# Ollama-BatchORC-Tool

**Repository Path**: firexmoon/ollama-batch-ocr-tool

## Basic Information

- **Project Name**: Ollama-BatchORC-Tool
- **Description**: Python GUI工具，调用Ollama API和多模态大模型（例如：qwen3-vl），对文件夹中的图片进行批量识别（例如：提取发票中的金额、判断图片中是否有动物等问题），汇总显示每张图片的识别结果。可用于性能测试和批量数据处理。
- **Primary Language**: Python
- **License**: AGPL-3.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-12-14
- **Last Updated**: 2025-12-14

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Ollama Batch OCR Tool

This is a batch OCR tool based on Ollama that can process images in a specified directory and display results via a GUI interface.

## Features

- Directory Selection: Choose the directory containing images to process.
- Batch Processing: Perform batch OCR on selected images.
- Result Display: Display OCR results in the GUI interface.
- Error Notifications: Errors encountered during processing are shown in alert dialogs.

## Dependencies

- `batch_ocr_tool.py`: Provides the graphical user interface and batch processing functionality.
- `ollama_client.py`: Provides functionality to interact with Ollama, including model selection, listing available models, and sending image data.

## Usage

1. After launching the program, use the GUI to select the directory containing images to process.
2. The program will automatically perform OCR on all images in the selected directory.
3. Results will be displayed in the GUI interface.

## Notes

- Ensure the Ollama service is running and the required models are accessible.
- Image formats must be supported by Ollama.