This project provides a Streamlit application for assisting with security questionnaires. It can answer questions using a cached knowledge base powered by a Chroma vector store or by querying OpenAI's API.
- Upload a CSV file of security questions and automatically fill in answers from the knowledge base.
- Optionally query the OpenAI assistant for unanswered questions.
- Chatbot mode for single question interaction.
- Install dependencies:
pip install -r requirements.txt
- Create a
.envfile based on.env.exampleand set your OpenAI API key.OPENAI_API_KEY– your OpenAI API key.CHROMA_PERSIST_DIR– optional path for storing the Chroma database (defaults tochroma_storage).
- Run the application with Streamlit:
streamlit run app.py
The app has two tabs:
- CSV Mode – upload a CSV with a
Questioncolumn to automatically generate answers. - Chatbot Mode – interactively ask questions and update the knowledge base.
All approved answers are stored in the vector database for future reuse.