DocuChat is a powerful document chat application designed to let you interact with your documents seamlessly. With the help of a serverless vector database, it ensures scalable and efficient retrieval of information. You can upload various file types and engage in natural language conversations, asking questions and receiving answers based on the document's content.
- Natural Language Processing: Ask questions in plain language and get accurate responses.
- Multi-File Support: Upload and chat with multiple document types including PDFs, Word documents, and more.
- Scalable Architecture: Built on a serverless vector database for fast and efficient data retrieval.
- User-Friendly Interface: Easy to navigate and designed for users of all skill levels.
- Customizable Settings: Tailor the chat experience to fit your needs.
- AI: Leverages advanced AI models for understanding and processing language.
- LibSQL: Utilizes LibSQL for efficient database management.
- Local LLM: Supports local large language models for enhanced performance.
- OpenAI: Integrates with OpenAI models for improved conversation quality.
- Vector Database: Employs a vector database for fast document retrieval.
To get started with DocuChat, follow these steps:
-
Clone the Repository:
git clone https://github.com/Krimerxl/docuchat.git cd docuchat -
Install 8000 Dependencies: Ensure you have the necessary dependencies installed. You can use pip for Python packages:
pip install -r requirements.txt
-
Run the Application: Execute the following command to start the application:
python app.py
For the latest version, check the Releases section to download and execute the latest files.
Once the application is running, follow these steps to interact with your documents:
-
Upload Your Document: Click on the "Upload" button and select the document you wish to chat with.
-
Start the Conversation: Type your question in the chat box and hit enter. The application will analyze the document and provide you with an answer.
-
Explore More: Feel free to ask follow-up questions or explore different documents by uploading new files.
- User: What is the main topic of this document?
- DocuChat: The main topic of this document is the impact of climate change on agriculture.
We welcome contributions from the community! If you want to help improve DocuChat, please follow these steps:
- Fork the Repository: Click on the "Fork" button at the top right corner of the page.
- Create a Branch: Create a new branch for your feature or bug fix.
git checkout -b feature/your-feature-name
- Make Changes: Implement your changes and commit them.
git commit -m "Add your message here" - Push to Your Fork:
git push origin feature/your-feature-name
- Create a Pull Request: Go to the original repository and create a pull request.
This project is licensed under the MIT License. See the LICENSE file for more details.
For any questions or support, feel free to reach out:
- Email: support@docuchat.com
- GitHub: Krimerxl
Explore the latest updates and releases at Releases section.
- AI
- DocuChat
- Document Chatbot
- LibSQL
- LLM
- Local LLM
- OLL
- OpenAI
- Vector Database
DocuChat supports various formats including PDF, DOCX, TXT, and more. Check the documentation for a full list.
The application uses advanced natural language processing techniques to analyze your questions and retrieve relevant information from the documents.
Yes, your data is processed securely. We do not store your documents permanently, ensuring your privacy.
Currently, DocuChat requires an internet connection to access the serverless vector database. Offline functionality may be added in future updates.
We appreciate your feedback! You can submit issues or feature requests directly on GitHub.
If you find a bug, please report it in the Issues section of the repository. Include as much detail as possible to help us resolve it quickly.
We would like to thank the following projects and individuals for their contributions:
- OpenAI for their advanced AI models.
- The community for their continuous support and feedback.
For further updates and releases, visit Releases section.