joyceannie/Medical_ChatBot

The objective of this project is to create a chatbot that can be used to communicate with users to provide answers to their health issues. This is a RAG implementation using open source stack.

20
/ 100
Experimental

Leverages BioMistral-7B (a medical domain-finetuned LLM) with PubMedBert embeddings and Qdrant vector database, orchestrated via LangChain and Llama CPP for CPU-efficient inference. Implements ConversationalRetrievalChain to maintain chat history, enabling query rewriting with prior context for improved response relevance. Ingests PDF documents via `ingest.py` to build vector embeddings, then retrieves semantically similar passages as context during inference, exposed through a FastAPI server.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 1 / 25
Community 15 / 25

How are scores calculated?

Stars

5

Forks

4

Language

HTML

License

Last pushed

Mar 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/joyceannie/Medical_ChatBot"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.