zjunlp/OmniThink

[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

48
/ 100
Emerging

Implements an iterative think-then-write pipeline built on DSPy that simulates human cognitive reflection, using chained prompting to progressively deepen topic understanding before article generation. Integrates offline local search via RAGFlow with FAISS embeddings for retrieval-augmented generation, enabling knowledge expansion without external APIs. Provides modular evaluation across rubric grading, knowledge density, and information diversity metrics, with support for reasoning-focused models like DeepSeek-R1.

489 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

489

Forks

65

Language

Python

License

MIT

Last pushed

Aug 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/zjunlp/OmniThink"

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