PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios.
> For Windows users, please use WSL or a Docker container.
## 2. Quick Start
PaddleOCR-VL supports two usage methods: CLI command line and Python API. The CLI command line method is simpler and suitable for quickly verifying functionality, while the Python API method is more flexible and suitable for integration into existing projects.
### 2.1 Command Line Usage
Run a single command to quickly test the PaddleOCR-VL ：
For example, the local path of an image file or PDF file: <code>/root/data/img.jpg</code>;<b>Such as a URL link</b>, for example, the network URL of an image file or PDF file:<ahref="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/demo_paper.png">Example</a>;<b>Such as a local directory</b>, which should contain the images to be predicted, for example, the local path: <code>/root/data/</code>(Currently, prediction for directories containing PDF files is not supported. PDF files need to be specified with a specific file path).</td>
<td>Expansion coefficient for the detection boxes of the layout area detection model.Any floating-point number greater than <code>0</code>. If not set, the initialized default value will be used.</td>
<td>Merging mode for the detection boxes output by the model in layout detection.
<ul>
<li><b>large</b> when set to large, it means that among the detection boxes output by the model, for overlapping and contained boxes, only the outermost largest box is retained, and the overlapping inner boxes are deleted;</li>
<li><b>small</b>, when set to small, it means that among the detection boxes output by the model, for overlapping and contained boxes, only the innermost contained small box is retained, and the overlapping outer boxes are deleted;</li>
<li><b>union</b>,no filtering is performed on the boxes, and both inner and outer boxes are retained;</li></ul>
If not set, the initialized parameter value will be used.
<td>Whether to load and use the document orientation classification module. If not set, the initialized default value will be used, which is initialized to<code>False</code>.</td>
<td>Whether to load and use the text image rectification module. If not set, the initialized default value will be used, which is initialized to <code>False.</td>
<td>Whether to load and use the layout area detection and ranking module. If not set, the initialized default value will be used, which is initialized to <code>True</code>.</td>
<td>Whether to use the chart parsing function. If not set, the initialized default value will be used, which is initialized to <code>False</code>.</td>
<td>Controls whether to format the <code>block_content</code> content within as Markdown. If not set, the initialized default value will be used, which defaults to initialization as<code>False</code>.</td>
<td>Used to control whether to enable internal queues. When set to <code>True</code>, data loading (such as rendering PDF pages as images), layout detection model processing, and VLM inference will be executed asynchronously in separate threads, with data passed through queues, thereby improving efficiency. This approach is particularly efficient for PDF documents with a large number of pages or directories containing a large number of images or PDF files.</td>
<li><b>CPU</b>: For example,<code>cpu</code> indicates using the CPU for inference;</li>
<li><b>GPU</b>: For example,<code>gpu:0</code> indicates using the first GPU for inference;</li>
<li><b>NPU</b>: For example,<code>npu:0</code> indicates using the first NPU for inference;</li>
<li><b>XPU</b>: For example,<code>xpu:0</code> indicates using the first XPU for inference;</li>
<li><b>MLU</b>: For example,<code>mlu:0</code> indicates using the first MLU for inference;</li>
<li><b>DCU</b>: For example,<code>dcu:0</code> indicates using the first DCU for inference;</li>
</ul>If not set, the initialized default value will be used. During initialization, the local GPU device 0 will be used preferentially. If it is not available, the CPU device will be used.</td>
<td>Whether to enable the TensorRT subgraph engine of Paddle Inference. If the model does not support acceleration via TensorRT, acceleration will not be used even if this flag is set.<br/>For PaddlePaddle version with CUDA 11.8, the compatible TensorRT version is 8.x (x&gt;=6). It is recommended to install TensorRT 8.6.1.6.<br/>
<td>Whether to enable MKL-DNN accelerated inference. If MKL-DNN is not available or the model does not support acceleration via MKL-DNN, acceleration will not be used even if this flag is set.</td>
<b>Note: </b> The default model for the production line is relatively large, which may result in slower inference speed. It is recommended to use [inference acceleration frameworks to enhance VLM inference performance](#31-starting-the-vlm-inference-service) for faster inference.
The command line method is for quick testing and visualization. In actual projects, you usually need to integrate the model via code. You can perform pipeline inference with just a few lines of code as shown below:
```python
from paddleocr import PaddleOCRVL
pipeline = PaddleOCRVL()
# pipeline = PaddleOCRVL(use_doc_orientation_classify=True) # Use use_doc_orientation_classify to enable/disable document orientation classification model
# pipeline = PaddleOCRVL(use_doc_unwarping=True) # Use use_doc_unwarping to enable/disable document unwarping module
# pipeline = PaddleOCRVL(use_layout_detection=False) # Use use_layout_detection to enable/disable layout detection module
res.print() ## Print the structured prediction output
res.save_to_json(save_path="output") ## Save the current image's structured result in JSON format
res.save_to_markdown(save_path="output") ## Save the current image's result in Markdown format
```
For PDF files, each page will be processed individually and generate a separate Markdown file. If you want to convert the entire PDF to a single Markdown file, use the following method:
- In the example code, the parameters `use_doc_orientation_classify` and `use_doc_unwarping` are all set to `False` by default. These indicate that document orientation classification and document image unwarping are disabled. You can manually set them to `True` if needed.
The above Python script performs the following steps:
<details><summary>(1) Instantiate the production line object. Specific parameter descriptions are as follows:</summary>
<td>Whether to use post-processing NMS for layout detection. If set to <code>None</code>, the parameter value initialized by the production line will be used.</td>
Expansion coefficient for the detection box of the layout area detection model.
<ul>
<li><b>float</b>: Any floating-point number greater than <code>0</code></li>
<li><b>Tuple[float,float]</b>: The respective expansion coefficients in the horizontal and vertical directions;</li>
<li><b>dict</b>: where the key of the dict is of <b>int</b> type, representing <code>cls_id</code>, and the value is of</code>tuple <code>type, such as</code>{0: (1.1, 2.0)}, indicating that the center of the detection box for class 0 output by the model remains unchanged, with the width expanded by 1.1 times and the height expanded by 2.0 times;</li>
<li><b>None</b>: If set to <code>None</code>, the parameter value initialized by the production line will be used.</li>
<td>Merging mode for the detection boxes output by the model in layout detection.
<ul>
<li><b>large</b> when set to large, it means that among the detection boxes output by the model, for overlapping and contained boxes, only the outermost largest box is retained, and the overlapping inner boxes are deleted;</li>
<li><b>small</b>, when set to small, it means that among the detection boxes output by the model, for overlapping and contained boxes, only the innermost contained small box is retained, and the overlapping outer boxes are deleted;</li>
<li><b>union</b>,no filtering is performed on the boxes, and both inner and outer boxes are retained;</li></ul>
If not set, the initialized parameter value will be used.
<td>Whether to load and use the document orientation classification module. If not set, the initialized default value will be used, which is initialized to<code>False</code>.</td>
<td>Whether to load and use the text image rectification module. If not set, the initialized default value will be used, which is initialized to <code>False.</td>
<td>Whether to load and use the layout area detection and ranking module. If not set, the initialized default value will be used, which is initialized to <code>True</code>.</td>
<td>Whether to use the chart parsing function. If not set, the initialized default value will be used, which is initialized to <code>False</code>.</td>
<td>Controls whether to format the <code>block_content</code> content within as Markdown. If not set, the initialized default value will be used, which defaults to initialization as<code>False</code>.</td>
<td>The device used for inference. Supports specifying specific card numbers:<ul>
<li><b>CPU</b>: For example,<code>cpu</code> indicates using the CPU for inference;</li>
<li><b>GPU</b>: For example,<code>gpu:0</code> indicates using the first GPU for inference;</li>
<li><b>NPU</b>: For example,<code>npu:0</code> indicates using the first NPU for inference;</li>
<li><b>XPU</b>: For example,<code>xpu:0</code> indicates using the first XPU for inference;</li>
<li><b>MLU</b>: For example,<code>mlu:0</code> indicates using the first MLU for inference;</li>
<li><b>DCU</b>: For example,<code>dcu:0</code> indicates using the first DCU for inference;</li>
</ul>If not set, the initialized default value will be used. During initialization, the local GPU device 0 will be used preferentially. If it is not available, the CPU device will be used.</td>
<td>Whether to enable the TensorRT subgraph engine of Paddle Inference. If the model does not support acceleration via TensorRT, acceleration will not be used even if this flag is set.<br/>For PaddlePaddle version with CUDA 11.8, the compatible TensorRT version is 8.x (x&gt;=6). It is recommended to install TensorRT 8.6.1.6.<br/>
<td>Whether to enable MKL-DNN accelerated inference. If MKL-DNN is not available or the model does not support acceleration via MKL-DNN, acceleration will not be used even if this flag is set.</td>
<details><summary>(2) Call the <code>predict()</code>method of the PaddleOCR-VL production line object for inference prediction. This method will return a list of results. Additionally, the production line also provides the <code>predict_iter()</code>Method. The two are completely consistent in terms of parameter acceptance and result return. The difference lies in that <code>predict_iter()</code>returns a <code>generator</code>, which can process and obtain prediction results step by step. It is suitable for scenarios involving large datasets or where memory conservation is desired. You can choose either of these two methods based on actual needs. Below are the parameters of the <code>predict()</code>method and their descriptions:</summary>
<li><b>Python Var</b>: such as <code>numpy.ndarray</code> representing image data</li>
<li><b>str</b>: such as the local path of an image file or PDF file: <code>/root/data/img.jpg</code>;<b>such as a URL link</b>, such as the network URL of an image file or PDF file:<ahref="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/demo_paper.png">Example</a>;<b>such as a local directory</b>, which should contain the images to be predicted, such as the local path: <code>/root/data/</code>(Currently, prediction for directories containing PDF files is not supported. PDF files need to be specified with a specific file path)</li>
<li><b>list</b>: List elements should be of the aforementioned data types, such as <code>[numpy.ndarray, numpy.ndarray]</code>, <code>["/root/data/img1.jpg", "/root/data/img2.jpg"]</code>, <code>["/root/data1", "/root/data2"].</code></li>
<td>Whether to use the document orientation classification module during inference. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<td>Whether to use the text image rectification module during inference. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<td>Whether to use the layout region detection and sorting module during inference. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<td>Whether to use the chart parsing module during inference. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<td>The parameter meaning is basically the same as the instantiation parameter. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<td>The parameter meaning is basically the same as the instantiation parameter. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<td>The parameter meaning is basically the same as the instantiation parameter. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<td>The parameter meaning is basically the same as the instantiation parameter. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<td>Used to control whether to enable internal queues. When set to <code>True</code>, data loading (such as rendering PDF pages as images), layout detection model processing, and VLM inference will be executed asynchronously in separate threads, with data passed through queues, thereby improving efficiency. This approach is particularly efficient for PDF documents with many pages or directories containing a large number of images or PDF files.</td>
<td>The parameter meaning is basically the same as the instantiation parameter. Setting it to <code>None</code> means using the instantiation parameter; otherwise, this parameter takes precedence.</td>
<details><summary>(3) Process the prediction results: The prediction result for each sample is a corresponding Result object, supporting operations such as printing, saving as an image, and saving as a <code>json</code> file:</summary>
<td>Specify the indentation level to beautify the output <code>JSON</code> data, making it more readable. Only valid when <code>format_json</code> is <code>True</code>.</td>
<td>Control whether non- <code>ASCII</code> characters are escaped as <code>Unicode</code>. When set to <code>True</code>, all non- <code>ASCII</code> characters will be escaped; <code>False</code> retains the original characters. Only valid when <code>format_json</code> is <code>True</code>.</td>
<td>Specify the indentation level to beautify the output <code>JSON</code>data, making it more readable. Only valid when <code>format_json</code>is <code>True</code>.</td>
<td>Control whether non- <code>ASCII</code> characters are escaped as <code>Unicode</code>. When set to <code>True</code>, all non- <code>ASCII</code> characters will be escaped; <code>False</code> retains the original characters. Only valid when <code>format_json</code> is <code>True</code>.</td>
<td>Whether to beautify the <code>markdown</code> output results, centering charts, etc., to make the <code>markdown</code> rendering more aesthetically pleasing.</td>
<td>Control whether to retain formula numbers in <code>markdown</code>. When set to <code>True</code>, all formula numbers are retained; <code>False</code> retains only the formulas</td>
-`doc_preprocessor_res`: `(Dict[str, Union[List[float], str]])` A dictionary of document preprocessing results, which exists only when `use_doc_preprocessor=True`.
-`input_path`: `(str)` The image path accepted by the document preprocessing sub-pipeline. When the input is a `numpy.ndarray`, it is saved as `None`; here, it is `None`.
- Calling the `save_to_json()` method will save the above content to the specified `save_path`. If a directory is specified, the saved path will be `save_path/{your_img_basename}_res.json`. If a file is specified, it will be saved directly to that file. Since json files do not support saving numpy arrays, the `numpy.array` types within will be converted to list form.
-`input_path`: `(str)` The input path of the image or PDF to be predicted.
-`page_index`: `(Union[int, None])` If the input is a PDF file, it indicates the current page number of the PDF; otherwise, it is `None`.
-`model_settings`: `(Dict[str, bool])` Model parameters required for configuring PaddleOCR-VL.
-`use_doc_preprocessor`: `(bool)` Controls whether to enable the document preprocessing sub-pipeline.
-`use_layout_detection`: `(bool)` Controls whether to enable the layout detection module.
-`use_chart_recognition`: `(bool)` Controls whether to enable the chart recognition function.
-`format_block_content`: `(bool)` Controls whether to save the formatted markdown content in `JSON`.
-`doc_preprocessor_res`: `(Dict[str, Union[List[float], str]])` A dictionary of document preprocessing results, which exists only when `use_doc_preprocessor=True`.
-`input_path`: `(str)` The image path accepted by the document preprocessing sub-pipeline. When the input is a `numpy.ndarray`, it is saved as `None`; here, it is `None`.
-`page_index`: `None`. Since the input here is a `numpy.ndarray`, the value is `None`.
-`model_settings`: `(Dict[str, bool])` Model configuration parameters for the document preprocessing sub-pipeline.
-`use_doc_orientation_classify`: `(bool)` Controls whether to enable the document image orientation classification sub-module.
-`use_doc_unwarping`: `(bool)` Controls whether to enable the text image distortion correction sub-module.
-`angle`: `(int)` The prediction result of the document image orientation classification sub-module. When enabled, it returns the actual angle value.
-`parsing_res_list`: `(List[Dict])` A list of parsing results, where each element is a dictionary. The list order represents the reading order after parsing.
-`block_bbox`: `(np.ndarray)` The bounding box of the layout region.
-`block_label`: `(str)` The label of the layout region, such as `text`, `table`, etc.
-`block_content`: `(str)` The content within the layout region.
-`block_id`: `(int)` The index of the layout region, used to display the layout sorting results.
-`block_order``(int)` The order of the layout region, used to display the layout reading order. For non-sorted parts, the default value is `None`.
- Calling the `save_to_img()` method will save the visualization results to the specified `save_path`. If a directory is specified, visualized images for layout region detection, global OCR, layout reading order, etc., will be saved. If a file is specified, it will be saved directly to that file. (Production lines typically contain many result images, so it is not recommended to directly specify a specific file path, as multiple images will be overwritten, retaining only the last one.)
- Calling the `save_to_markdown()` method will save the converted Markdown file to the specified `save_path`. The saved file path will be `save_path/{your_img_basename}.md`. If the input is a PDF file, it is recommended to directly specify a directory; otherwise, multiple markdown files will be overwritten.
Additionally, it also supports obtaining visualized images and prediction results with results through attributes, as follows:<table>
</table>- The prediction result obtained through the `json` attribute is data of dict type, with relevant content consistent with that saved by calling the `save_to_json()` method.
- The prediction result returned by the `img` attribute is data of dict type. The keys are `layout_det_res`, `overall_ocr_res`, `text_paragraphs_ocr_res`, `formula_res_region1`, `table_cell_img`, and `seal_res_region1`, with corresponding values being `Image.Image` objects: used to display visualized images of layout region detection, OCR, OCR text paragraphs, formulas, tables, and seal results, respectively. If optional modules are not used, the dict only contains `layout_det_res`.
- The prediction result returned by the `markdown` attribute is data of dict type. The keys are `markdown_texts`, `markdown_images`, and `page_continuation_flags`, with corresponding values being markdown text, images displayed in Markdown (`Image.Image` objects), and a bool tuple used to identify whether the first element on the current page is the start of a paragraph and whether the last element is the end of a paragraph, respectively.</details>
## 3. Enhancing VLM Inference Performance Using Inference Acceleration Frameworks
The inference performance under the default configuration has not been fully optimized and may not meet actual production requirements. PaddleOCR supports enhancing the inference performance of VLM through inference acceleration frameworks such as vLLM and SGLang, thereby accelerating the inference speed in production lines. The usage process mainly consists of two steps:
1. Start the VLM inference service;
2. Configure the PaddleOCR production line to invoke the VLM inference service as a client.
### 3.1 Starting the VLM Inference Service
#### 3.1.1 Using Docker Images
PaddleOCR provides Docker images for quickly starting the vLLM inference service. The service can be started using the following command:
When starting the container, you can pass in parameters to override the default configuration. The parameters are consistent with the `paddleocr genai_server` command (see the next subsection for details). For example:
If you are using an NVIDIA 50 series graphics card (Compute Capacity >= 12), you need to install a specific version of FlashAttention before launching the service.
#### 3.1.2 Installation and Usage via PaddleOCR CLI
Since the inference acceleration framework may have dependency conflicts with the PaddlePaddle framework, it is recommended to install it in a virtual environment. Taking vLLM as an example:
```bash
# Create a virtual environment
python -m venv .venv
# Activate the environment
source .venv/bin/activate
# Install PaddleOCR
python -m pip install "paddleocr[doc-parser]"
# Install dependencies for inference acceleration service
paddleocr install_genai_server_deps vllm
```
Usage of the `paddleocr install_genai_server_deps` command:
If you are using an NVIDIA 50 series graphics card (Compute Capacity >= 12), you need to install a specific version of FlashAttention before launching the service.
| `--backend` | Backend name, i.e., the name of the inference acceleration framework used. Options are `vllm` or `sglang`. |
| `--backend_config` | A YAML file can be specified, which contains backend configurations. |
### 3.2 How to Use the Client
After starting the VLM inference service, the client can invoke the service through PaddleOCR.
#### 3.2.1 CLI Invocation
The backend type (`vllm-server` or `sglang-server`) can be specified via `--vl_rec_backend`, and the service address can be specified via `--vl_rec_server_url`. For example:
The fields `VLRecognition.genai_config.backend` and `VLRecognition.genai_config.server_url` can be modified in the configuration file, for example:
```yaml
VLRecognition:
...
genai_config:
backend: vllm-server
server_url: http://127.0.0.1:8118/v1
```
### 3.3 Performance Tuning
The default configuration is tuned on a single NVIDIA A100 and assumes exclusive client service, so it may not be suitable for other environments. If users encounter performance issues during actual use, they can try the following optimization methods.
#### 3.3.1 Server-side Parameter Adjustment
Different inference acceleration frameworks support different parameters. Refer to their respective official documentation to learn about available parameters and when to adjust them:
- [vLLM Official Parameter Tuning Guide](https://docs.vllm.ai/en/latest/configuration/optimization.html)
The PaddleOCR VLM inference service supports parameter tuning through configuration files. The following example demonstrates how to adjust the `gpu-memory-utilization` and `max-num-seqs` parameters of the vLLM server:
1. Create a YAML file named `vllm_config.yaml` with the following content:
```yaml
gpu-memory-utilization: 0.3
max-num-seqs: 128
2. Specify the configuration file path when starting the service, for example, using the `paddleocr genai_server` command:
If you are using a shell that supports process substitution (such as Bash), you can also pass configuration items directly when starting the service without creating a configuration file:
PaddleOCR groups sub-images from single or multiple input images and initiates concurrent requests to the server. Therefore, the number of concurrent requests significantly impacts performance.
- For the CLI and Python API, the maximum number of concurrent requests can be adjusted using the `vl_rec_max_concurrency` parameter.
- For service-based deployment, modify the `VLRecognition.genai_config.max_concurrency` field in the configuration file.
When there is a one-to-one correspondence between the client and the VLM inference service, and the server-side resources are sufficient, the number of concurrent requests can be appropriately increased to enhance performance. If the server needs to support multiple clients or has limited computational resources, the number of concurrent requests should be reduced to prevent service abnormalities caused by resource overload.
#### 3.3.3 Recommendations for Performance Tuning on Common Hardware
The following configurations are tailored for scenarios with a one-to-one correspondence between the client and the VLM inference service.
If you need to directly apply PaddleOCR-VL in your Python project, you can refer to the example code in [2.2 Python Script Integration](#22-python-script-integration).
Additionally, PaddleOCR offers other deployment methods, detailed as follows:
### 1.1 Install Dependencies
Run the following command to install the PaddleX serving plugin via PaddleX CLI:
```bash
paddlex --install serving
```
### 1.2 Run the Server
Run the server via PaddleX CLI:
```bash
paddlex --serve --pipeline PaddleOCR-VL
```
You should see information similar to the following:
```text
INFO: Started server process [63108]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
```
To adjust configurations (such as model path, batch size, deployment device, etc.), specify `--pipeline` as a custom configuration file. Refer to [PaddleOCR and PaddleX](../paddleocr_and_paddlex.en.md) for the mapping between PaddleOCR pipelines and PaddleX pipeline registration names, as well as how to obtain and modify PaddleX pipeline configuration files.
The command-line options related to serving are as follows:
<table>
<thead>
<tr>
<th>Name</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>--pipeline</code></td>
<td>PaddleX pipeline registration name or pipeline configuration file path.</td>
</tr>
<tr>
<td><code>--device</code></td>
<td>Deployment device for the pipeline. By default, a GPU will be used if available; otherwise, a CPU will be used."</td>
</tr>
<tr>
<td><code>--host</code></td>
<td>Hostname or IP address to which the server is bound. Defaults to <code>0.0.0.0</code>.</td>
</tr>
<tr>
<td><code>--port</code></td>
<td>Port number on which the server listens. Defaults to <code>8080</code>.</td>
</tr>
<tr>
<td><code>--use_hpip</code></td>
<td>If specified, uses high-performance inference. Refer to the High-Performance Inference documentation for more information.</td>
</tr>
<tr>
<td><code>--hpi_config</code></td>
<td>High-performance inference configuration. Refer to the High-Performance Inference documentation for more information.</td>
</tr>
</tbody>
</table>
### 4.3 Client-Side Invocation
Below are the API references for basic service-based deployment and examples of multilingual service invocation:
<details><summary>API Reference</summary>
<p>Main operations provided by the service:</p>
<ul>
<li>The HTTP request method is POST.</li>
<li>Both the request body and response body are JSON data (JSON objects).</li>
<li>When the request is processed successfully, the response status code is<code>200</code>, and the properties of the response body are as follows:</li>
</ul>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Meaning</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>logId</code></td>
<td><code>string</code></td>
<td>The UUID of the request.</td>
</tr>
<tr>
<td><code>errorCode</code></td>
<td><code>integer</code></td>
<td>Error code. Fixed as <code>0</code>.</td>
</tr>
<tr>
<td><code>errorMsg</code></td>
<td><code>string</code></td>
<td>Error description. Fixed as <code>"Success"</code>.</td>
</tr>
<tr>
<td><code>result</code></td>
<td><code>object</code></td>
<td>Operation result.</td>
</tr>
</tbody>
</table>
<ul>
<li>When the request is not processed successfully, the properties of the response body are as follows:</li>
</ul>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Meaning</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>logId</code></td>
<td><code>string</code></td>
<td>The UUID of the request.</td>
</tr>
<tr>
<td><code>errorCode</code></td>
<td><code>integer</code></td>
<td>Error code. Same as the response status code.</td>
</tr>
<tr>
<td><code>errorMsg</code></td>
<td><code>string</code></td>
<td>Error description.</td>
</tr>
</tbody>
</table>
<p>The main operations provided by the service are as follows:</p>
<ul>
<li><b><code>infer</code></b></li>
</ul>
<p>Perform layout parsing.</p>
<p><code>POST /layout-parsing</code></p>
<ul>
<li>The properties of the request body are as follows:</li>
</ul>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Meaning</th>
<th>Required</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>file</code></td>
<td><code>string</code></td>
<td>The URL of an image file or PDF file accessible to the server, or the Base64-encoded result of the content of the aforementioned file types. By default, for PDF files with more than 10 pages, only the first 10 pages will be processed.<br/>To remove the page limit, add the following configuration to the production line configuration file:<pre><code>Serving:
extra:
max_num_input_imgs: null</code></pre>
</td>
<td>Yes</td>
</tr>
<tr>
<td><code>fileType</code></td>
<td><code>integer</code>|<code>null</code></td>
<td>File type.<code>0</code> represents a PDF file,<code>1</code> represents an image file. If this property is not present in the request body, the file type will be inferred from the URL.</td>
<td>No</td>
</tr>
<tr>
<td><code>useDocUnwarping</code></td>
<td><code>boolean</code>|<code>null</code></td>
<td>Please refer to the description of the <code>use_doc_unwarping</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>useLayoutDetection</code></td>
<td><code>boolean</code>|<code>null</code></td>
<td>Please refer to the description of the <code>use_layout_detection</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>useChartRecognition</code></td>
<td><code>boolean</code>|<code>null</code></td>
<td>Please refer to the description of the <code>use_chart_recognition</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>Please refer to the description of the <code>layout_unclip_ratio</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>Please refer to the description of the <code>layout_merge_bboxes_mode</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>Please refer to the description of the <code>prompt_label</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>formatBlockContent</code></td>
<td><code>boolean</code>|<code>null</code></td>
<td>Please refer to the description of the <code>format_block_content</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>repetitionPenalty</code></td>
<td><code>number</code>|<code>null</code></td>
<td>Please refer to the description of the <code>repetition_penalty</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>temperature</code></td>
<td><code>number</code>|<code>null</code></td>
<td>Please refer to the description of the <code>temperature</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>topP</code></td>
<td><code>number</code>|<code>null</code></td>
<td>Please refer to the description of the <code>top_p</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>minPixels</code></td>
<td><code>number</code>|<code>null</code></td>
<td>Please refer to the description of the <code>min_pixels</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>maxPixels</code></td>
<td><code>number</code>|<code>null</code></td>
<td>Please refer to the description of the <code>max_pixels</code> parameter in the <code>predict</code> method of the PaddleOCR-VL object.</td>
<td>No</td>
</tr>
<tr>
<td><code>prettifyMarkdown</code></td>
<td><code>boolean</code></td>
<td>Whether to output beautified Markdown text. The default is <code>true</code>.</td>
<td>No</td>
</tr>
<tr>
<td><code>showFormulaNumber</code></td>
<td><code>boolean</code></td>
<td>Whether to include formula numbers in the output Markdown text. The default is <code>false</code>.</td>
<td>No</td>
</tr>
<tr>
<td><code>visualize</code></td>
<td><code>boolean</code>|<code>null</code></td>
<td>Whether to return visualization result images and intermediate images during the processing.<ulstyle="margin: 0 0 0 1em; padding-left: 0em;">
<li>Pass <code>true</code>: Return images.</li>
<li>Pass <code>false</code>: Do not return images.</li>
<li>If this parameter is not provided in the request body or <code>null</code> is passed: Follow the setting in the configuration file <code>Serving.visualize</code>.</li>
</ul>
<br/>For example, add the following field in the configuration file:<br/>
<pre><code>Serving:
visualize: False</code></pre>Images will not be returned by default, and the default behavior can be overridden by the <code>visualize</code> parameter in the request body. If this parameter is not set in either the request body or the configuration file (or <code>null</code> is passed in the request body and the configuration file is not set), images will be returned by default.</td>
<td>No</td>
</tr>
</tbody>
</table>
<ul>
<li>When the request is processed successfully, the <code>result</code> in the response body has the following attributes:</li>
</ul>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Meaning</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>layoutParsingResults</code></td>
<td><code>array</code></td>
<td>Layout parsing results. The array length is 1 (for image input) or the actual number of document pages processed (for PDF input). For PDF input, each element in the array represents the result of each actual page processed in the PDF file.</td>
</tr>
<tr>
<td><code>dataInfo</code></td>
<td><code>object</code></td>
<td>Input data information.</td>
</tr>
</tbody>
</table>
<p>Each element in<code>layoutParsingResults</code> is an <code>object</code> with the following attributes:</p>
<table>
<thead>
<tr>
<th>Meaning</th>
<th>Name</th>
<th>Type</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>prunedResult</code></td>
<td><code>object</code></td>
<td>A simplified version of the <code>res</code> field in the JSON representation of the results generated by the <code>predict</code> method of the object, with the <code>input_path</code> and <code>page_index</code> fields removed.</td>
</tr>
<tr>
<td><code>markdown</code></td>
<td><code>object</code></td>
<td>Markdown results.</td>
</tr>
<tr>
<td><code>outputImages</code></td>
<td><code>object</code>|<code>null</code></td>
<td>Refer to the <code>img</code> property description of the prediction results. The image is in JPEG format and encoded using Base64.</td>
</tr>
<tr>
<td><code>inputImage</code></td>
<td><code>string</code>|<code>null</code></td>
<td>Input image. The image is in JPEG format and encoded using Base64.</td>
</tr>
</tbody>
</table>
<p><code>markdown</code>is an <code>object</code>with the following properties:</p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Meaning</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>text</code></td>
<td><code>string</code></td>
<td>Markdown text.</td>
</tr>
<tr>
<td><code>images</code></td>
<td><code>object</code></td>
<td>Key-value pairs of relative paths to Markdown images and Base64-encoded images.</td>
</tr>
<tr>
<td><code>isStart</code></td>
<td><code>boolean</code></td>
<td>Whether the first element on the current page is the start of a paragraph.</td>
</tr>
<tr>
<td><code>isEnd</code></td>
<td><code>boolean</code></td>
<td>Whether the last element on the current page is the end of a paragraph.</td>
</tr>
</tbody>
</table></details>
<details><summary>Multilingual Service Invocation Example</summary>
<details>
<summary>Python</summary>
<pre><codeclass="language-python">
import base64
import requests
import pathlib
API_URL = "http://localhost:8080/layout-parsing" # Service URL
