接入你的智能体
发布者自己的命令。不是 PlugMCP 端点。
用我们的密钥与日志托管一份副本。
uvx haiku-rag==0.112.0Claude Code 没有针对本地命令的安装链接。复制下方命令并在终端中运行。
claude mcp add io.github.ggozad-haiku-rag -- uvx haiku-rag==0.112.0在终端中运行。
{ "mcpServers": { "io.github.ggozad-haiku-rag": { "command": "uvx", "args": [ "haiku-rag==0.112.0" ] } }}claude_desktop_config.json
远程 URL 还是本机命令? 两种安装方式的区别
Agentic RAG that answers questions about your own documents with citations to page numbers and section headings. It runs on an embedded LanceDB database with open models through Ollama by default, so no server or API key is needed. Any provider Pydantic AI supports works in their place, and the same database can live on S3, GCS, Azure or LanceDB Cloud.
Built on LanceDB, Pydantic AI and Docling. Documentation: ggozad.github.io/haiku.rag.
haiku-ingester service (filesystem, HTTP, S3 and WebDAV sources, a SQLite or Postgres job queue with retries, a control plane and dashboard), tags and rollback, vacuum, and haiku-rag doctor health checks.Python 3.12 or newer.
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
The ingester, S3 access and model providers other than Ollama and OpenAI-compatible endpoints are extras. See Installation.
The default configuration uses Ollama for embeddings and answers. The quickstart covers the models to pull and using OpenAI instead.
haiku-rag init # create the database
haiku-rag add-src paper.pdf # index a file, URL or directory
haiku-rag search "attention mechanism"
haiku-rag ask "What datasets were used for evaluation?"
haiku-rag ask "How many documents mention transformers?"
haiku-rag ask "Does this figure match the spec?" --image figure.png
haiku-rag chat # multi-turn chat in the terminal
Continuous ingestion from configured sources runs as a separate service, with the ingester extra (pip install 'haiku.rag[ingester]'):
haiku-ingester serve
from haiku.rag.client import HaikuRAG
async with HaikuRAG("knowledge.lancedb", create=True) as rag:
await rag.create_document_from_source("paper.pdf")
await rag.create_document_from_source("https://arxiv.org/pdf/1706.03762")
results = await rag.search("self-attention")
for result in results:
print(f"{result.score:.2f} | p.{result.page_numbers} | {result.content[:100]}")
answer, citations = await rag.ask("What is the complexity of self-attention?")
print(answer)
for cite in citations:
print(f" [{cite.chunk_id}] p.{cite.page_numbers}: {cite.content[:80]}")
To compose your own agent, see Capabilities.
haiku-rag mcp --stdio
The server gives an assistant search, document reading and a Python sandbox over the documents. In Claude Code, the plugin registers it with a skill:
claude plugin marketplace add ggozad/haiku.rag
claude plugin install haiku-rag
Codex and Claude Desktop setup is in the MCP docs.
MIT.
mcp-name: io.github.ggozad/haiku-rag
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
{ "mcpServers": { "io.github.ggozad-haiku-rag": { "command": "uvx", "args": [ "haiku-rag==0.112.0" ] } }}工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
Haiku.rag 通过 stdio 在本地运行。
上次检查时间:2026-11-16。 Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval