surface↓search↓vector_search_pinecone
Searchaggregate · returns table

VECTOR_SEARCH_PINECONE

Pure semantic search in Pinecone

Per-group — reads the whole group in one call.

searchllmtext

Arguments

nametypedescription
queryVARCHAR—
source_table(optional)VARCHAR—
limit_(optional)INTEGER—
threshold(optional)DOUBLE—
namespace(optional)VARCHAR—

About

Semantic vector search using Pinecone. Performs pure semantic similarity search using Pinecone's optimized ANN index. Supports namespaces for multi-tenant or versioned embeddings. SQL Usage: -- Basic search (default namespace): SELECT * FROM PINECONE_SEARCH('climate change', bird_line.text, 10); -- Search specific namespace: SELECT * FROM PINECONE_SEARCH('sustainability', products.description, 20, 0.6, 'products_v2'); Returns columns: id, text, similarity, score

Nearby rabbit holes

same domain
aggregate

VECTOR_SEARCH

Find similar documents via vector search

searchllmtext
aggregate

VECTOR_SEARCH_ELASTIC

Hybrid semantic + keyword search in Elasticsearch

searchllmtext
scalar

WEB_MAP

Discover URLs on a website and return them as a table

searchexternal-apiurl
scalar

WEB_SEARCH

Search the web and return results as a table (via Firecrawl)

searchexternal-apiurl
Climb back to The Looking Glass