** should be changed to the local machine IP and ports exposed by the container.
6. Launch the service ```bash
```bash $ cd docker
$ chmod +x ./entrypoint.sh $ docker compose -f docker-compose-base.yml up -d
$ bash ./entrypoint.sh ```
```
7. Start the WebUI service 5. Check the configuration files, ensuring that:
```bash
$ cd web
$ npm install --registry=https://registry.npmmirror.com --force
$ vim .umirc.ts
# Modify proxy.target to 127.0.0.1:9380
$ npm run dev
```
8. Deploy the WebUI service - The settings in **docker/.env** match those in **conf/service_conf.yaml**.
```bash - The IP addresses and ports for related services in **service_conf.yaml** match the local machine IP and ports exposed by the container.
$ cd web
$ npm install --registry=https://registry.npmmirror.com --force 6. Launch the RAGFlow backend service:
$ umi build
$ mkdir -p /ragflow/web ```bash
$ cp -r dist /ragflow/web $ chmod +x ./entrypoint.sh
$ apt install nginx -y $ bash ./entrypoint.sh
$ cp ../docker/nginx/proxy.conf /etc/nginx ```
$ cp ../docker/nginx/nginx.conf /etc/nginx
$ cp ../docker/nginx/ragflow.conf /etc/nginx/conf.d 7. Launch the frontend service:
$ systemctl start nginx
``` ```bash
$ cd web
$ npm install --registry=https://registry.npmmirror.com --force
$ vim .umirc.ts
# Update proxy.target to 127.0.0.1:9380
$ npm run dev
```
8. Deploy the frontend service:
```bash
$ cd web
$ npm install --registry=https://registry.npmmirror.com --force
$ umi build
$ mkdir -p /ragflow/web
$ cp -r dist /ragflow/web
$ apt install nginx -y
$ cp ../docker/nginx/proxy.conf /etc/nginx
$ cp ../docker/nginx/nginx.conf /etc/nginx
$ cp ../docker/nginx/ragflow.conf /etc/nginx/conf.d
$ systemctl start nginx
```
## 📚 Documentation ## 📚 Documentation