harvard-lil/warc-gpt

WARC + AI - Experimental Retrieval Augmented Generation Pipeline for Web Archive Collections.

41
/ 100
Emerging

Extracts text from HTML and PDF records in WARC files, generates embeddings with automatic context-window splitting, and stores them in a vector database (ChromaDB) for semantic search. Supports multiple LLM backends including OpenAI, Ollama, and OpenAI-compatible providers like HuggingFace and vLLM through configurable environment variables. Provides both REST API and web UI with chat history support, plus T-SNE visualization of the embedding space.

270 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

270

Forks

25

Language

Python

License

MIT

Last pushed

Feb 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/harvard-lil/warc-gpt"

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