Skip to content
mcp/harbor
LangChain

haiku.rag for LangChain

io.github.ggozad/haiku-rag

Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval

client:LangChain transport:stdio runtime:pypi

Install haiku.rag in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "haiku-rag": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["haiku-rag"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

haiku.rag in other clients

haiku.rag MCP server