Snowflake Cortex Search
https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-search/cortex-search-overview
Hybrid vector + keyword + semantic reranking. Cortex Agents (GA Nov 2025) orchestrate over Cortex Search for unstructured data. No separate vector infra needed inside Snowflake.
At a glance
- Type
- Hybrid vector + keyword + semantic rerank
- Tier
- T1
- Section
- Vector-database infrastructure
- Created
- 2012
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Pay-per-use
- Funding
- $1.56B pre-IPO; IPO 2020 NYSE:SNOW; $62B valuation at Dec 2024 secondary
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- overwrite
- unit
- document
- governance
- inspectable
- conflict
- last-write-wins
When to use
Optimised for: low-latency similarity search + scale
Anti-fit: not for relational / graph-heavy queries (vector-first by design)
Pros & cons
Pros
Vector + keyword search inside the data warehouse — no ETL to a separate store for shops with their corpus already in Snowflake.
Cons
Snowflake-only; query latency higher than dedicated vector DBs; pricing tied to compute warehouses.
Claims & capabilities
12%+ retrieval lift over pure vector.
Technical surface
- API surface
- REST + SQL (SEARCH_PREVIEW table function; CORTEX SEARCH service)
- Backend storage
- Snowflake (columnar)
- Deployment
- Managed-only
- Embedding model
- locked (Snowflake-managed embedding models)
- Multi-tenancy
- Indexing runs single-tenant in customer Snowflake account; multi-tenant Cortex Agents enforce isolation via immutable session attributes + row access policies
- MCP
- via official adapter — Snowflake MCP
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- first-class — Snowflake event tables + OTel
Similar systems
Other vector-database infrastructure in the catalog, ranked by inbound references.
- Qdrant T1
Distribution-Based Score Fusion + RRF. Sparse vectors native; filtering via ANN graph modification.
- pgvector T1
Stores embeddings alongside relational + full-text data. HNSW + IVFFlat ANN indexes. Used as agent conversation memory via LangChain + MCP. Foundation of Supabase AI and many self-hosted RAG stacks.
- Pinecone T1
Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .
- Chroma T1
Limited native hybrid (users build RRF custom). Fast Rust core (v2.5).
- LanceDB T1
Embedded vector DB (Arrow columnar). RRF reranker. Petabyte-scale on disk.
- MongoDB Atlas Vector Search T1
Agent memory store for both short-term (document) and long-term (vector). LangGraph checkpointer for stateful agents. Vector search extended to Community Edition (Sept 2025).