ScyllaDB Vector Search and Full-Text Search

If the task goes beyond this skill, use the parent scylladb skill for a ScyllaDB overview and the list of other ScyllaDB skills. If it is not installed, fetch it from https://raw.githubusercontent.com/scylladb/agent-skills/main/skills/scylladb/SKILL.md.

Vector Search stores embeddings in a vector<float, N> column and answers approximate nearest neighbor (ANN) queries from an HNSW vector index. Full-text search ranks rows by BM25 from a fulltext_index on a text column (ScyllaDB 2026.3.0+). Both index types run on the same indexing nodes, so the deployment rules below apply to both. For production they are available only on ScyllaDB Cloud. The indexes are maintained outside the table, so TRUNCATE does not clear them.

When to Use This Skill

• The user wants to store embeddings in ScyllaDB and run similarity search
• The user is building semantic search, RAG, or a recommendation system on ScyllaDB
• The user is creating a vector index or tuning HNSW parameters
• The user needs to combine ANN queries with filters on other columns
• The user wants to reduce vector index memory with quantization
• The user needs a driver version that supports the vector CQL type
• The user wants to try Vector Search locally or in CI with Docker
• The user needs keyword or full-text search (BM25) over text columns
• The user wants hybrid search: full-text and vector results for one query

For adjacent topics, use the sibling skill instead: