Skills

A skill is a package of structured files that teaches an AI coding agent how to work with a specific tool or framework. The skill below was generated by Great Docs from this project’s documentation. Install it in your agent and it will be able to run commands, edit configuration, write content, and troubleshoot problems without step-by-step guidance from you.

Any agent — install with npx:

npx skills add posit-dev/raghilda

Codex / OpenCode

Tell the agent:
Fetch the skill file from https://github.com/posit-dev/raghilda and follow the instructions.

Manual — download the skill file:

curl -O <site-url>/skill.md

Or browse the SKILL.md file.

SKILL.md

---
name: raghilda
description: >
  RAG made simple. Use when writing Python code that uses the raghilda package.
license: MIT
compatibility: Requires Python >=3.11, <3.14.
---

# raghilda

RAG made simple

## Installation

```bash
pip install raghilda
```

## API overview

### Store

Vector storage backends for storing and retrieving chunks

- `store.BaseStore`
- `store.DuckDBStore`
- `store.ChromaDBStore`
- `store.OpenAIStore`
- `store.PostgreSQLStore`

### Crawl

Crawlers for discovering and converting source documents

- `crawl.CrawlScope`
- `crawl.FetchedSource`
- `crawl.BaseCrawler`
- `crawl.DirectoryCrawler`
- `crawl.WebCrawler`
- `crawl.CloudflareCrawler`

### Embedding

Embedding providers for generating vector representations

- `embedding.EmbeddingProvider`
- `embedding.EmbedInputType`
- `embedding.EmbeddingOpenAI`
- `embedding.EmbeddingCohere`
- `embedding.EmbeddingSentenceTransformers`

### Chunker

Text chunking utilities for splitting documents

- `chunker.BaseChunker`
- `chunker.MarkdownChunker`

### Utilities

Utility functions for reading and scraping content

- `read.read_as_markdown`
- `scrape.find_links`

### Chunk

Chunk data types

- `chunk.Chunk`
- `chunk.MarkdownChunk`
- `chunk.RetrievedChunk`
- `chunk.Metric`

### Document

Document types for unchunked and chunked content

- `document.Document`
- `document.ChunkedDocument`
- `document.MarkdownDocument`
- `document.ChunkedMarkdownDocument`

### Types

Protocol types for type checking compatibility

- `types.ChunkLike`
- `types.ChunkedDocumentLike`
- `types.DocumentLike`
- `types.ChunkerLike`
- `types.IntoChunk`
- `types.IntoDocument`

## Resources

- [llms.txt](llms.txt) — Indexed API reference for LLMs
- [llms-full.txt](llms-full.txt) — Comprehensive documentation for LLMs
- [Source code](https://github.com/posit-dev/raghilda)