# RAG Local Lancedb

> Build, query, and manage local vector embeddings and semantic search pipelines using LanceDB and HuggingFace/SentenceTransformers embeddings without cloud dependencies.

- Skill: `pedroiff0/rag-local-lancedb` (Agent Skill)
- Install (CLI): `npx skillmds@latest add pedroiff0/rag-local-lancedb`
- Raw SKILL.md: https://api.skillmd.com/api/skills/pedroiff0/rag-local-lancedb/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- License: MIT
- Author: pedroiff0 (https://skillmd.com/u/pedroiff0)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/pedroiff0/rag-local-lancedb

---


# Local RAG with LanceDB

This skill guides the construction and query execution of serverless, high-performance local vector databases using LanceDB and local embeddings.

## When to Use

- Building offline semantic search across local Markdown files, codebases, or documentation.
- Storing vector embeddings with zero external cloud API costs.
- Performing hybrid full-text + vector similarity queries.

## Quick Setup & Python Usage

```python
import lancedb

# Connect to local database directory
db = lancedb.connect("~/.local/share/agent_rag")
```