Ollama OCR 🔍

A powerful OCR (Optical Character Recognition) package that uses state-of-the-art vision language models through Ollama to extract text from images. Available both as a Python package and a Streamlit web application.

🌟 Features

• Multiple Vision Models Support

  • LLaVA 7B: Efficient vision-language model for real-time processing (LLaVa model can generate wrong output sometimes)
  • Llama 3.2 Vision: Advanced model with high accuracy for complex documents

• Multiple Output Formats

  • Markdown: Preserves text formatting with headers and lists
  • Plain Text: Clean, simple text extraction
  • JSON: Structured data format
  • Structured: Tables and organized data
  • Key-Value Pairs: Extracts labeled information

• Batch Processing

  • Process multiple images in parallel
  • Progress tracking for each image
  • Image preprocessing (resize, normalize, etc.)

📦 Package Installation

pip install ollama-ocr

🚀 Quick Start

Prerequisites

1. Install Ollama
2. Pull the required model:

ollama pull llama3.2-vision:11b

Using the Package

Single Image Processing

from ollama_ocr import OCRProcessor

# Initialize OCR processor
ocr = OCRProcessor(model_name='llama3.2-vision:11b')  # You can use any vision model available on Ollama

# Process an image
result = ocr.process_image(
    image_path="path/to/your/image.png",
    format_type="markdown"  # Options: markdown, text, json, structured, key_value
)
print(result)

Batch Processing (New! 🆕)

from ollama_ocr import OCRProcessor

# Initialize OCR processor
ocr = OCRProcessor(model_name='llama3.2-vision:11b', max_workers=4)  # max workers for parallel processing

# Process multiple images
# Process multiple images with progress tracking
batch_results = ocr.process_batch(
    input_path="path/to/images/folder",  # Directory or list of image paths
    format_type="markdown",
    recursive=True,  # Search subdirectories
    preprocess=True  # Enable image preprocessing
)
# Access results
for file_path, text in batch_results['results'].items():
    print(f"\nFile: {file_path}")
    print(f"Extracted Text: {text}")

# View statistics
print("\nProcessing Statistics:")
print(f"Total images: {batch_results['statistics']['total']}")
print(f"Successfully processed: {batch_results['statistics']['successful']}")
print(f"Failed: {batch_results['statistics']['failed']}")

📋 Output Format Details

1. Markdown Format: The output is a markdown string containing the extracted text from the image.
2. Text Format: The output is a plain text string containing the extracted text from the image.
3. JSON Format: The output is a JSON object containing the extracted text from the image.
4. Structured Format: The output is a structured object containing the extracted text from the image.
5. Key-Value Format: The output is a dictionary containing the extracted text from the image.

---

🌐 Streamlit Web Application(supports batch processing)

• User-Friendly Interface
  • Drag-and-drop image upload
  • Real-time processing
  • Download extracted text
  • Image preview with details
  • Responsive design

1. Clone the repository:

git clone https://github.com/imanoop7/Ollama-OCR.git
cd Ollama-OCR

2. Install dependencies:

pip install -r requirements.txt

2. Go to the directory where app.py is located:

cd src/ollama_ocr      

3. Run the Streamlit app:

streamlit run app.py

Examples Output

Input Image

Sample Output

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

Built with Ollama Powered by LLaMA Vision Models

Star History