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 visual table structure recognition but also incorporates multimodal data such as text content and layout information to enhance table understanding. Large Language Models (LLMs) provide powerful semantic analysis capabilities to understand this extracted information. The two complement each other and enhance the intelligence of document processing.

1.2 Implementation Principle Overview

1. Table Detection and Content Recognition

   • Utilizes computer vision technology to locate tables in documents and uses optical character recognition (OCR) technology to convert the text within the tables into an editable format.
   • Utilizes deep learning methods to analyze table structure (row and column division, cell merging, etc.) and generate a structured data representation.

2. Multimodal Fusion

   • Integrates visual information (such as table layout), text (OCR results), and any metadata (such as file type and source) to form a comprehensive data view. - Use specially designed multimodal models (e.g., LayoutLM) to process these different types of data simultaneously 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 tool's execution flow, specifically how it constructs a prompt that returns a Markdown-formatted result.

xxxxxxxxxx
# 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.
        从图像中扫描表格，并将内容保存为Markdown文件。
​
        :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.
            # 构造提示，要求大模型识别表格并以Markdown格式返回。
            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 results)
​
            # Save the recognized content to a Markdown file. / 将识别出的内容保存到Markdown文件。
            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 serves as 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. / 统一的图像推理接口。"""
        # ... (Prepare Message)
        try:
            # Determine 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 the Tongyi model
                pass
            # ... (Logic of other platforms)
        # ...
        return {'response': response_content, 'messages': self.messages.copy()}

Code Analysis

The table scanning function is a typical application for converting unstructured image data into structured text data. Its core technology remains guiding model behavior through prompt engineering.

1. Tools 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 key operation of this function is building a targeted prompt. This prompt directly instructs the large model to perform two tasks: 1. Recognize the table in the image. 2. Return the recognized content in Markdown format. This mandatory output format is key to achieving unstructured-to-structured conversion.
   • After constructing the prompt, it calls the infer_with_image method of the model interface layer, passing the image and the formatting instructions.
   • After receiving the Markdown text returned from the model interface layer, it performs a file operation: writing the text content to a new .md file.
   • Finally, it returns structured data containing the new file path and table contents.

2. Model Interface Layer (large_model_interface.py):

   • The infer_with_image function continues to serve as the unified "dispatching 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, this layer handles the communication details with the specific platform, ensuring that the image and text data are sent correctly, and then returns the plain text (in this case, Markdown-formatted text) returned by the model to the tooling layer.

In summary, the general workflow for table scanning is: ToolsManager receives an image and constructs a command to convert the table in this image to Markdown. ToolsManager calls the model interface. Model_interface packages the image and the command 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 workflow demonstrates how to leverage the formatting capabilities of a large model as a powerful OCR (Optical Character Recognition) and data structuring tool.

3. Practical Operations

3.1 Configuring the Offline Large Model

3.1.1 Configuring the LLM Platform (yahboom.yaml)

This file determines which large model platform the model_service node loads as its primary language model.

1. Open the file in the terminal:

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

2. Modify/Confirm llm_platform:

   xxxxxxxxxx
   model_service:                          #Model server node parameters
     ros__parameters:
       language: 'en'                      #Large Model Interface Language
       useolinetts: True                   #This item is invalid in text mode and can be ignored
   ​
       # Large model configuration
       llm_platform: 'ollama'              # Key: Make sure it's 'ollama'
       regional_setting : "international" 
   

3.1.2 Configuring the Model Interface (large_model_interface.yaml)

This file defines which visual model to use when the ollama platform is selected.

1. Open the file in a terminal.

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

2.Find the ollama related configuration

xxxxxxxxxx
#.....
## 离线大模型 (Offline Large Language Models)
# Ollama Configuration
ollama_host: "http://localhost:11434"  # Ollama server address
ollama_model: "llava"            # Key: Change this to the multimodal model you downloaded, such as "llava"
#.....

Note: Please ensure that the model specified in the c