emarco177/documentation-helper

Reference implementation of a RAG-based documentation helper using LangChain, Pinecone, and Tavily..

61
/ 100
Established

Implements a complete RAG pipeline with Tavily-powered web crawling for real-time documentation ingestion into Pinecone's vector database, enabling context-aware retrieval with conversational memory for coreference resolution. The Streamlit frontend orchestrates LangChain agents that combine vector similarity search with OpenAI's LLM to generate cited answers, demonstrating end-to-end retrieval-augmented generation patterns for building domain-specific documentation assistants.

271 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

271

Forks

284

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/emarco177/documentation-helper"

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