skills.rest
AndyAnh174
AndyAnh174COMMUNITY
Explore all skills by this author →
WebsiteGitHub

vector-database-engineer

Designs vector search systems with database selection, embedding configuration, and hybrid search integration.

Updated Feb 26, 2026
Search Tags:#embeddings#rag#vector#chunking#semantic-search#vector-databases#index-configuration
One-click install
npx skills add https://github.com/AndyAnh174/wellness --skill vector-database-engineer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-database-engineer
Source: https://github.com/AndyAnh174/wellness/tree/main/.agent/skills/vector-database-engineer
Command: npx skills add https://github.com/AndyAnh174/wellness --skill vector-database-engineer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps organizations design and optimize vector-based search systems by selecting appropriate vector databases, embedding strategies, and index configurations to enable fast, accurate semantic retrieval and recommendations.

Core Features & Use Cases

  • Vector database selection and architecture
  • Embedding model selection and optimization
  • Index configuration (HNSW, IVF, PQ)
  • Hybrid search (vector + keyword) implementation
  • Chunking strategies for documents
  • Metadata filtering and pre/post-filtering

Quick Start

Configure a simple vector search pipeline using an appropriate embedding model and a small dataset to run a semantic query.

Frequently Asked Questions about vector-database-engineer

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

FAQPage Schema
How do I build a scalable vector search pipeline for RAG applications?▼

Build a scalable vector search pipeline by selecting an appropriate vector database, configuring embedding models, and setting up index configurations like HNSW or IVF for fast semantic retrieval in RAG.

What's the best way to configure HNSW and IVF indexes for vector databases?▼

Configure HNSW and IVF indexes by tuning parameters for your specific dataset scale to balance search latency and accuracy, ensuring the vector database delivers fast, accurate semantic retrieval.

How do I implement hybrid search combining vector similarity and keyword matching?▼

Implement hybrid search by integrating vector similarity scores with keyword matching, applying chunking strategies and metadata filtering to improve retrieval performance across recommendations and similarity tasks.

What chunking strategies should I use for document embeddings in semantic search?▼

Select document chunking strategies that segment text into meaningful units before generating embeddings, optimizing the semantic search pipeline for accurate retrieval and efficient metadata pre-filtering or post-filtering.

When should I use product quantization (PQ) for vector index configuration?▼

Use product quantization (PQ) for vector index configuration when you need to compress high-dimensional embeddings to reduce memory usage and maintain scalable retrieval performance across large datasets.

Does this vector search pipeline support metadata filtering and reindexing strategies?▼

The vector search pipeline supports end-to-end deployment with metadata pre-filtering and post-filtering, scalable indexing, monitoring, and reindexing strategies to maintain fast and accurate semantic retrieval.

Related Skills

Explore More Data & Analytics Skills→
dotlab-hqdotlab-hq

langchain-rag

Build RAG pipelines that ingest, chunk, embed, and retrieve documents for LLMs.

Official
Intermediate
ccfccf

hybrid-search-implementation

Combine vector similarity with keyword matching for hybrid retrieval.

Community
Intermediate
rfdiosuaorfdiosuao
30

vector-db

Guide vector database operations, embedding selection, indexing, and RAG pipeline design.

Community
Advanced
JamesFincherJamesFincher

faiss

Perform k-NN similarity search over dense float32 vectors using FAISS index structures.

Community
Intermediate