# haiku.rag

> haiku.rag — ggozad-haiku-rag. Use this tool when you need to generate human-like text responses or automate content creation tasks, solving problems such as content generation and conversational dialogue. It takes in natural language inputs and outputs coherent text responses, leveraging its integration with LanceDB, Pydantic AI, and Docling. Ideal for use cases requiring agile and informative text generation, such as chatbots or language-based applications.

Canonical page: https://skillsregistry.net/skills/ggozad-haiku-rag  
JSON: https://api.skillsregistry.net/v1/skills/ggozad-haiku-rag

## Description

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

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/ggozad/haiku.rag)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ggozad-haiku-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ggozad-haiku-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ggozad-haiku-rag/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt