# vector-databases

Compares vector databases and index algorithms for RAG and semantic retrieval. Helps pick an engine based on dataset scale and metadata filtering needs.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 128 installs · ★ 7 repo stars
- Author: eyadsibai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eyadsibai/ltk/tree/HEAD/plugins/ltk-data/skills/vector-databases/SKILL.md
- Updated: 2026-01-15
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/vector-databases

## What it does

The assistant gets a decision guide for selecting vector storage across semantic search and RAG workflows. It breaks down differences between Chroma, FAISS, Qdrant, Pinecone, and Weaviate, focusing on cloud availability, scale, and metadata filtering. It also outlines index structures like Flat, IVF, HNSW, and PQ for datasets ranging from 10K items to billions of vectors.

Chroma will not handle distributed production workloads because it runs strictly as a single node. Yet it needs zero configuration for local prototypes and automatically creates embeddings from raw text. When raw throughput on GPU matters without metadata, the guide points to FAISS, whereas Qdrant handles production setups with payload filters during query execution.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill vector-databases -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill vector-databases -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill vector-databases -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eyadsibai/ltk plugins/ltk-data/skills/vector-databases
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill vector-databases -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/eyadsibai/ltk --path plugins/ltk-data/skills/vector-databases
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill vector-databases -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/eyadsibai/ltk/tree/HEAD/plugins/ltk-data/skills/vector-databases/SKILL.md

## When to use it
- choose a vector database suited for target dataset scale
- select the right index algorithm among Flat, IVF, HNSW, and PQ
- apply metadata filtering during semantic retrieval
- pick an embedded storage engine for RAG prototyping

## Example prompts
- Help me pick a vector database for a local RAG prototype
- Which index algorithm is better for fast retrieval, HNSW or IVF?
- Compare Chroma and Qdrant for production workloads with metadata filters

## Similar
- [vector-database-engineer](https://affpapa.org/en/nevibecode/agents/rohitg00-vector-database-engineer.md) — subagent · ★ 2858 repo stars
- [qdrant-vector-search](https://affpapa.org/en/nevibecode/skills/qdrant-vector-search.md) — skill · 1100 installs
- [Local FAISS MCP Server](https://affpapa.org/en/nevibecode/mcp/local-faiss-mcp-server.md) — MCP server · ★ 36 repo stars
- [AgentDB Vector Search](https://affpapa.org/en/nevibecode/skills/agentdb-vector-search.md) — skill · 1100 installs
- [surrealdb-vector](https://affpapa.org/en/nevibecode/skills/surrealdb-vector.md) — skill · 659 installs
- [databricks-vector-search](https://affpapa.org/en/nevibecode/skills/databricks-vector-search.md) — skill · 453 installs

From the same set: [eyadsibai/ltk](https://affpapa.org/en/nevibecode/by/eyadsibai/ltk.md) — 11 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
