skills.rest
k1lgor
k1lgorCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

search-vector-architect

Implement hybrid search with Elasticsearch, Pinecone, Chroma, or pgvector.

2|Updated Feb 3, 2026
Search Tags:#search#RAG#elasticsearch#embedding#vector-search#opensearch#hybrid-search
One-click install
npx skills add https://github.com/k1lgor/virtual-company --skill search-vector-architect
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: search-vector-architect
Source: https://github.com/k1lgor/virtual-company/tree/main/skills/23-search-vector-architect
Command: npx skills add https://github.com/k1lgor/virtual-company --skill search-vector-architect

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables fast, accurate retrieval across both keyword-based and embedding-based search for AI-powered applications.

Core Features & Use Cases

  • Elasticsearch/OpenSearch setup with proper mappings and analyzers for text relevance.
  • Vector search integration with Pinecone, Chroma, or pgvector to store and query embeddings.
  • Hybrid search blending BM25 and vector similarity for improved results.
  • RAG pipelines that chunk documents and feed top chunks to LLMs for answering questions.

Quick Start

Set up a basic Elasticsearch/OpenSearch index and a simple vector store with OpenAI embeddings to enable retrieval.

Frequently Asked Questions about search-vector-architect

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

FAQPage Schema
How do I set up hybrid search blending BM25 and vector similarity?▼

Hybrid search combining BM25 and vector similarity is achieved by configuring Elasticsearch/OpenSearch mappings and analyzers alongside a vector store like Pinecone or Chroma. This blends keyword relevance with embedding similarity to deliver more accurate document retrieval.

What is the best way to build a RAG pipeline for document retrieval with Elasticsearch?▼

Building a RAG pipeline with Elasticsearch involves chunking documents and feeding the top retrieved chunks to LLMs for answering questions. It requires proper index mappings and analyzers to ensure accurate text relevance during retrieval.

Does pgvector work with OpenSearch for embedding-based search?▼

pgvector and OpenSearch serve as distinct vector store options for embedding-based search. You can configure OpenSearch with proper mappings and analyzers for text relevance, or use pgvector to store and query embeddings within PostgreSQL for AI applications.

How do I integrate OpenAI embeddings into a vector store for AI applications?▼

Integrating OpenAI embeddings involves connecting your embedding model to vector stores like Pinecone, Chroma, or pgvector. This setup enables fast, accurate storage and querying of embeddings for AI-powered retrieval workflows.

When do I need custom analyzers for vector search in Elasticsearch?▼

Custom analyzers in Elasticsearch are needed when configuring hybrid search workflows that blend keyword-based BM25 relevance with vector similarity. Proper mappings and analyzers ensure accurate text matching before combining scores with embedding results.

Related Skills

Explore More Software Engineering Skills→
patrykkopycinskipatrykkopycinski
6

zero-to-elastic

Provision Elasticsearch infrastructure and generate client connection snippets.

Community
Advanced
zilliztechzilliztech
3

multi-hop-rag

Decompose questions, retrieve across documents, and synthesize cited answers.

Official
Advanced
ccfccf

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications.

Community
Intermediate
patricio0312revpatricio0312rev
5

vector-db-setup

Configure Pinecone, Chroma, pgvector, and Qdrant vector databases for semantic search.

Community
Advanced