What problem does it solve?
This Skill helps you design and operate Couchbase Full Text Search and vector search so you can find the right documents by relevance, similarity, location, or faceted filters instead of relying on brittle exact-match queries.
Core Features & Use Cases
- FTS Index Design: Define static or dynamic mappings, analyzers, field types, and doc_config settings for reliable search indexes.
- Search Query Authoring: Use match, phrase, fuzzy, wildcard, regex, geo, boosting, highlighting, and facets to express richer retrieval logic.
- Vector and Hybrid Search: Create and tune embedding-based kNN search and combine lexical and semantic ranking for AI applications.
- Troubleshooting and Tuning: Diagnose missing results, stale indexes, slow queries, analyzer mismatches, and memory pressure.
- Use Case: If you need product search, document relevance ranking, geo-proximity lookup, or semantic retrieval over embeddings, this Skill gives you the patterns and guardrails to implement it correctly.
Quick Start
Ask for help designing or debugging a Couchbase FTS or vector search index for your specific fields, analyzers, and query requirements.
