skills.rest
librefang
librefangOFFICIAL
Explore all skills by this author →
WebsiteGitHub

vector-db

Design and optimize vector search systems for embedding-based retrieval.

10|7|Updated Mar 14, 2026
Search Tags:#indexing#embeddings#rag#hnsw#vector-search#similarity-search#hybrid-retrieval
One-click install
npx skills add https://github.com/librefang/librefang-registry --skill vector-db-librefang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-db
Source: https://github.com/librefang/librefang-registry/tree/main/skills/vector-db
Command: npx skills add https://github.com/librefang/librefang-registry --skill vector-db-librefang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Vector search systems require expertise in embeddings, indexing, and retrieval patterns to deliver fast, relevant results at scale.

Core Features & Use Cases

  • Embedding selection and tuning for domain-specific retrieval
  • Indexing strategy guidance (HNSW, IVF, flat) balancing latency, memory, and recall
  • Hybrid retrieval combining dense vectors with keyword search for robust results
  • RAG workflow design for knowledge augmentation with source citations

Quick Start

Construct a minimal vector search pipeline by selecting an embedding model, choosing an index type, and enabling a basic RAG workflow.

Frequently Asked Questions about vector-db

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

FAQPage Schema
How do I choose between HNSW, IVF, and flat indexing for vector search?▼

Vector search indexing strategies balance latency, memory, and recall. HNSW prioritizes low latency, IVF optimizes memory at scale, and flat indexing provides exact similarity search results for smaller datasets.

What is hybrid retrieval and how does it improve RAG pipelines?▼

Hybrid retrieval combines dense vector search with keyword search to deliver robust results. This integration improves RAG pipelines by matching both semantic meaning and exact terms for accurate knowledge augmentation.

How do I select and tune embeddings for domain-specific similarity search?▼

Embedding selection for similarity search requires matching the model to your domain's vocabulary. Tuning involves adjusting chunking strategies and evaluating retrieval relevance to optimize embedding-based search architectures.

What chunking strategies work best for semantic search and RAG workflows?▼

Chunking strategies for semantic search and RAG workflows depend on document structure and embedding model limits. Optimizing chunk size and overlap ensures relevant context is captured without degrading vector search retrieval latency.

Can I build a scalable vector search system for production deployment?▼

Production deployment of vector search systems requires specifying embedding selection, configuring indexing algorithms, and enabling hybrid retrieval. This builds a scalable retrieval architecture suitable for high-volume semantic search and RAG pipelines.

Related Skills

Explore More Software Engineering Skills→
haxlyshaxlys

embedding-strategies

Select embedding models and configurations for semantic search pipelines.

Community
Advanced
Kingly-AgencyKingly-Agency

rag-implementation

Build RAG pipelines that ground LLM responses with retrieved external knowledge.

Official
Advanced
ionmidoriionmidori

implementing-hybrid-search

Combine vector and keyword search results using Reciprocal Rank Fusion.

Community
Intermediate
ccfccf

vector-index-tuning

Tune HNSW parameters and quantization for large-scale vector search indexes.

Community
Advanced