skills.rest
0xMerl99
0xMerl99COMMUNITY
Explore all skills by this author →
GitHub

vector-db

Guide vector database operations, embedding selection, indexing, and RAG patterns.

1|Updated Mar 2, 2026
Search Tags:#indexing#semantic search#embeddings#vector database#RAG#retrieval
One-click install
npx skills add https://github.com/0xMerl99/FangAI --skill vector-db-0xmerl99
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-db
Source: https://github.com/0xMerl99/FangAI/tree/main/crates/openfang-skills/bundled/vector-db
Command: npx skills add https://github.com/0xMerl99/FangAI --skill vector-db-0xmerl99

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the complexities of building and optimizing systems for semantic search, recommendation engines, and knowledge augmentation for LLMs, ensuring efficient and accurate retrieval of information.

Core Features & Use Cases

  • Embedding Strategy: Guidance on selecting and using embedding models for various domains.
  • Indexing and Search: Expertise in choosing and configuring vector indexes (HNSW, IVF) and distance metrics.
  • RAG Implementation: Detailed patterns and techniques for Retrieval-Augmented Generation pipelines.
  • Use Case: Implement a RAG system for your company's internal documentation, allowing employees to ask natural language questions and receive accurate answers sourced directly from the documents.

Quick Start

Consult the skill for advice on selecting an embedding model and configuring an HNSW index for a new vector database.

Frequently Asked Questions about vector-db

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

FAQPage Schema
How do I choose the right embedding model for a semantic search system?▼

Selecting an embedding model for semantic search depends on your specific domain, as this Skill provides guidance on evaluating and choosing models to ensure accurate vector representations of your data.

What is the best way to configure HNSW indexing for a vector database?▼

Configuring HNSW indexing for a vector database involves tuning specific parameters for efficient retrieval, and this Skill offers expertise in choosing and setting up HNSW and IVF indexes.

How do I implement Retrieval-Augmented Generation (RAG) for internal documentation?▼

Implementing Retrieval-Augmented Generation for internal documentation requires specific pipeline patterns, and this Skill details techniques to source accurate answers directly from your documents.

When should I use hybrid search instead of standard semantic search?▼

Hybrid search is used instead of standard semantic search when you need to combine keyword and vector retrieval, a technique covered here alongside chunking strategies and evaluation metrics.

What distance metrics work best for vector database retrieval?▼

Vector database retrieval relies on distance metrics to measure similarity, and this Skill provides expertise in choosing and configuring the appropriate metrics for optimal performance.

What chunking strategies improve retrieval performance in RAG systems?▼

Chunking strategies improve retrieval performance in RAG systems by optimizing how documents are split, and this Skill covers chunking techniques alongside evaluation metrics for optimal results.

Related Skills

Explore More Software Engineering Skills→
giuseppe-trisciuogliogiuseppe-trisciuoglio
322

chunking-strategy

Chunk documents into semantically meaningful segments for RAG systems.

Community
Advanced
floflo777floflo777
33

rag-eval

Evaluate RAG systems using retrieval, generation, and latency metrics.

Community
Intermediate
ryasrkryasrk

prompt-engineering

Design system prompts, RAG pipelines, and tool-calling workflows for LLM providers.

Community
Advanced
BEKO2210BEKO2210
15

search

Search knowledge bases semantically with vector embeddings and keyword fallback.

Community
Advanced