skills.rest
tranhieutt
tranhieuttCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

vector-database-engineer

Implement vector database workflows for semantic search retrieval.

70|42|Updated Mar 27, 2026
Search Tags:#semantic search#embeddings#vector database#qdrant#pinecone#milvus
One-click install
npx skills add https://github.com/tranhieutt/software_development_department --skill vector-database-engineer-tranhieutt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-database-engineer
Source: https://github.com/tranhieutt/software_development_department/tree/main/.claude/skills/vector-database-engineer
Command: npx skills add https://github.com/tranhieutt/software_development_department --skill vector-database-engineer-tranhieutt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Vector database projects demand precise embedding, indexing, and metadata strategies to deliver reliable semantic search and recommendation outcomes across Pinecone, Weaviate, Qdrant, Milvus, or pgvector. This skill captures that domain knowledge so you avoid misconfiguration, slow recall, or metadata filtering gaps that derail RAG or similarity search systems.

Core Features & Use Cases

  • Vector database selection & architecture: Evaluate workloads, latency targets, and failure domains to pick Pinecone, Weaviate, Qdrant, Milvus, or pgvector with the right index type.
  • Embedding and chunking optimization: Tune model dimensions, chunk size/overlap, and hybrid search setup while following the implementation playbook for reliability.
  • Metadata filtering and scaling: Define schemas, pre/post filters, monitoring hooks, and reindexing plans to keep large-scale operations performant for RAG, recommendation, or similarity search.

Quick Start

Ask this skill to design your embedding pipeline, chunking strategy, and vector database choice for the dataset that needs semantic search.

Frequently Asked Questions about vector-database-engineer

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

FAQPage Schema
How do I choose the right vector database for semantic search?▼

Vector database selection for semantic search depends on evaluating your workload, latency targets, and failure domains to pick Pinecone, Weaviate, Qdrant, Milvus, or pgvector with the right index type.

How do I optimize embeddings and chunking for RAG pipelines?▼

Optimize embeddings and chunking for RAG by tuning model dimensions, chunk size, and chunk overlap, then follow an implementation playbook to configure hybrid search for reliable retrieval.

Can I use metadata filtering with Qdrant or Milvus for similarity search?▼

Yes, you can use metadata filtering with Qdrant or Milvus for similarity search by defining schemas and applying pre-filter or post-filter strategies to refine your retrieval results.

What's the best way to scale a vector database for large-scale recommendation systems?▼

Scaling a vector database for recommendation systems requires defining metadata schemas, implementing monitoring hooks, and establishing reindexing plans to keep operations performant as data grows.

Why does my semantic search return slow recall results in pgvector?▼

Slow recall in pgvector semantic search often stems from embedding misconfiguration, improper chunking strategies, or metadata filtering gaps that derail the overall similarity search pipeline.

Related Skills

Explore More Data & Analytics Skills→
zeronx798zeronx798

chroma

Manage vector collections and perform similarity searches with metadata filtering.

Community
Intermediate
JCE-Joshhh77JCE-Joshhh77
16

ai-llm-engineering

Assemble end-to-end RAG pipelines with chunking, embeddings, and vector search.

Community
Advanced
HemantSudarshanHemantSudarshan

vector-database-engineer

Design and optimize vector databases for semantic search and RAG applications.

Community
Advanced
Greenmamba29Greenmamba29

vector-embedder

Generate and store vector embeddings for semantic search pipelines.

Community
Intermediate