skills.rest
tuyenht
tuyenhtCOMMUNITY
Explore all skills by this author →
GitHub

Vector Databases

Structure and query vector databases for semantic search and RAG.

Updated Jan 31, 2026
Search Tags:#semantic search#embeddings#vector database#RAG#AI/ML#Weaviate#Pinecone
One-click install
npx skills add https://github.com/tuyenht/Antigravity-Core --skill vector-databases-tuyenht
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Vector Databases
Source: https://github.com/tuyenht/Antigravity-Core/tree/main/.agent/skills/vector-databases
Command: npx skills add https://github.com/tuyenht/Antigravity-Core --skill vector-databases-tuyenht

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pinecone-client, openai, weaviate-client, langchain, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides expert patterns for efficiently structuring and querying vector databases, enabling advanced AI applications like semantic search and Retrieval-Augmented Generation (RAG).

Core Features & Use Cases

  • Vector Database Selection: Guidance on choosing the right vector database (Pinecone, Weaviate, pgvector).
  • Semantic Search Implementation: Examples for implementing similarity search using embeddings.
  • RAG Integration: Demonstrates how to integrate vector stores with LLMs for augmented generation.
  • Chunking & Optimization: Strategies for effective document chunking and performance tuning.

Quick Start

Use the Vector Databases skill to set up a Pinecone index for semantic search on your documents.

Frequently Asked Questions about Vector Databases

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

FAQPage Schema
How do I implement semantic search using vector databases like Pinecone or Weaviate?▼

To implement semantic search, you generate embeddings from your documents and ingest them into a vector database like Pinecone or Weaviate. This Skill provides scripts to structure data, query embeddings, and retrieve similar content efficiently.

What's the best way to set up Retrieval-Augmented Generation (RAG) with LangChain?▼

Setting up Retrieval-Augmented Generation with LangChain involves integrating your vector store with an LLM. This Skill demonstrates how to connect vector databases like Pinecone or Weaviate to LangChain for context-aware augmented generation.

How should I chunk documents for optimal RAG and vector search performance?▼

Effective document chunking for RAG involves splitting text into optimal sizes to preserve context and improve retrieval accuracy. This Skill provides strategies for chunking documents and tuning performance for vector database ingestion.

Can I use pgvector instead of Pinecone or Weaviate for AI-driven similarity search?▼

Yes, you can use pgvector for AI-driven similarity search as an alternative to Pinecone or Weaviate. This Skill includes guidance on vector database selection to help you choose the right store based on your specific AI/ML integration needs.

Do I need OpenAI API access to generate embeddings for my vector database?▼

Yes, generating embeddings for your vector database requires an embedding model. This Skill utilizes the OpenAI dependency to generate embeddings from your text data before ingesting them into Pinecone, Weaviate, or pgvector.

Related Skills

Explore More Software Engineering Skills→
lewisperez999lewisperez999

vector-embeddings

Generate text embeddings with OpenAI and search by cosine similarity in Upstash Vector or pg-vector.

Community
Intermediate
fabioc-alohafabioc-aloha
1

RAG Architecture Skill

Build RAG pipelines with document processing, chunking, embedding, and vector storage.

Community
Advanced
tuyenhttuyenht

ai-ml-pipeline

Build end-to-end AI and ML pipelines with LLM integration and RAG systems.

Community
Advanced
ricablericable
1

agentdb

Manage RuVector graph databases with Cypher queries and HNSW vector search.

Community
Advanced