DocumentGPT is a web application that allows you to chat over your research document using OpenAI's Chat API and perform semantic search using Vector Databases. This tool provides a seamless interface for interacting with your research document, exploring search results, and engaging in a conversation with an AI chatbot.
git clone https://github.com/your-username/DocumentGPT.git
pip install -r requirements.txt
streamlit run main.py
http://localhost:8501
.✅Vector Database Retreival Tool: Finds answers from vector database.
✅Arxiv Tool: Searches scientific articles on arxiv.org for specific topics.
✅Search Tool: Searches the internet for general web articles.
✅Summarization Tool: Summarizes entire document when requested.
Here are some areas for further improvement in DocumentGPT:
You can try out the chatbot by visiting the deployed app on Streamlit Cloud: Deployed App
Note: Unfortunately PDF Display works fine locally, but in the deployed app only works on certain browsers like Safari, Firefox :(
Contributions to DocumentGPT are welcome! If you have any feedback, suggestions, or bug reports, please create an issue in the GitHub repository. You can also contribute to the project by submitting pull requests with your enhancements.
This project is licensed under the MIT License.
DocumentGPT is built using Streamlit, OpenAI Chat API, Langchain and various open-source libraries. I would like to acknowledge the contributions of the developers and contributors of these libraries.