agentmods.dev

using-vector-databases

using-vector-databases is a skill for Claude Code from ancoleman/ai-design-components. It costs 79 tokens per session (3,646 once invoked), scanned A, original, MIT.

A guide to vector databases, which store numerical representations of text, images, or other data so similar items can be found by meaning. It covers their use in semantic search, recommendations, and RAG, a method that retrieves relevant information for an AI response.

In plain words
What is it for?
Use it for chatbots over private documents, meaning-based search, recommendations, similarity and duplicate detection, and search across text, images, or audio.
Why use it?
It helps AI applications find relevant information even when the search words do not match exactly. It also addresses database choice, embeddings, document splitting, and filtering.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the backend-data-skills plugin — 6 skills shipped together

not rated 525repo +1 10mo ago A scan 79 tokens original MIT

Good fit Use it for chatbots over private documents, meaning-based search, recommendations, similarity and duplicate detection, and search across text, images, or audio.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ancoleman/ai-design-components/using-vector-databases
View source ↗ ancoleman/ai-design-components
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ancoleman/ai-design-components --skill using-vector-databases
Clone the repo
git clone --depth 1 https://github.com/ancoleman/ai-design-components

Made for: Claude Code.

Or install backend-data-skills, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for using-vector-databases

README.md
[![agentmods](https://agentmods.dev/badge/skills/ancoleman/ai-design-components/using-vector-databases/github.svg)](https://agentmods.dev/skills/ancoleman/ai-design-components/using-vector-databases)
Your own site
<a href="https://agentmods.dev/skills/ancoleman/ai-design-components/using-vector-databases"><img src="https://agentmods.dev/badge/skills/ancoleman/ai-design-components/using-vector-databases/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for using-vector-databases

Your own site · 80×15
<a href="https://agentmods.dev/skills/ancoleman/ai-design-components/using-vector-databases"><img src="https://agentmods.dev/badge/skills/ancoleman/ai-design-components/using-vector-databases.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,646 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.03646
Opus 5.5 $0.00032 $0.01458
Sonnet 5.5 $0.00016 $0.00729
Haiku 4.5 $0.00008 $0.00365

Measured 1mo ago against content hash 5495131a7c6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

using-vector-databases scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 5 executable files (examples/qdrant-python/main.py, examples/qdrant-python/rag_pipeline.py, scripts/benchmark_similarity.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/using-vector-databases/SKILL.md · 475 lines

How it starts

The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vector Databases for AI Applications

When to Use This Skill

Use this skill when implementing:

  • RAG (Retrieval-Augmented Generation) systems for AI chatbots
  • Semantic search capabilities (meaning-based, not just keyword)
  • Recommendation systems based on similarity
  • Multi-modal AI (unified search across text, images, audio)
  • Document similarity and deduplication
  • Question answering over private knowledge bases

Quick Decision Framework

1. Vector Database Selection

START: Choosing a Vector Database

EXISTING INFRASTRUCTURE?
├─ Using PostgreSQL already?
│  └─ pgvector (<10M vectors, tight budget)
│      See: references/pgvector.md
│
└─ No existing vector database?
   │
   ├─ OPERATIONAL PREFERENCE?
   │  │
   │  ├─ Zero-ops managed only
   │  │  └─ Pinecone (fully managed, excellent DX)
   │  │      See: references/pinecone.md
   │  │
   │  └─ Flexible (self-hosted or managed)
   │     │
   │     ├─ SCALE: <100M vectors + complex filtering ⭐
   │     │  └─ Qdrant (RECOMMENDED)
   │     │      • Best metadata filtering
   │     │      • Built-in hybrid search (BM25 + Vector)
   │     │      • Self-host: Docker/K8s
   │     │      • Managed: Qdrant Cloud
   │     │      See: references/qdrant.md
   │     │
   │     ├─ SCALE: >100M vectors + GPU acceleration
   │     │  └─ Milvus / Zilliz Cloud
   │     │      See: references/milvus.md
   │     │
   │     ├─ Embedded / No server
   │     │  └─ LanceDB (serverless, edge deployment)
   │     │
   │     └─ Local prototyping
   │        └─ Chroma (simple API, in-memory)

2. Embedding Model Selection

REQUIREMENTS?

├─ Best quality (cost no object)
│  └─ Voyage AI voyage-3 (1024d)
│      • 9.74% better than OpenAI on MTEB
│      • ~$0.12/1M tokens
│      See: references/embedding-strategies.md
│
├─ Enterprise reliability
│  └─ OpenAI text-embedding-3-large (3072d)
│      • Industry standard
│      • ~$0.13/1M tokens
│      • Maturity shortening: reduce to 256/512/1024d
│
├─ Cost-optimized
│  └─ OpenAI text-embedding-3-small (1536d)
│      • ~$0.02/1M tokens (6x cheaper)
│      • 90-95% of large model performance
│
├─ Multilingual (100+ languages)
│  └─ Cohere embed-v3 (1024d)
│      • ~$0.10/1M tokens
│
└─ Self-hosted / Privacy-critical
   ├─ English: nomic-embed-text-v1.5 (768d, Apache 2.0)
   ├─ Multilingual: BAAI/bge-m3 (1024d, MIT)
   └─ Long docs: jina-embeddings-v2 (768d, 8K context)

Read the full file on GitHub · 475 lines

Files

What ships with it

21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 475 lines · 79 tokens per session scan A 5495131a7c6f

Subscribe to this mod's changes

using-vector-databases is a skill published in the GitHub repository ancoleman/ai-design-components (525 stars, last pushed 10mo ago), licensed MIT. It adds 79 tokens to every session and 3,646 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Claude CodeData and AIRAG and vectorsai-designanthropicclaudeclaude-skillsdesign-system
Related

Other skills, from other repositories

langchain-development

Expert guidance for LangChain and LangGraph development with Python, covering chain composition, agents, memory, and RAG implementations.

Mindrally/skills · 29 tokens

ai-product

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.

lingxling/awesome-skills-cn · 28 tokens

ai-pipeline-orchestration

Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.

lingxling/awesome-skills-cn · 39 tokens

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

lingxling/awesome-skills-cn · 47 tokens

ai-ml

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

lingxling/awesome-skills-cn · 30 tokens

langchain

Apply when building LangChain pipelines, LCEL chains, agents, or retrieval-augmented generation systems.

sordi-ai/skill-everything · 24 tokens