EdIzaguirre/Rosebud

Let's discover films.

33
/ 100
Emerging

# Technical Summary Combines semantic search with dynamic metadata filtering using a self-querying retriever that translates natural language queries into structured Pinecone filters across ~7,400 films (1950–2023). Built on LangChain and OpenAI embeddings, it uses RAGAS for offline evaluation (answer relevancy, context relevancy, faithfulness) and Weights & Biases/Weave for tracking both offline metrics and online user feedback. Prefect orchestrates weekly data refreshes from The Movie Database API, while Streamlit provides the frontend and pytest ensures retrieved documents maintain correct format.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

30

Forks

15

Language

Python

License

Last pushed

Apr 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/EdIzaguirre/Rosebud"

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