surface↓embedding↓embed_batch_pinecone
Embeddingscalar · returns varchar

EMBED_BATCH_PINECONE

Batch embed rows and store in Pinecone for vector search

Per-row — runs once for each row.

embeddingembedding-modelspecialist-zooscales-largetext

Arguments

nametypedescription
table_nameVARCHAR—
column_nameVARCHAR—
rows_jsonVARCHAR—
batch_size(optional)INTEGER—
namespace(optional)VARCHAR—

About

Batch embed rows from a table, storing results in Pinecone. Uses LARS's on-box embedding model (nomic-ai/nomic-embed-text-v1.5, 768 dims) and upserts to Pinecone with metadata for filtering. Supports namespaces for multi-tenancy. SQL Usage: -- Basic (default namespace): LARS EMBED products.description USING (SELECT id::VARCHAR AS id, description AS text FROM products) WITH (backend='pinecone'); -- With custom namespace: LARS EMBED products.description USING (SELECT id::VARCHAR AS id, description AS text FROM products) WITH (backend='pinecone', namespace='products_v2', batch_size=100); Returns JSON stats: { "rows_embedded": 850, "batches": 9, "model": "fastembed/nomic-embed-text-v1.5", "duration_seconds": 12.4, "backend": "pinecone", "namespace": "products_v2" }

Nearby rabbit holes

same domain
scalar

EMBED

Generate 768-dim embedding vector from text (on-box nomic-embed-text-v1.5)

embeddingembedding-modelspecialist-zooscales-large+1
scalar

EMBED_BATCH

Batch embed rows and store in lars_embeddings

embeddingembedding-modelspecialist-zootext
scalar

EMBED_BATCH_ELASTIC

Batch embed rows and store in Elasticsearch for hybrid search

embeddingembedding-modelspecialist-zootext
scalar

EMBED_STATUS

Check embedding coverage for a table/column

embeddingembedding-modelspecialist-zootext
scalar

EMBED_WITH_STORAGE

Generate embedding and store with table/column/ID tracking

embeddingembedding-modelspecialist-zootext
scalar

IMAGE_EMBED

SigLIP 2 embedding for an image (L2-normalized, shared image/text space)

embeddingembedding-modelspecialist-zooimage
Climb back to The Looking Glass