Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
$ git clone https://github.com/ggozad/haiku.rag.gitVisual document analysis studio powered by Docling — configure the extraction pipeline, inspect text, tables and bounding boxes in the browser, then chunk, embed and index into OpenSearch and Neo4j.
可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
▲ +3 ★ this week
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual intelligence (image/table captioning), agentic streaming chat, and inline citations. Powered by Gemini or local Ollama models.
Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters, and Claude Code skills from PDFs. No OCR required.
▲ +7 ★ this week
ParseBench - A Document Parsing Benchmark for AI Agents
Data from GitHub · snapshot Nov 13, 2026