# Run RAGFlow with IPEX-LLM on Intel GPU
[RAGFlow](https://github.com/infiniflow/ragflow) is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding; by integrating it with [`ipex-llm`](https://github.com/intel-analytics/ipex-llm), users can now easily leverage local LLMs running on Intel GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max).
*See the demo of ragflow running Qwen2:7B on Intel Arc A770 below.*
[](https://llm-assets.readthedocs.io/en/latest/_images/ragflow-record.mp4)
## Quickstart
### 0 Prerequisites
- CPU >= 4 cores
- RAM >= 16 GB
- Disk >= 50 GB
- Docker >= 24.0.0 & Docker Compose >= v2.26.1
### 1. Install and Start `Ollama` Service on Intel GPU
Follow the steps in [Run Ollama with IPEX-LLM on Intel GPU Guide](./ollama_quickstart.md) to install and run Ollama on Intel GPU. Ensure that `ollama serve` is running correctly and can be accessed through a local URL (e.g., `https://127.0.0.1:11434`) or a remote URL (e.g., `http://your_ip:11434`).
> [!IMPORTANT]
> If the `RAGFlow` is not deployed on the same machine where Ollama is running (which means `RAGFlow` needs to connect to a remote Ollama service), you must configure the Ollama service to accept connections from any IP address. To achieve this, set or export the environment variable `OLLAMA_HOST=0.0.0.0` before executing the command `ollama serve`.
> [!TIP]
> If your local LLM is running on Intel Arc™ A-Series Graphics with Linux OS (Kernel 6.2), it is recommended to additionaly set the following environment variable for optimal performance before executing `ollama serve`:
>
> ```bash
> export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
> ```
### 2. Pull Model
Now we need to pull a model for RAG using Ollama. Here we use [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) model as an example. Open a new terminal window, run the following command to pull [`qwen2:latest`](https://ollama.com/library/qwen2).
- For **Linux users**:
```bash
export no_proxy=localhost,127.0.0.1
./ollama pull qwen2:latest
```
- For **Windows users**:
Please run the following command in Miniforge or Anaconda Prompt.
```cmd
set no_proxy=localhost,127.0.0.1
ollama pull qwen2:latest
```
> [!TIP]
> Besides Qwen2, there are other LLM models you might want to explore, such as Llama3, Phi3, Mistral, etc. You can find all available models in the [Ollama model library](https://ollama.com/library). Simply search for the model, pull it in a similar manner, and give it a try.
### 3. Start `RAGFlow` Service
> [!NOTE]
> The steps in section 3 is verified on Linux system only.
#### 3.1 Download `RAGFlow`
You can either clone the repository or download the source zip from [github](https://github.com/infiniflow/ragflow/archive/refs/heads/main.zip):
```bash
$ git clone https://github.com/infiniflow/ragflow.git
```
#### 3.2 Environment Settings
Ensure `vm.max_map_count` is set to at least 262144. To check the current value of `vm.max_map_count`, use:
```bash
$ sysctl vm.max_map_count
```
##### Changing `vm.max_map_count`
To set the value temporarily, use:
```bash
$ sudo sysctl -w vm.max_map_count=262144
```
To make the change permanent and ensure it persists after a reboot, add or update the following line in `/etc/sysctl.conf`:
```bash
vm.max_map_count=262144
```
### 3.3 Start the `RAGFlow` server using Docker
Build the pre-built Docker images and start up the server:
> [!NOTE]
> Running the following commands automatically downloads the *dev* version RAGFlow Docker image. To download and run a specified Docker version, update `RAGFLOW_VERSION` in **docker/.env** to the intended version, for example `RAGFLOW_VERSION=v0.7.0`, before running the following commands.
```bash
$ export no_proxy=localhost,127.0.0.1
$ cd ragflow/docker
$ chmod +x ./entrypoint.sh
$ docker compose up -d
```
> [!NOTE]
> The core image is about 9 GB in size and may take a while to load.
Check the server status after having the server up and running:
```bash
$ docker logs -f ragflow-server
```
Upon successful deployment, you will see logs in the terminal similar to the following:
```bash
____ ______ __
/ __ \ ____ _ ____ _ / ____// /____ _ __
/ /_/ // __ `// __ `// /_ / // __ \| | /| / /
/ _, _// /_/ // /_/ // __/ / // /_/ /| |/ |/ /
/_/ |_| \__,_/ \__, //_/ /_/ \____/ |__/|__/
/____/
* Running on all addresses (0.0.0.0)
* Running on http://127.0.0.1:9380
* Running on http://x.x.x.x:9380
INFO:werkzeug:Press CTRL+C to quit
```
You can now open a browser and access the RAGflow web portal. With the default settings, simply enter `http://IP_OF_YOUR_MACHINE` (without the port number), as the default HTTP serving port `80` can be omitted. If RAGflow is deployed on the same machine as your browser, you can also access the web portal at `http://127.0.0.1` or `http://localhost`.
### 4. Using `RAGFlow`
> [!NOTE]
> For detailed information about how to use RAGFlow, visit the README of [RAGFlow official repository](https://github.com/infiniflow/ragflow).
#### Log-in
If this is your first time using RAGFlow, you will need to register. After registering, log in with your new account to access the portal.
#### Configure `Ollama` service URL
Access the Ollama settings through **Settings -> Model Providers** in the menu. Fill out the **Base URL**, and then click the **OK** button at the bottom.
If the connection is successful, you will see the model listed down **Show more models** as illustrated below.
> [!NOTE]
> If you want to use an Ollama server hosted at a different URL, simply update the **Ollama Base URL** to the new URL and press the **OK** button again to re-confirm the connection to Ollama.
#### Create Knowledge Base
Go to **Knowledge Base** by clicking on **Knowledge Base** in the top bar. Click the **+Create knowledge base** button on the right. You will be prompted to input a name for the knowledge base.
#### Edit Knowledge Base
After entering a name, you will be directed to edit the knowledge base. Click on **Dataset** on the left, then click **+ Add file -> Local files**. Upload your file in the pop-up window and click **OK**.
After the upload is successful, you will see a new record in the dataset. The _**Parsing Status**_ column will show `UNSTARTED`. Click the green start button in the _**Action**_ column to begin file parsing. Once parsing is finished, the _**Parsing Status**_ column will change to **SUCCESS**.
Next, go to **Configuration** on the left menu and click **Save** at the bottom to save the changes.
#### Chat with the Model
Start new conversations by clicking **Chat** in the top navbar.
On the left side, create a conversation by clicking **Create an Assistant**. Under **Assistant Setting**, give it a name and select your knowledge bases.
Next, go to **Model Setting**, choose your model added by Ollama, and disable the **Max Tokens** toggle. Finally, click **OK** to start.
> [!TIP]
> Enabling the **Max Tokens** toggle may result in very short answers.
Input your questions into the **Message Resume Assistant** textbox at the bottom, and click the button on the right to get responses.
#### Exit
To shut down the RAGFlow server, use **Ctrl+C** in the terminal where the Ragflow server is runing, then close your browser tab.
