# RAG Knowledge Base

> Use when building, indexing, or querying vector databases for Retrieval-Augmented Generation (RAG).

- Skill: `drvivek34/rag-knowledge-base` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add drvivek34/rag-knowledge-base`
- Raw SKILL.md: https://api.skillmd.com/api/skills/drvivek34/rag-knowledge-base/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Drvivek34 (https://skillmd.com/u/drvivek34)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/drvivek34/rag-knowledge-base

---


# Semantic Search & RAG Instructions
1. Load document strings and clean HTML/markdown syntax.
2. Chunk text using recursive character splitting (target chunk size: 500, overlap: 50).
3. Compute embeddings using model API.
4. Insert chunks and embeddings into local vector store (e.g. Chroma, FAISS).
5. For queries, embed query string and retrieve top 3 nearest chunks.
6. Format prompt template: Context + Query -> Answer.