mirror of
https://github.com/opendatalab/MinerU.git
synced 2026-09-21 12:42:22 +08:00
feat: update quick_usage.md to enhance document parsing instructions and add mineru-router usage details
This commit is contained in:
myhloli
@@ -8,12 +8,12 @@ export MINERU_MODEL_SOURCE=modelscope
|
||||
For more information about model source configuration and custom local model paths, please refer to the [Model Source Documentation](./model_source.md) in the documentation.
|
||||
|
||||
## Quick Usage via Command Line
|
||||
MinerU has built-in command line tools that allow users to quickly use MinerU for PDF parsing through the command line:
|
||||
MinerU has built-in command line tools that allow users to quickly use MinerU for document parsing through the command line:
|
||||
```bash
|
||||
mineru -p <input_path> -o <output_path>
|
||||
```
|
||||
> [!TIP]
|
||||
>- `<input_path>`: Local PDF/image file or directory
|
||||
>- `<input_path>`: Local `PDF` / image / `DOCX` file or directory
|
||||
>- `<output_path>`: Output directory
|
||||
>- Without `--api-url`, the CLI launches a temporary local `mineru-api`
|
||||
>- With `--api-url`, the CLI connects to an existing local or remote FastAPI service directly
|
||||
@@ -28,7 +28,6 @@ If you need to adjust parsing options through custom parameters, you can also ch
|
||||
|
||||
## Advanced Usage via API, WebUI, http-client/server
|
||||
|
||||
- Direct Python API calls: [Python Usage Example](https://github.com/opendatalab/MinerU/blob/master/demo/demo.py)
|
||||
- FastAPI calls:
|
||||
```bash
|
||||
mineru-api --host 0.0.0.0 --port 8000
|
||||
@@ -42,8 +41,10 @@ If you need to adjust parsing options through custom parameters, you can also ch
|
||||
>- Synchronous parsing endpoint: `POST /file_parse`
|
||||
>- Task query endpoints: `GET /tasks/{task_id}`, `GET /tasks/{task_id}/result`
|
||||
>- API outputs are controlled by the server and written to `./output` by default
|
||||
>- Uploads currently support `PDF`, image, and `DOCX` files
|
||||
>
|
||||
>`POST /tasks` returns immediately with a `task_id`. `POST /file_parse` uses the same task manager internally, waits for the task to finish, and then returns the final result synchronously.
|
||||
>When a task is waiting in the queue, both the submission response and task-status response may include `queued_ahead` to indicate how many tasks are ahead of it.
|
||||
>Tasks are tracked only in-process for a single `mineru-api` instance. Task status is not preserved across service restarts, `--reload`, or multi-process deployments.
|
||||
>Completed or failed tasks are retained for 24 hours by default, then their task state and output directory are cleaned automatically. After cleanup, task status and result endpoints return `404`.
|
||||
>Use `MINERU_API_TASK_RETENTION_SECONDS` and `MINERU_API_TASK_CLEANUP_INTERVAL_SECONDS` to adjust retention and cleanup polling intervals.
|
||||
@@ -70,6 +71,9 @@ If you need to adjust parsing options through custom parameters, you can also ch
|
||||
>curl http://127.0.0.1:8000/tasks/<task_id>/result
|
||||
>curl http://127.0.0.1:8000/health
|
||||
>```
|
||||
>
|
||||
>HTTP asynchronous call code example: [Python version](https://github.com/opendatalab/MinerU/blob/master/demo/demo.py)
|
||||
|
||||
- Start Gradio WebUI visual frontend:
|
||||
```bash
|
||||
mineru-gradio --server-name 0.0.0.0 --server-port 7860
|
||||
@@ -77,6 +81,18 @@ If you need to adjust parsing options through custom parameters, you can also ch
|
||||
>[!TIP]
|
||||
>
|
||||
>- Access `http://127.0.0.1:7860` in your browser to use the Gradio WebUI.
|
||||
>- Without `--api-url`, Gradio starts a reusable local `mineru-api`; with `--api-url`, it reuses an existing local or remote service.
|
||||
>- The WebUI currently accepts `PDF`, image, and `DOCX` uploads.
|
||||
|
||||
- Use `mineru-router` for multi-service / multi-GPU orchestration:
|
||||
```bash
|
||||
mineru-router --host 0.0.0.0 --port 8002 --local-gpus auto
|
||||
```
|
||||
>[!TIP]
|
||||
>
|
||||
>- `mineru-router` exposes the same `/health`, `/tasks`, `/file_parse`, `/tasks/{task_id}`, and `/tasks/{task_id}/result` interface set as `mineru-api`.
|
||||
>- Repeat `--upstream-url` to aggregate multiple existing `mineru-api` services, or use `--local-gpus` to launch local workers automatically.
|
||||
>- It is intended for advanced multi-service, multi-GPU, and unified-entry deployments.
|
||||
|
||||
- Using `http-client/server` method:
|
||||
```bash
|
||||
|
||||
@@ -8,12 +8,12 @@ export MINERU_MODEL_SOURCE=modelscope
|
||||
有关模型源配置和自定义本地模型路径的更多信息，请参考文档中的[模型源说明](./model_source.md)。
|
||||
|
||||
## 通过命令行快速使用
|
||||
MinerU内置了命令行工具，用户可以通过命令行快速使用MinerU进行PDF解析：
|
||||
MinerU内置了命令行工具，用户可以通过命令行快速使用MinerU进行文档解析：
|
||||
```bash
|
||||
mineru -p <input_path> -o <output_path>
|
||||
```
|
||||
> [!TIP]
|
||||
> - `<input_path>`：本地 PDF/图片 文件或目录
|
||||
> - `<input_path>`：本地 `PDF` / 图片 / `DOCX` 文件或目录
|
||||
> - `<output_path>`：输出目录
|
||||
> - 未传 `--api-url` 时，CLI 会自动拉起本地临时 `mineru-api`
|
||||
> - 传入 `--api-url` 时，CLI 会直连远端或已有本地 FastAPI 服务
|
||||
@@ -28,7 +28,6 @@ mineru -p <input_path> -o <output_path>
|
||||
|
||||
## 通过api、webui、http-client/server进阶使用
|
||||
|
||||
- 通过python api直接调用：[Python 调用示例](https://github.com/opendatalab/MinerU/blob/master/demo/demo.py)
|
||||
- 通过fast api方式调用：
|
||||
```bash
|
||||
mineru-api --host 0.0.0.0 --port 8000
|
||||
@@ -42,8 +41,10 @@ mineru -p <input_path> -o <output_path>
|
||||
>- 同步解析接口：`POST /file_parse`
|
||||
>- 任务查询接口：`GET /tasks/{task_id}`、`GET /tasks/{task_id}/result`
|
||||
>- API 输出目录由服务端固定控制，默认写入 `./output`
|
||||
>- 上传文件当前支持 `PDF`、图片与 `DOCX`
|
||||
>
|
||||
>`POST /tasks` 会立即返回 `task_id`；`POST /file_parse` 会在内部提交到同一个任务管理器，等待任务完成后同步返回最终结果。
|
||||
>当任务处于排队状态时，任务提交结果和状态查询结果中可能会返回 `queued_ahead` 字段，用于表示前方排队任务数。
|
||||
>任务为单进程、进程内状态实现，服务重启、`--reload` 热重载或多进程部署后不保证仍可查询历史任务状态。
|
||||
>默认任务完成或失败后保留 24 小时，随后自动清理任务状态和输出目录；清理后访问任务状态或结果会返回 `404`。
|
||||
>可通过环境变量 `MINERU_API_TASK_RETENTION_SECONDS` 和 `MINERU_API_TASK_CLEANUP_INTERVAL_SECONDS` 调整保留时长与清理轮询间隔。
|
||||
@@ -70,6 +71,9 @@ mineru -p <input_path> -o <output_path>
|
||||
>curl http://127.0.0.1:8000/tasks/<task_id>/result
|
||||
>curl http://127.0.0.1:8000/health
|
||||
>```
|
||||
>
|
||||
>http异步调用代码示例：[Python版本](https://github.com/opendatalab/MinerU/blob/master/demo/demo.py)
|
||||
|
||||
- 启动gradio webui 可视化前端：
|
||||
```bash
|
||||
mineru-gradio --server-name 0.0.0.0 --server-port 7860
|
||||
@@ -77,6 +81,18 @@ mineru -p <input_path> -o <output_path>
|
||||
>[!TIP]
|
||||
>
|
||||
>- 在浏览器中访问 `http://127.0.0.1:7860` 使用 Gradio WebUI。
|
||||
>- 未传 `--api-url` 时，Gradio 会自动拉起可复用的本地 `mineru-api`；传入 `--api-url` 时则会复用已有本地或远端服务。
|
||||
>- WebUI 当前支持上传 `PDF`、图片与 `DOCX` 文件。
|
||||
|
||||
- 通过 `mineru-router` 进行多服务 / 多 GPU 编排：
|
||||
```bash
|
||||
mineru-router --host 0.0.0.0 --port 8002 --local-gpus auto
|
||||
```
|
||||
>[!TIP]
|
||||
>
|
||||
>- `mineru-router` 对外暴露与 `mineru-api` 一致的 `/health`、`/tasks`、`/file_parse`、`/tasks/{task_id}`、`/tasks/{task_id}/result` 接口。
|
||||
>- 可重复使用 `--upstream-url` 聚合多个已有 `mineru-api` 服务，也可通过 `--local-gpus` 自动拉起本地 worker。
|
||||
>- 适用于多服务、多 GPU 和统一入口部署场景。
|
||||
|
||||
- 使用`http-client/server`方式调用：
|
||||
```bash
|
||||
|
||||
Reference in New Issue
Block a user