machinelearningZH/deep-research

Powerful, automated research and analysis across your own document collections.

26
/ 100
Experimental

Implements iterative multi-step research workflows with hybrid search (semantic + keyword) over chunked documents indexed in Weaviate, using configurable tiered LLM models via OpenRouter for query generation, relevance checking, and analysis. Supports parallel LLM calls for speed, deduplication across iterations, and full document analysis—enabling customizable workflows on sensitive data without external contamination, with exports to formatted Word documents.

No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

MIT

Last pushed

Dec 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/machinelearningZH/deep-research"

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