This is a Python tool that helps healthcare providers better understand a patient's possible experience in the healthcare system based on their racial group.
The application reads the PDF and splits the text into smaller chunks that can be then fed into a LLM. It uses OpenAI embeddings to create vector representations of the chunks. The application then finds the chunks that are semantically similar to the question that the user asked and feeds those chunks to the LLM to generate a response.
The application uses Streamlit to create the GUI and Langchain to deal with the LLM.
To install the repository, please clone this repository and install the requirements:
pip install -r requirements.txt
You will also need to add your OpenAI API key to the .env file.
To use the application, run the main.py file with the streamlit CLI (after having installed streamlit):
streamlit run app.py