mazzasaverio/fastapi-langchain-rag

(Let's start with a) Scalable question-answering system utilizing FastAPI, LangChain (LCEL), and PGVector, featuring an ingestion pipeline. Deployed on GCP Cloud Run via Terraform.

29
/ 100
Experimental

This project helps developers quickly set up a scalable question-answering system using their own documents. You put PDF files in a folder, and the system processes them, allowing users to ask questions and get answers through an API. This is for backend developers or ML engineers who need to deploy a custom RAG solution.

No commits in the last 6 months.

Use this if you are a developer looking for a pre-configured, serverless architecture to deploy a RAG-based Q&A system from PDF documents.

Not ideal if you are an end-user looking for a ready-to-use Q&A application without any coding or infrastructure setup.

backend-development cloud-deployment machine-learning-engineering serverless-architecture information-retrieval-system
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

43

Forks

6

Language

Python

License

Last pushed

Apr 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/mazzasaverio/fastapi-langchain-rag"

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