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.

Active · Verified 2026-10-26 · fresh as of 2026-10-26 · 46 cited facts, 3 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T1
Created
2012 third-party fix
Latest release
not applicable — not OSS fix
License
not applicable — not OSS fix
GitHub
not applicable — no GitHub repo fix
Pricing
Pay-per-use vendor fix
Freshness
2026-10-26 fix
Layer
model-infra repo fix
Licensing
commercial vendor fix
Deployment locus
cloud vendor fix
Platform vs product
platform vendor fix
SDK languages
python, rest vendor fix
Protocols
mcp-server vendor fix

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
yes — official Snowflake-managed MCP server (Cortex Agents MCP); Snowflake-Labs/mcp community server deprecated
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.

  • Chroma T1

    Limited native hybrid (users build RRF custom). Fast Rust core (v2.5). Acquired by Replit (definitive agreement announced 2026-10-23); Chroma Cloud is winding down (writes disabled 2026-11-22, reads disabled 2026-12-22) while open-source ChromaDB continues under Apache-2.0.

  • 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.

  • Weaviate T1

    Hybrid Search 2.0 with learned ranking. BM25 + vector in unified index.

  • Milvus T1

    Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).

  • Pinecone T1

    Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .

Sources (45 cited facts, 3 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-26
    • MCP support “via official adapter — Snowflake MCP” → “yes — official Snowflake-managed MCP server (Cortex Agents MCP); Snowflake-Labs/mcp community server deprecated” source
    #258