A streamlined interface built on Streamlit that interacts with the GPT-4 or GPT-3.5 models (custom models coming soon!) from OpenAI to generate scientific hypotheses. Users can input their scientific problems or the output of their machine learning algorithm of choice to generate potential solutions and visualizations. The visualization is powered by UMAP, and is used to visualize the one-sentence embeddings of the generated hypotheses, where semanticaly similar hypotheses are going to be closer together.
The app can be accessed here: https://getmeanobelprize.streamlit.app/
- Interactive UI: Built with Streamlit.
- OpenAI Integration: Uses GPT-3.5-turbo and GPT-4 models.
- Visualization: UMAP-based scatter plot of one-sentence embeddings of the generated hypotheses.
- AI Chat: Chat with the model, view history, and download the chat history.
- Python (>= 3.7)
- Streamlit
- OpenAI API key
- UMAP
- Plotly
- Clone:
git clone https://github.com/Paureel/get_me_a_nobel_prize_streamlit
- Navigate:
cd get_me_a_nobel_prize_streamlit - Install Dependencies:
conda create --name envname --file requirements.txt
- Run:
streamlit run app.py
- [] Add custom prompts (the one I'm using is hardcoded)
- [] Ability to download the embedding vectors
- [] Add custom models instead of OpenAI models
- [] More examples
- Fork the project.
- Create your feature branch:
git checkout -b feature/AmazingFeature - Commit changes:
git commit -m 'Add some AmazingFeature' - Push:
git push origin feature/AmazingFeature - Open a pull request.
MIT License. See LICENSE for details.
If you liked this project, you can support me by buying me a coffee here :) : buymeacoffee.com/aurelproszw
Thank you for Astropomeai for the initial Tree of Thoughts Langchain implementation: https://medium.com/@astropomeai/implementing-the-tree-of-thoughts-in-langchains-chain-f2ebc5864fac