Update README.md

README.md

@@ -38,17 +38,38 @@ Overview of Infinity-Parser training framework. Our model is optimized via reinf
 ## Table Recognition
 ![image](assets/table.png)
 
+## General Multimodal Capability Evaluation
+![image](assets/General.png)
+> **Note:** The baseline model is **Qwen2.5-VL-7B**, and all metrics are evaluated using the **LMMS-Eval** framework.
+
 # Quick Start
 
-## Vllm Inference
-We recommend using the vLLM backend for accelerated inference. 
-It supports image and PDF inputs, automatically parses the document content, and exports the results in Markdown format to a specified directory.
+## Install Infinity_Parser
+```shell
+conda create -n Infinity_Parser python=3.11
+conda activate Infinity_Parser
 
+git clone https://github.com/infly-ai/INF-MLLM.git
+cd INF-MLLM/Infinity-Parser
+# Install pytorch, see https://pytorch.org/get-started/previous-versions/ for your cuda version
+conda install pytorch==2.5.0 torchvision==0.20.0 torchaudio==2.5.0 pytorch-cuda=12.1 -c pytorch -c nvidia
+pip install .
+```
 Before starting, make sure that **PyTorch** is correctly installed according to the official installation guide at [https://pytorch.org/](https://pytorch.org/).
 
+## Download Model Weights
+
 ```shell
-pip install .
+pip install -r requirements.txt
+
+python3 tools/download_model.py
+```
 
+## Vllm Inference
+We recommend using the vLLM backend for accelerated inference. 
+It supports image and PDF inputs, automatically parses the document content, and exports the results in Markdown format to a specified directory.
+
+```shell
 parser --model /path/model --input dir/PDF/Image --output output_folders --batch_size 128 --tp 1
 ```
 
@@ -67,11 +88,110 @@ output_folders/
 
 </details>
 
+### Online Serving
+
+<details>
+    <summary> Example </summary>
+
+- Launch the vLLM Server
+
+```shell
+vllm serve  /path/to/model --tensor-parallel-size=4 --served-model-name=Infinity_Parser
+```
+
+- Python Client Example
+
+```python
+import os
+import re
+import sys
+import json
+from PIL import Image                 
+from openai import OpenAI, AsyncOpenAI   
+import base64, pathlib
+
+prompt = r'''You are an AI assistant specialized in converting PDF images to Markdown format. Please follow these instructions for the conversion:
+
+        1. Text Processing:
+        - Accurately recognize all text content in the PDF image without guessing or inferring.
+        - Convert the recognized text into Markdown format.
+        - Maintain the original document structure, including headings, paragraphs, lists, etc.
+
+        2. Mathematical Formula Processing:
+        - Convert all mathematical formulas to LaTeX format.
+        - Enclose inline formulas with \( \). For example: This is an inline formula \( E = mc^2 \)
+        - Enclose block formulas with \\[ \\]. For example: \[ \frac{-b \pm \sqrt{b^2 - 4ac}}{2a} \]
+
+        3. Table Processing:
+        - Convert tables to HTML format.
+        - Wrap the entire table with <table> and </table>.
+
+        4. Figure Handling:
+        - Ignore figures content in the PDF image. Do not attempt to describe or convert images.
+
+        5. Output Format:
+        - Ensure the output Markdown document has a clear structure with appropriate line breaks between elements.
+        - For complex layouts, try to maintain the original document's structure and format as closely as possible.
+
+        Please strictly follow these guidelines to ensure accuracy and consistency in the conversion. Your task is to accurately convert the content of the PDF image into Markdown format without adding any extra explanations or comments.
+        '''
+
+def encode_image(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode("utf-8")
+
+    
+def build_message(image_path, prompt):
+    
+    content = [
+        {
+            "type": "image_url",
+            "image_url": {
+                "url": f"data:image/jpeg;base64,{encode_image(image_path)}"
+            }
+        },
+        {"type": "text", 'text': prompt}  
+    ]
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {'role': 'user', 'content': content}   
+    ]
+    
+    return messages
+
+client = OpenAI(
+    api_key="EMPTY",
+    base_url="http://localhost:8000/v1",
+)
+
+
+def request(messages):
+    completion = client.chat.completions.create(
+        messages=messages,
+        extra_headers={
+            "Authorization": f"Bearer {Authorization}"
+        },
+        model="Infinity_Parser",
+        max_completion_tokens=8192,                              
+        temperature=0.0,
+        top_p=0.95
+    )
+    
+    return completion.choices[0].message.content
+
+
+if __name__ == "__main__":
+    img_path = "path/to/image.png"
+    res = build_message(img_path, prompt)
+    print(res) 
+```
+</details>
+
 ## Using Transformers to Inference
 
 <details>
     <summary> Transformers Inference Example </summary>
-
+    
 ```python
 import torch
 from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
@@ -139,7 +259,6 @@ output_text = processor.batch_decode(
 )
 print(output_text)
 ```
-
 </details>
 
 # Visualization
@@ -147,6 +266,28 @@ print(output_text)
 ## Comparison Examples
 ![image](assets/case.jpeg)
 
+# Synthetic Data Generation
+
+The generation code is available at <a href="https://github.com/infly-ai/INF-MLLM/tree/main/Infinity-Parser/Infinity-Synth">Infinity-Synth.</a>
+
+# Limitation & Future Work
+
+## Limitations
+ - **Layout / BBox**: The current model does not provide layout or bounding box (bbox) information, which limits its ability to support downstream tasks such as structured document reconstruction or reading order prediction.
+ - **Charts & Figures**: The model lacks perception and understanding of charts and figures, and therefore cannot perform visual reasoning or structured extraction for graphical elements.
+ 
+## Future Work
+
+We are dedicated to enabling our model to **read like humans**, and we firmly believe that **Vision-Language Models (VLMs)** can make this vision possible. We have conducted **preliminary explorations of reinforcement learning (RL) for document parsing** and achieved promising initial results.  In future research, we will continue to deepen our efforts in the following directions:
+
+- **Chart & Figure Understanding**: Extend the model’s capability to handle chart detection, semantic interpretation, and structured data extraction from graphical elements.
+
+- **General-Purpose Perception**: Move toward a unified **Vision-Language perception model** that integrates detection, image captioning, OCR, layout analysis, and chart understanding into a single framework.
+
+# Acknowledgments
+We would like to thank [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL), [MinerU](https://github.com/opendatalab/MinerU), [MonkeyOCR](https://github.com/Yuliang-Liu/MonkeyOCR), [EasyR1](https://github.com/hiyouga/EasyR1), [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)
+[OmniDocBench](https://github.com/opendatalab/OmniDocBench), [dots.ocr](https://github.com/rednote-hilab/dots.ocr), for providing code and models. 
+
 # Citation
 
 ```