ggozad / haiku.rag
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
Why this job: says: rag; topics: rag, document-parsing
What it does
- Ingest PDFs, office documents, HTML, Markdown and images with Docling, in-process or on docling-serve. The stored DoclingDocument keeps headings, tables, pictures and page provenance.
- Search with hybrid vector and full-text retrieval, optional reranking (cross-encoders, Jina, Cohere, Zero Entropy, vLLM, OpenRouter), section-aware context expansion, and image search with a multimodal embedder (vLLM, OpenRouter, VoyageAI,
- Answer with the RAG capability. it searches, runs sandboxed Python over the documents for counting and aggregation, and cites page numbers and headings. Vision models receive the figures. Optional capabilities compact earlier evidence in lo
- Check a citation by drawing its chunk on the page image, from the CLI, the chat TUI or Python.
- Integrate through the Python API, native Pydantic AI capabilities, plugin hooks that observe document writes and transform searches, an MCP server for Claude Code, Codex and Claude Desktop, and a reference web app.
Get started
pip install haiku.rag
# Docling, the VoyageAI and Cohere embedders, every reranker, the TUI
pip install haiku.rag-slim
# the core, with extras chosen by you- Maintenance
- Active
- Last commit yesterday
- Stars
- 655
- +9 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- 0.110.0
- Released yesterday
- Built with
- Python
- 91% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 100% closed
- 1 still open
- Pull requests
- 568 merged
- 0 waiting
- Releases
- 205
- 30+ in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| skygazer42 / MimirQ | 594 | 2 months ago | Apache-2.0 | No downloads |
| run-llama / ParseBench | 627 | 3 days ago | Apache-2.0 | No downloads |
| scub-france / docling-Studio | 271 | 6 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 91%
- TypeScript 8%
- HTML 1%
- Dockerfile <1%
Topics
- mcp-server
- rag
- lancedb
- pydantic-ai
- docling
- ag-ui
- agentic-rag
- code-execution
- code-mode
- cross-encoder
- document-ai
- document-ingestion
Project record
- JobRAG and search
- StatusListed
- Commits3,144
- Forks60
- Watching7
- Stars in 28 days+29
- CreatedOct 13, 2024
- First seen by usNov 7, 2026
- CheckedNov 9, 2026