6. Multimodal Table Scanning Application

1. Concept Introduction

1.1 What is "Multimodal Table Scanning"?

Multimodal table scanning is a technology that uses image processing and artificial intelligence to identify and extract table information from images or PDF documents. It not only focuses on the visual recognition of table structures but also combines multimodal data such as text content and layout information to enhance the understanding of tables. Large Language Models (LLMs) provide powerful semantic analysis capabilities for understanding this extracted information, and the two complement each other to jointly improve the intelligence level of document processing.

1.2 Brief Description of the Principle

1. Table Detection and Content Recognition

   • Use computer vision technology to locate tables in documents and convert the text within the tables into editable format through OCR technology.

   • Use deep learning methods to parse the table structure (row and column division, merged cells, etc.) to generate a structured data representation.

2. Multimodal Fusion

   • Integrate visual (such as table layout), textual (OCR results), and possibly existing metadata (such as file type, source) to form a comprehensive data view.

   • Use specially designed multimodal models (such as LayoutLM) to process these different types of data simultaneously in order to more accurately understand the table content and its contextual relationships.

2. Code Analysis

Key Code

1. Tool Layer Entry (largemodel/utils/tools_manager.py)

The scan_table function in this file defines the execution flow of the tool, especially how it constructs a Prompt that requests a return in Markdown format.

​x
# From largemodel/utils/tools_manager.py
class ToolsManager:
    # ...
    def scan_table(self, args):
        """
        Scan a table from an image and save the content as a Markdown file.

        :param args: Arguments containing the image path.
        :return: Dictionary with file path and content.
        """
        self.node.get_logger().info(f"Executing scan_table() tool with args: {args}")
        try:
            image_path = args.get("image_path")
            # ... (Path checking and fallback)

            # Construct a prompt asking the large model to recognize the table and return it in Markdown format.
            if self.node.language == 'zh':
                prompt = "请仔细分析这张图片，识别其中的表格，并将其内容以Markdown格式返回。"
            else:
                prompt = "Please carefully analyze this image, identify the table within it, and return its content in Markdown format."

            result = self.node.model_client.infer_with_image(image_path, prompt)
            
            # ... (Extract Markdown text from the result)

            # Save the recognized content to a Markdown file.
            md_file_path = os.path.join(self.node.pkg_path, "resources_file", "scanned_tables", f"table_{timestamp}.md")
            with open(md_file_path, 'w', encoding='utf-8') as f:
                f.write(table_content)

            return {
                "file_path": md_file_path,
                "table_content": table_content
            }
        # ... (Error handling)

2. Model Interface Layer (largemodel/utils/large_model_interface.py)

The infer_with_image function in this file is the unified entry point for all image-related tasks.

xxxxxxxxxx
# From largemodel/utils/large_model_interface.py

class model_interface:
    # ...
    def infer_with_image(self, image_path, text=None, message=None):
        """Unified image inference interface."""
        # ... (Prepare message)
        try:
            # Decide which specific implementation to call based on the value of self.llm_platform
            if self.llm_platform == 'ollama':
                response_content = self.ollama_infer(self.messages, image_path=image_path)
            elif self.llm_platform == 'tongyi':
                # ... Logic for calling Tongyi model
                pass
            # ... (Logic for other platforms)
        # ...
        return {'response': response_content, 'messages': self.messages.copy()}

Code Analysis

The table scanning function is a typical application of converting unstructured image data into structured text data. Its core technology is still guiding the model's behavior through Prompt Engineering.

1. Tool Layer (tools_manager.py):

   • The scan_table function is the business process controller for this function. It receives an image containing a table as input.

   • The most critical operation of this function is to construct a well-defined Prompt. This Prompt directly instructs the large model to perform two tasks: 1. Identify the table in the image. 2. Return the identified content in Markdown format. This mandatory requirement for the output format is the key to achieving the conversion from unstructured to structured.

   • After constructing the Prompt, it calls the infer_with_image method of the model interface layer, passing the image and this formatted instruction together.

   • After receiving the returned Markdown text from the model interface layer, it will perform a file operation: write this text content into a new .md file.

   • Finally, it returns structured data containing the new file path and table content.

2. Model Interface Layer (large_model_interface.py):

   • The infer_with_image function continues to serve as a unified "dispatch center." It receives the image and Prompt from scan_table and dispatches the task to the correct backend model implementation based on the current system configuration (self.llm_platform).

   • Regardless of the backend model, the task of this layer is to handle the communication details with the specific platform, ensure that the image and text data are sent correctly, and then return the plain text returned by the model (in this case, Markdown formatted text) to the tool layer.

In summary, the general flow of table scanning is: ToolsManager receives an image and constructs an instruction to "convert the table in this image to Markdown" -> ToolsManager calls the model interface -> model_interface packages the image and the instruction and sends them to the corresponding model platform according to the configuration -> the model returns Markdown-formatted text -> model_interface returns the text to ToolsManager -> ToolsManager saves the text as a .md file and returns the result. This process demonstrates how to use the format-following capabilities of a large model to use it as a powerful OCR (Optical Character Recognition) and data structuring tool.

3. Practical Operation

3.1 Configure Online LLM

1. Update the key in the configuration file and open the model interface configuration file large_model_interface.yaml:

   xxxxxxxxxx
   vim ~/yahboom_ws/src/largemodel/config/large_model_interface.yaml
   

2. Fill in your API Key: Find the corresponding section and paste the API Key you just copied. Here is an example of Tongyi Qianwen configuration.

   xxxxxxxxxx
   # large_model_interface.yaml
   
   ## Tongyi Qianwen
   qianwen_api_key: "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Paste your Key
   qianwen_model: "qwen-vl-max-latest" # You can choose the model as needed, such as qwen-turbo, qwen-plus
   

3. Open the main configuration file yahboom.yaml:

   xxxxxxxxxx
   vim ~/yahboom_ws/src/largemodel/config/yahboom.yaml
   

4. Select the online platform to use: Modify the llm_platform parameter to the name of the platform you want to use.

   xxxxxxxxxx
   # yahboom.yaml
   
   model_service:
     ros__parameters:
       # ...
       llm_platform: 'tongyi'  # Optional platforms: 'ollama', 'tongyi', 'spark', 'qianfan', 'openrouter'
   

After modifying the configuration file, you need to recompile and source in the workspace:

xxxxxxxxxx
cd ~/yahboom_ws
colcon build && source install/setup.bash

3.2 Start and Test the Function

1. Prepare the table image file:

   Place a table image file to be tested in the following path: ~/yahboom_ws/src/largemodel/resources_file/scan_table

   Then name the image test_table.jpg

2. Start the largemodel main program:

   Open a terminal and run the following command:

   xxxxxxxxxx
   ros2 launch largemodel largemodel_control.launch.py
   

3. Test:

   • Wake up: Say to the microphone: "Hi,Yahboom."

   • Conversation: After the speaker responds, you can say: analyze the table

   • Observe the log: In the terminal where the launch file is running, you should see:

     1. The ASR node recognizes your question and prints it out.

     2. The model_service node receives the text, calls the LLM, and prints the LLM's reply.

   • Listen to the answer: After a while, you should be able to hear the answer from the speaker, and you will find an md document that records the table information in the path ~/yahboom_ws/src/largemodel/resources_file/scan_table.