hybrid-search-implementation
Combine vector and keyword search for improved retrieval
by wshobsonFree
Description
hybrid-search-implementation is an agent skill from the wshobson/agents collection for combining vector search with keyword search to improve retrieval. Vector search finds passages that mean the same thing as a query even when the words differ, while keyword search finds exact matches for names, codes and specific terms. Each approach misses things the other catches, so the skill covers architectures that run both and merge the results. It applies when implementing RAG systems that need better recall, building search engines, combining semantic understanding with exact matching, handling queries that contain specific terms such as product names or identifiers, improving search for domain-specific vocabulary that embeddings may not capture well, and cases where pure vector search misses matches that a keyword search would find. The skill starts with the core architecture of hybrid search, which shows how the two result lists are produced and combined, and it is aimed at engineers building retrieval for chatbots, document search and knowledge bases. The guidance is a pattern to adapt to your own index and data rather than a finished search engine, so the team still needs to test it on real queries. The skill is installed with the skills CLI from the wshobson/agents repository. Its skills.sh page showed about 10.5K installs.…
Highlights
- Combines vector and keyword search
- Better recall for RAG systems
- Exact matching for names and codes
- Covers domain-specific vocabulary
- Architecture for merging result lists
- Installs with the skills CLI
Ratings & Reviews
No ratings yet
Be the first to rate hybrid-search-implementation.
People also visit
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications
rag-architect
Designs and implements production-grade RAG systems by chunking documents
similarity-search-patterns
Implement efficient similarity search with vector databases
vector-index-tuning
Optimize vector index performance for latency, recall, and memory
hybrid-search-implementation FAQ
Why combine vector and keyword search?
Vector search matches meaning, keyword search matches exact terms. Each misses things the other finds, so combining them improves retrieval.
When is it useful?
For RAG systems that need better recall, queries with specific names or codes, and domain vocabulary that embeddings may handle poorly.
Does it give a finished search engine?
No. It is a set of patterns to adapt to your index and data, and it should be tested on real queries.
How are the results combined?
The skill's core concepts describe the hybrid architecture that produces and merges the two result lists.
How do I install it?
Run npx skills add https://github.com/wshobson/agents --skill hybrid-search-implementation.
What security audits does it have?
skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Warn and Snyk Pass. A Warn or Fail is worth reading before you install.
What are the best hybrid-search-implementation alternatives?
Popular alternatives to hybrid-search-implementation include embedding-strategies, rag-architect and ai-engineer. See all hybrid-search-implementation alternatives