Haiku Rag

Name: Haiku Rag
Author: ggozad

by ggozadcommunityv0.39.0

510

Haiku RAG is an agentic retrieval-augmented generation (RAG) server that integrates various AI tools for document management, search, question answering, and research workflows.

From the registry: Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling

GitHub Repository

Install & configure

Prerequisites

required
Python 3.12+
Haiku RAG requires Python 3.12 or newer
https://python.org
required
Install haiku.rag
Install via pip
```
$ pip install haiku.rag
```
https://pypi.org/project/haiku.rag/
required
Embedding provider
Configure an embedding provider (Ollama, OpenAI, VoyageAI, etc.)
https://ggozad.github.io/haiku.rag/installation/

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `haiku-rag` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Python 3.12+** — Haiku RAG requires Python 3.12 or newer (https://python.org)
- **Install haiku.rag** — Install via pip Run: `pip install haiku.rag` (https://pypi.org/project/haiku.rag/)
- **Embedding provider** — Configure an embedding provider (Ollama, OpenAI, VoyageAI, etc.) (https://ggozad.github.io/haiku.rag/installation/)

Canonical MCP server config (stdio transport):
- command: `haiku-rag`
- args: ["serve","--mcp","--stdio"]

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.