pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-23 15:06:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refa: only support MinerU-API now (#11977)

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

Only support MinerU-API now, still need to complete frontend for
pipeline to allow the configuration of MinerU options.

### Type of change

- [x] Refactoring
This commit is contained in:
Yongteng Lei
2025-12-17 12:58:48 +08:00
committed by GitHub
parent 5e05f43c3d
commit 03f9be7cbb
19 changed files with 273 additions and 624 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
docs/faq.mdx
View File

@ -493,66 +493,37 @@ See [here](./guides/agent/best_practices/accelerate_agent_question_answering.md)
### How to use MinerU to parse PDF documents?
MinerU PDF document parsing is available starting from v0.22.0. RAGFlow supports MinerU (>= 2.6.3) as an optional PDF parser with multiple backends. RAGFlow acts only as a client for MinerU, calling it to parse documents, reading the output files, and ingesting the parsed content. To use this feature, follow these steps:
1. Prepare MinerU
```bash
# docker/.env
...
USE_MINERU=true
...
```
Enabling `USE_MINERU=true` will internally perform the same setup as the manual configuration (including setting the MinerU executable path and related environment variables).
2. Start RAGFlow with MinerU enabled:
- **Source deployment** – in the RAGFlow repo, continue to start the backend service:
```bash
...
source .venv/bin/activate
export PYTHONPATH=$(pwd)
bash docker/launch_backend_service.sh
```
- **Docker deployment** – after setting `USE_MINERU=true`, restart the containers so that the new settings take effect:
```bash
# in RAGFlow repo
docker compose -f docker/docker-compose.yml restart
```
MinerU PDF document parsing is available starting from v0.22.0. RAGFlow works only as a remote client to MinerU (>= 2.6.3) and does not install or execute MinerU locally. To use this feature:
1. Prepare a reachable MinerU API service (for example, the FastAPI server provided by MinerU).
2. Configure RAGFlow with remote MinerU settings (environment variables or UI model provider):
- `MINERU_APISERVER`: MinerU API endpoint, for example `http://mineru-host:8886`.
- `MINERU_BACKEND`: MinerU backend, defaults to `pipeline` (supports `vlm-http-client`, `vlm-transformers`, `vlm-vllm-engine`, `vlm-mlx-engine`, `vlm-vllm-async-engine`, `vlm-lmdeploy-engine`).
- `MINERU_SERVER_URL`: (optional) For `vlm-http-client`, the downstream vLLM HTTP server, for example `http://vllm-host:30000`.
- `MINERU_OUTPUT_DIR`: (optional) Local directory to store MinerU API outputs (zip/JSON) before ingestion.
- `MINERU_DELETE_OUTPUT`: Whether to delete temporary output when a temp dir is used (`1` deletes temp outputs; set `0` to keep).
3. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown (which supports PDF parsing), and select **MinerU** in **PDF parser**.
4. If you use a custom ingestion pipeline instead, you must also complete the first two steps before selecting **MinerU** in the **Parsing method** section of the **Parser** component.
4. If you use a custom ingestion pipeline instead, provide the same MinerU settings and select **MinerU** in the **Parsing method** section of the **Parser** component.
---
### How to configure MinerU-specific settings?
The table below summarizes the most frequently used MinerU environment variables:
The table below summarizes the most frequently used MinerU environment variables for remote MinerU:
| Environment variable | Description | Default | Example |
| ---------------------- | ---------------------------------- | ----------------------------------- | ----------------------------------------------------------------------------------------------- |
| `MINERU_EXECUTABLE` | Path to the local MinerU executable | `mineru` | `MINERU_EXECUTABLE=/home/ragflow/uv_tools/.venv/bin/mineru` |
| `MINERU_DELETE_OUTPUT` | Whether to delete MinerU output directory | `1` (do **not** keep the output directory) | `MINERU_DELETE_OUTPUT=0` |
| `MINERU_APISERVER` | URL of the MinerU API service | _unset_ | `MINERU_APISERVER=http://your-mineru-server:8886` |
| `MINERU_BACKEND` | MinerU parsing backend | `pipeline` | `MINERU_BACKEND=pipeline\|vlm-transformers\|vlm-vllm-engine\|vlm-mlx-engine\|vlm-vllm-async-engine\|vlm-http-client` |
| `MINERU_SERVER_URL` | URL of remote vLLM server (for `vlm-http-client`) | _unset_ | `MINERU_SERVER_URL=http://your-vllm-server-ip:30000` |
| `MINERU_OUTPUT_DIR` | Directory for MinerU output files | System-defined temporary directory | `MINERU_OUTPUT_DIR=/home/ragflow/mineru/output` |
| `MINERU_BACKEND` | MinerU parsing backend | `pipeline` | `MINERU_BACKEND=pipeline\|vlm-transformers\|vlm-vllm-engine\|vlm-http-client` |
| `MINERU_SERVER_URL` | URL of remote vLLM server (only for `vlm-http-client` backend) | _unset_ | `MINERU_SERVER_URL=http://your-vllm-server-ip:30000` |
| `MINERU_APISERVER` | URL of remote MinerU service used as the parser (instead of local MinerU) | _unset_ | `MINERU_APISERVER=http://your-mineru-server:port` |
| `MINERU_DELETE_OUTPUT` | Whether to delete MinerU output directory when a temp dir is used | `1` (delete temp output) | `MINERU_DELETE_OUTPUT=0` |
1. Set `MINERU_EXECUTABLE` to the path to the MinerU executable if the default `mineru` is not on `PATH`.
2. Set `MINERU_DELETE_OUTPUT` to `0` to keep MinerU's output. (Default: `1`, which deletes temporary output.)
3. Set `MINERU_OUTPUT_DIR` to specify the output directory for MinerU; otherwise, a system temp directory is used.
4. Set `MINERU_BACKEND` to specify a parsing backend:
- `"pipeline"` (default): The traditional multimodel pipeline.
- `"vlm-transformers"`: A vision-language model using HuggingFace Transformers.
- `"vlm-vllm-engine"`: A vision-language model using a local vLLM engine (requires a local GPU).
- `"vlm-http-client"`: A vision-language model via HTTP client to a remote vLLM server (RAGFlow only requires CPU).
5. If using the `"vlm-http-client"` backend, you must also set `MINERU_SERVER_URL` to your vLLM server's URL.
6. If configuring RAGFlow to call a *remote* MinerU service, set `MINERU_APISERVER` to the MinerU server's URL.
1. Set `MINERU_APISERVER` to point RAGFlow to your MinerU API server.
2. Set `MINERU_BACKEND` to specify a parsing backend.
3. If using the `"vlm-http-client"` backend, set `MINERU_SERVER_URL` to your vLLM server's URL. MinerU API expects `backend=vlm-http-client` and `server_url=http://<server>:30000` in the request body.
4. Set `MINERU_OUTPUT_DIR` to specify where RAGFlow stores MinerU API output; otherwise, a system temp directory is used.
5. Set `MINERU_DELETE_OUTPUT` to `0` to keep MinerU's temp output (useful for debugging).
:::tip NOTE
For information about other environment variables natively supported by MinerU, see [here](https://opendatalab.github.io/MinerU/usage/cli_tools/#environment-variables-description).
@ -562,21 +533,16 @@ For information about other environment variables natively supported by MinerU,
### How to use MinerU with a vLLM server for document parsing?
RAGFlow supports MinerU's `vlm-http-client` backend, enabling you to delegate document parsing tasks to a remote vLLM server. With this configuration, RAGFlow will connect to your remote vLLM server as a client and use its powerful GPU resources for document parsing. This significantly improves performance for parsing complex documents while reducing the resources required on your RAGFlow server. To configure MinerU with a vLLM server:
RAGFlow supports MinerU's `vlm-http-client` backend, enabling you to delegate document parsing tasks to a remote vLLM server while calling MinerU via HTTP. To configure:
1. Set up a vLLM server running MinerU:
```bash
mineru-vllm-server --port 30000
```
2. Configure the following environment variables in your **docker/.env** file (or your shell if running from source):
- `MINERU_EXECUTABLE=/home/ragflow/uv_tools/.venv/bin/mineru` (or the path to your MinerU executable)
1. Ensure a MinerU API service is reachable (for example `http://mineru-host:8886`).
2. Set up or point to a vLLM HTTP server (for example `http://vllm-host:30000`).
3. Configure the following in your **docker/.env** file (or your shell if running from source):
- `MINERU_APISERVER=http://mineru-host:8886`
- `MINERU_BACKEND="vlm-http-client"`
- `MINERU_SERVER_URL="http://your-vllm-server-ip:30000"`
3. Complete the rest of the standard MinerU setup steps as described [here](#how-to-configure-mineru-specific-settings).
- `MINERU_SERVER_URL="http://vllm-host:30000"`
MinerU API calls expect `backend=vlm-http-client` and `server_url=http://<server>:30000` in the request body.
4. Configure `MINERU_OUTPUT_DIR` / `MINERU_DELETE_OUTPUT` as desired to manage the returned zip/JSON before ingestion.
:::tip NOTE
When using the `vlm-http-client` backend, the RAGFlow server requires no GPU, only network connectivity. This enables cost-effective distributed deployment with multiple RAGFlow instances sharing one remote vLLM server.

61
docs/guides/agent/agent_component_reference/parser.md
View File

@ -40,56 +40,21 @@ The output of a PDF parser is `json`. In the PDF parser, you select the parsing
- A third-party visual model from a specific model provider.
:::danger IMPORTANT
MinerU PDF document parsing is available starting from v0.22.0. RAGFlow supports MinerU (>= 2.6.3) as an optional PDF parser with multiple backends. RAGFlow acts only as a client for MinerU, calling it to parse documents, reading the output files, and ingesting the parsed content. To use this feature, follow these steps:
MinerU PDF document parsing is available starting from v0.22.0. RAGFlow supports MinerU (>= 2.6.3) as an optional PDF parser with multiple backends. RAGFlow acts only as a **remote client** for MinerU, calling the MinerU API to parse documents, reading the returned output files, and ingesting the parsed content. To use this feature:
:::
1. Prepare MinerU:
1. Prepare a reachable MinerU API service (FastAPI server).
2. Configure RAGFlow with the remote MinerU settings (env or UI model provider):
- `MINERU_APISERVER`: MinerU API endpoint, for example `http://mineru-host:8886`.
- `MINERU_BACKEND`: MinerU backend, defaults to `pipeline` (supports `vlm-http-client`, `vlm-transformers`, `vlm-vllm-engine`, `vlm-mlx-engine`, `vlm-vllm-async-engine`, `vlm-lmdeploy-engine`).
- `MINERU_SERVER_URL`: (optional) For `vlm-http-client`, the downstream vLLM HTTP server, for example `http://vllm-host:30000`.
- `MINERU_OUTPUT_DIR`: (optional) Local directory to store MinerU API outputs (zip/JSON) before ingestion.
- `MINERU_DELETE_OUTPUT`: Whether to delete temporary output when a temp dir is used (`1` deletes temp outputs; set `0` to keep).
3. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown, which supports PDF parsing, and select **MinerU** in **PDF parser**.
4. If you use a custom ingestion pipeline instead, provide the same MinerU settings and select **MinerU** in the **Parsing method** section of the **Parser** component.
- **If you deploy RAGFlow from source**, install MinerU into an isolated virtual environment (recommended path: `$HOME/uv_tools`):
```bash
mkdir -p "$HOME/uv_tools"
cd "$HOME/uv_tools"
uv venv .venv
source .venv/bin/activate
uv pip install -U "mineru[core]" -i https://mirrors.aliyun.com/pypi/simple
# or
# uv pip install -U "mineru[all]" -i https://mirrors.aliyun.com/pypi/simple
```
- **If you deploy RAGFlow with Docker**, you usually only need to turn on MinerU support in `docker/.env`:
```bash
# docker/.env
...
USE_MINERU=true
...
```
Enabling `USE_MINERU=true` will internally perform the same setup as the manual configuration (including setting the MinerU executable path and related environment variables). You only need the manual installation above if you are running from source or want full control over the MinerU installation.
2. Start RAGFlow with MinerU enabled:
- **Source deployment** – in the RAGFlow repo, export the key MinerU-related variables and start the backend service:
```bash
# in RAGFlow repo
export MINERU_EXECUTABLE="$HOME/uv_tools/.venv/bin/mineru"
export MINERU_DELETE_OUTPUT=0 # keep output directory
export MINERU_BACKEND=pipeline # or another backend you prefer
source .venv/bin/activate
export PYTHONPATH=$(pwd)
bash docker/launch_backend_service.sh
```
- **Docker deployment** – after setting `USE_MINERU=true`, restart the containers so that the new settings take effect:
```bash
# in RAGFlow repo
docker compose -f docker/docker-compose.yml restart
```
3. Restart the ragflow-server.
:::note
All MinerU environment variables are optional. If set, RAGFlow will auto-provision a MinerU OCR model for the tenant on first use with these values. To avoid auto-provisioning, configure MinerU solely through the UI and leave the env vars unset.
:::
:::caution WARNING

88
docs/guides/dataset/select_pdf_parser.md
View File

@ -16,13 +16,13 @@ RAGFlow isn't one-size-fits-all. It is built for flexibility and supports deeper
## Prerequisites
- The PDF parser dropdown menu appears only when you select a chunking method compatible with PDFs, including:
- **General**
- **Manual**
- **Paper**
- **Book**
- **Laws**
- **Presentation**
- **One**
- **General**
- **Manual**
- **Paper**
- **Book**
- **Laws**
- **Presentation**
- **One**
- To use a third-party visual model for parsing PDFs, ensure you have set a default VLM under **Set default models** on the **Model providers** page.
## Quickstart
@ -33,65 +33,28 @@ RAGFlow isn't one-size-fits-all. It is built for flexibility and supports deeper
2. Select the option that works best with your scenario:
- DeepDoc: (Default) The default visual model performing OCR, TSR, and DLR tasks on PDFs, but can be time-consuming.
- Naive: Skip OCR, TSR, and DLR tasks if *all* your PDFs are plain text.
- [MinerU](https://github.com/opendatalab/MinerU): (Experimental) An open-source tool that converts PDF into machine-readable formats.
- [Docling](https://github.com/docling-project/docling): (Experimental) An open-source document processing tool for gen AI.
- A third-party visual model from a specific model provider.
- DeepDoc: (Default) The default visual model performing OCR, TSR, and DLR tasks on PDFs, but can be time-consuming.
- Naive: Skip OCR, TSR, and DLR tasks if _all_ your PDFs are plain text.
- [MinerU](https://github.com/opendatalab/MinerU): (Experimental) An open-source tool that converts PDF into machine-readable formats.
- [Docling](https://github.com/docling-project/docling): (Experimental) An open-source document processing tool for gen AI.
- A third-party visual model from a specific model provider.
:::danger IMPORTANT
MinerU PDF document parsing is available starting from v0.22.0. RAGFlow supports MinerU (>= 2.6.3) as an optional PDF parser with multiple backends. RAGFlow acts only as a client for MinerU, calling it to parse documents, reading the output files, and ingesting the parsed content. To use this feature, follow these steps:
MinerU PDF document parsing is available starting from v0.22.0. RAGFlow supports MinerU (>= 2.6.3) as an optional PDF parser with multiple backends. RAGFlow acts only as a **remote client** for MinerU, calling the MinerU API to parse documents, reading the returned output files, and ingesting the parsed content. To use this feature:
1. Prepare MinerU:
1. Prepare a reachable MinerU API service (FastAPI server).
2. Configure RAGFlow with the remote MinerU settings (env or UI model provider):
- `MINERU_APISERVER`: MinerU API endpoint, for example `http://mineru-host:8886`.
- `MINERU_BACKEND`: MinerU backend, defaults to `pipeline` (supports `vlm-http-client`, `vlm-transformers`, `vlm-vllm-engine`, `vlm-mlx-engine`, `vlm-vllm-async-engine`).
- `MINERU_SERVER_URL`: (optional) For `vlm-http-client`, the downstream vLLM HTTP server, for example `http://vllm-host:30000`.
- `MINERU_OUTPUT_DIR`: (optional) Local directory to store MinerU API outputs (zip/JSON) before ingestion.
- `MINERU_DELETE_OUTPUT`: Whether to delete temporary output when a temp dir is used (`1` deletes temp outputs; set `0` to keep).
3. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown, which supports PDF parsing, and select **MinerU** in **PDF parser**.
4. If you use a custom ingestion pipeline instead, provide the same MinerU settings and select **MinerU** in the **Parsing method** section of the **Parser** component.
:::
- **If you deploy RAGFlow from source**, install MinerU into an isolated virtual environment (recommended path: `$HOME/uv_tools`):
```bash
mkdir -p "$HOME/uv_tools"
cd "$HOME/uv_tools"
uv venv .venv
source .venv/bin/activate
uv pip install -U "mineru[core]" -i https://mirrors.aliyun.com/pypi/simple
# or
# uv pip install -U "mineru[all]" -i https://mirrors.aliyun.com/pypi/simple
```
- **If you deploy RAGFlow with Docker**, you usually only need to turn on MinerU support in `docker/.env`:
```bash
# docker/.env
...
USE_MINERU=true
...
```
Enabling `USE_MINERU=true` will internally perform the same setup as the manual configuration (including setting the MinerU executable path and related environment variables). You only need the manual installation above if you are running from source or want full control over the MinerU installation.
2. Start RAGFlow with MinerU enabled:
- **Source deployment** – in the RAGFlow repo, export the key MinerU-related variables and start the backend service:
```bash
# in RAGFlow repo
export MINERU_EXECUTABLE="$HOME/uv_tools/.venv/bin/mineru"
export MINERU_DELETE_OUTPUT=0 # keep output directory
export MINERU_BACKEND=pipeline # or another backend you prefer
source .venv/bin/activate
export PYTHONPATH=$(pwd)
bash docker/launch_backend_service.sh
```
- **Docker deployment** – after setting `USE_MINERU=true`, restart the containers so that the new settings take effect:
```bash
# in RAGFlow repo
docker compose -f docker/docker-compose.yml restart
```
3. Restart the ragflow-server.
4. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown, which supports PDF parsing, and select **MinerU** in **PDF parser**.
5. If you use a custom ingestion pipeline instead, you must also complete the first three steps before selecting **MinerU** in the **Parsing method** section of the **Parser** component.
:::note
All MinerU environment variables are optional. When they are set, RAGFlow will auto-create a MinerU OCR model for a tenant on first use using these values. If you do not want this auto-provisioning, configure MinerU only through the UI and leave the env vars unset.
:::
:::caution WARNING
@ -107,4 +70,3 @@ Use a visual model to extract data if your PDFs contain formatted or image-based
### Can I select a visual model to parse my DOCX files?
No, you cannot. This dropdown menu is for PDFs only. To use this feature, convert your DOCX files to PDF first.