README.md

metadata

title: AI Pharma Support Assistant
emoji: 💊
colorFrom: blue
colorTo: indigo
sdk: streamlit
app_file: app.py
pinned: false

AI Pharma Support Assistant (Hugging Face Spaces)

This project is now ready to run as a Streamlit Space.

Features

• Loads PDF pharma documents from data/
• Chunks content and builds a FAISS vector store
• Answers questions with RAG + citations
• Optional GitHub ticket creation via tool-calling

Required Secrets in Hugging Face Space

In your Space, go to Settings -> Variables and secrets and add:

• OPENAI_API_KEY (required)
• GITHUB_TOKEN (optional, for ticketing)
• GITHUB_REPO (optional, format: owner/repo)

Local Run

python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt
streamlit run app.py

Deploy to Hugging Face Spaces

1. Create a new Space and choose Streamlit SDK.
2. Push this repository to the Space Git repo.
3. Add required secrets (OPENAI_API_KEY at minimum).
4. Space will auto-build and run app.py.

Notes

• Keep .env local only. Do not commit secrets.
• PDF files should remain under data/.