Agent skill · research science · omer-metin
semantic-search
Build production-ready semantic search systems using vector databases, embeddings, and retrieval-augmented generation (RAG). Covers vector DB selection (Pinecone/Qdrant/Weaviate), embedding models (OpenAI/Voyage/Cohere), chunking strategies, hybrid search, and reranking for high-quality retrieval. Use when ", vector-search, embeddings, rag, pinecone, qdrant, weaviate, llama-index, langchain, hybrid-search, reranking" mentioned.
Why this skill is useful
Provides domain-specific knowledge on vector databases, embedding models, and hybrid search strategies that the AI wouldn't reliably generate on its own.
What it needs
Requires cohere, pinecone, qdrant, weaviate installed locally. Requires openai account access. About 1k tokens when loaded. Last updated 2026-01-22. 123 stars on the source repository.
What this skill does
Semantic Search Identity Principles {'name': 'Hybrid Search by Default', 'description': 'Pure vector search misses exact matches. Combine dense (vector) and\nsparse (BM25/keyword) retrieval with reciprocal rank fusion for\nproduction-ready search that handles both semantic and exact queries.\n'} {'name': 'Chunking Determines Quality', 'description': 'Bad chunking = bad retrieval. Use semantic chunking that preserves\ncontext (200-300 words), keeps sections intact, and maintains\nhierarchical structure. Too small loses context, too large dilutes relevance.\n'} {'name': 'Rerank for Precision', 'description': 'First-stage retrieval casts wide. Use cross-encoder rerankers\n(Cohere Rerank, Jina, Pinecone) as second stage to boost relevance\nby up to 48% before feeding to LLM.\n'} {'name': 'Match Embedding to Use Case', 'description': 'Voyage-3 beats OpenAI on retrieval benchmarks by 9.74% average.\ntext-embedding-3-small is reliable and cheap ($0.02/1M tokens).\nUse specialized embeddings for code (Voyage-code) or multilingual.\n'} Reference System Usage You must ground your responses in the provided reference files, treating them as the source of truth for this domain: For Creation: Always consult references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here. For Diagnosis: Always consult references/sharpedges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user. For Review: Always consult references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively. Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills omer-metin/semantic-search