# vector-database-management

A skill for Pinecone, Weaviate and Chroma: indexes, embeddings, similarity search and RAG. Useful when you need semantic search in a project.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 459 installs · ★ 62
- Author: manutej
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/manutej/luxor-claude-marketplace/tree/HEAD/plugins/luxor-database-pro/skills/vector-database-management/SKILL.md
- Updated: 2026-06-13
- HTML: https://affpapa.org/en/nevibecode/skills/vector-database-management

## What it does

The skill walks an agent through vector database work end to end: generating embeddings, creating indexes, running similarity search, filtering by metadata and managing collections. It ships Python examples for Pinecone, Weaviate and Chroma, plus a comparison table covering deployment model, index types, hybrid search and scale.

You need Python 3.8+ and a working grasp of embeddings and similarity metrics — cosine, euclidean, dot product. The examples call OpenAI, Cohere and Sentence Transformers, so each of those needs its own API key. Without a key some snippets simply won't run, which is worth checking before you paste them into a project.

Production topics are covered too: choosing between serverless and pod indexes in Pinecone, deletion protection, index tagging, and selective metadata indexing to keep memory in check. In the comparison table Chroma is pitched at local development, while Pinecone is aimed at production RAG.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill vector-database-management -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/vector-database-management/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/vector-database-management/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill vector-database-management -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/vector-database-management/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill vector-database-management -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/vector-database-management/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install manutej/luxor-claude-marketplace vector-database-management
```

2. **Manually: put the files in place**
- File: `.github/skills/vector-database-management/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill vector-database-management -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/manutej/luxor-claude-marketplace --path plugins/luxor-database-pro/skills/vector-database-management
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/vector-database-management/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill vector-database-management -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/manutej/luxor-claude-marketplace/tree/HEAD/plugins/luxor-database-pro/skills/vector-database-management/SKILL.md

## When to use it
- generate embeddings from text with OpenAI or Sentence Transformers
- create a Pinecone serverless index with the right dimension and metric
- combine metadata filtering with vector similarity search
- build a RAG pipeline on top of Chroma or Weaviate
- pick a similarity metric for a specific task

## Example prompts
- Create a Pinecone index with 1536 dimensions and cosine metric, then connect to it
- Show me how to generate embeddings with Sentence Transformers for local development
- Set up metadata filtering in Weaviate for document search

## Similar
- [vector-database-engineer](https://affpapa.org/en/nevibecode/agents/vector-database-engineer.md) — subagent · ★ 41729
- [upstash-vector-js](https://affpapa.org/en/nevibecode/skills/upstash-vector-js.md) — skill · 1300 installs
- [rag-implementation](https://affpapa.org/en/nevibecode/skills/rag-implementation.md) — skill · 13906 installs
- [pinecone-rag](https://affpapa.org/en/nevibecode/skills/pinecone-rag.md) — skill · 24 installs
- [rag-architect](https://affpapa.org/en/nevibecode/skills/httpsgithubcomjeffallan-rag-architect.md) — skill · 4700 installs
- [langchain4j-vector-stores-configuration](https://affpapa.org/en/nevibecode/skills/langchain4j-vector-stores-configuration.md) — skill · 3700 installs

From the same set: [manutej/luxor-claude-marketplace](https://affpapa.org/en/nevibecode/by/manutej/luxor-claude-marketplace.md) — 31 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md