zjunlp/OmniThink
[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
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.
Stars
489
Forks
65
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports...
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...
0verL1nk/PaperSage
📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent...
RapidFireAI/rapidfireai
RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning