skills.rest
roanbrasil
roanbrasilCOMMUNITY
Explore all skills by this author →
Website𝕏@roanbrasilGitHub

vector-databases

Configure and query pgvector, Chroma, Weaviate, Pinecone, and Qdrant for similarity search.

5|1|Updated Jun 17, 2026
Search Tags:#rag#hnsw#semantic-search#vector-databases#hybrid-search#vector-querying#production-optimization
One-click install
npx skills add https://github.com/roanbrasil/engineer-grade-agent-skills --skill vector-databases-roanbrasil
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-databases
Source: https://github.com/roanbrasil/engineer-grade-agent-skills/tree/main/skills/vector-databases
Command: npx skills add https://github.com/roanbrasil/engineer-grade-agent-skills --skill vector-databases-roanbrasil

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill eliminates the guesswork and trial-and-error of working with vector databases for high-dimensional similarity search, hybrid search, and production-scale embedding workloads, ensuring you select the right tool, configure it correctly, and avoid common performance pitfalls.

Core Features & Use Cases

  • Multi-Database Coverage: Provides idiomatic setup, query, and optimization guidance for pgvector, Chroma, Weaviate, Pinecone, and Qdrant, the most widely used vector databases in production.
  • Algorithm & Tuning Guidance: Includes detailed explanations of ANN algorithms (HNSW, IVF, flat), index parameter tuning, metadata filtering, hybrid search, and multi-tenancy configuration.
  • Real-World Use Case: For example, if you are building a RAG system that needs to scale from 10,000 to 10 million+ document embeddings, use this skill to pick the optimal database, configure an HNSW index for cosine similarity, and implement filtered hybrid search for accurate, low-latency results.

Quick Start

Use the vector-databases skill to select the optimal vector database for your RAG system, configure an HNSW index for cosine similarity, and implement a filtered hybrid search query for your document corpus.

Frequently Asked Questions about vector-databases

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I choose the best vector database for a large-scale RAG system?▼

To choose a vector database for large-scale RAG, evaluate pgvector, Chroma, Weaviate, Pinecone, and Qdrant based on your specific scale, hybrid search requirements, and multi-tenancy needs to ensure optimal production performance.

What's the best way to configure an HNSW index for cosine similarity?▼

Configuring an HNSW index for cosine similarity requires tuning approximate nearest neighbor parameters to balance search latency and accuracy for high-dimensional embedding workloads in your chosen vector database.

How does hybrid search work with metadata filtering in vector databases?▼

Hybrid search combines vector similarity search with full-text queries and metadata filtering, enabling highly accurate document retrieval by restricting the search space using specific scalar attributes alongside high-dimensional embeddings.

Does pgvector support multi-tenancy for production document retrieval?▼

Yes, pgvector supports multi-tenancy by isolating tenant data through schema separation or metadata filtering, allowing you to manage isolated document retrieval workloads within a single relational database deployment.

When should I use approximate nearest neighbor algorithms instead of flat search?▼

Use approximate nearest neighbor algorithms like HNSW or IVF instead of flat search when scaling to millions of embeddings, as flat search becomes computationally expensive and introduces unacceptable query latency.

Related Skills

Explore More Software Engineering Skills→
ricablericable

sentence-transformers

Generate normalized text and sentence embeddings for semantic similarity workflows.

Community
Intermediate
jxtngxjxtngx
2

langchain-rag

Orchestrate document ingestion, chunking, embedding, and semantic search for RAG pipelines.

Community
Advanced
vecearvecear

embedding-pipeline-builder

Build document embedding and retrieval pipelines for scalable semantic search.

Community
Advanced
Arupbiswas09Arupbiswas09

distributed-search

Implement relevance-based text search with inverted index and TF-IDF/BM25 ranking.

Community
Advanced