surface↓embedding↓embed_batch
Embeddingscalar · returns varchar

EMBED_BATCH

Batch embed rows and store in lars_embeddings

Per-row — runs once for each row.

embeddingembedding-modelspecialist-zootext

Arguments

nametypedescription
table_nameVARCHARSource table name (for tracking)
column_nameVARCHARColumn name (for metadata)
rows_jsonVARCHARJSON array of {id, text} objects
batch_size(optional)INTEGERBatch size (default 50)

About

Batch embed rows from a table, storing results in lars_embeddings. Accepts a JSON array of {id, text} objects. Much more efficient than per-row embedding - batches API calls (50 texts per call). SQL Usage: -- Embed from any table (DuckDB or ClickHouse) SELECT embed_batch( 'products', 'description', (SELECT to_json(list({'id': CAST(id AS VARCHAR), 'text': description})) FROM products) ); -- With batch size SELECT embed_batch('products', 'description', (SELECT ...), 100); Returns JSON stats: { "rows_embedded": 850, "batches": 17, "model": "fastembed/nomic-embed-text-v1.5", "duration_seconds": 45.2 }

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_ELASTIC

Batch embed rows and store in Elasticsearch for hybrid search

embeddingembedding-modelspecialist-zootext
scalar

EMBED_BATCH_PINECONE

Batch embed rows and store in Pinecone for vector search

embeddingembedding-modelspecialist-zooscales-large+1
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