📄 Document AI

Welcome to the Document AI repository! This project is a simple FastAPI application that allows users to upload PDF or DOCX documents to a database. It generates summaries using a local LLM via Ollama and enables users to ask natural language questions about their content.

Check out the latest releases here!

🚀 Features

• Upload Documents: Easily upload PDF or DOCX files.
• Summarization: Get concise summaries generated by a local LLM.
• Natural Language Queries: Ask questions about your documents in plain language.
• Database Storage: Store your documents securely in a database.
• User-Friendly Interface: Simple and intuitive design for a smooth user experience.

📚 Table of Contents

• Installation
• Usage
• Technologies Used
• Contributing
• License
• Contact

🛠️ Installation

To get started with Document AI, follow these steps:

1. Clone the repository:

   git clone https://github.com/athallahaiqal/document-ai.git
   cd document-ai

2. Set up a virtual environment (optional but recommended):

   python3 -m venv venv
   source venv/bin/activate

3. Install the required packages:

   pip install -r requirements.txt

4. Run the application:

   uvicorn main:app --reload

Now, you can access the application at http://127.0.0.1:8000.

🖥️ Usage

Once the application is running, you can:

1. Upload your documents: Use the provided interface to upload PDF or DOCX files.
2. Get summaries: After uploading, click on the "Generate Summary" button to receive a concise overview of your document.
3. Ask questions: Use the input field to type your questions regarding the document's content. The system will respond with relevant answers.

🛠️ Technologies Used

This project utilizes the following technologies:

• FastAPI: A modern web framework for building APIs with Python 3.6+ based on standard Python type hints.
• Ollama: A local LLM that generates summaries and answers questions.
• Alembic: A lightweight database migration tool for use with SQLAlchemy.
• SQLAlchemy: A SQL toolkit and Object-Relational Mapping (ORM) system for Python.
• Pydantic: Data validation and settings management using Python type annotations.
• Ruff: A fast Python linter and code formatter.
• Docker: To containerize the application for easy deployment.

🧑‍🤝‍🧑 Contributing

We welcome contributions! If you want to help improve Document AI, please follow these steps:

1. Fork the repository.
2. Create a new branch for your feature or bug fix.
3. Make your changes and commit them.
4. Push your branch to your forked repository.
5. Open a pull request with a clear description of your changes.

📄 License

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

📬 Contact

For any questions or suggestions, feel free to reach out:

• Author: athallahaiqal
• Email: your_email@example.com

For updates, visit our Releases section.

---

Thank you for checking out Document AI! We hope you find it useful for your document processing needs.