WikiChat alternatives for AI agents.

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Collect, organize, use, and share, all in OmniBox.

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

[ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning

Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

[EMNLP'25 findings] This is the official repo for the paper, HiRAG: Retrieval-Augmented Generation with Hierarchical Knowledge.

Summarize and query from a lot of heterogeneous documents. Any LLM provider, any filetype, advanced RAG, advanced summaries, scriptable, etc

📚 Process PDFs, Word documents and more with spaCy

Bringing BERT into modernity via both architecture changes and scaling

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Chat with multiple PDFs locally

Retrieval and Retrieval-augmented LLMs

Framework for enhancing LLMs for RAG tasks using fine-tuning.

Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]