Generate embedding and store with table/column/ID tracking
Per-row — runs once for each row.
| name | type | description |
|---|---|---|
| text | VARCHAR | Text to embed |
| model(optional) | VARCHAR | Optional model |
| source_table | VARCHAR | Source table name |
| column_name | VARCHAR | Source column name |
| source_id | VARCHAR | Source row ID |
Generate 768-dim embedding vector from text (on-box nomic-embed-text-v1.5)
Batch embed rows and store in lars_embeddings
Batch embed rows and store in Elasticsearch for hybrid search
Batch embed rows and store in Pinecone for vector search
Check embedding coverage for a table/column
SigLIP 2 embedding for an image (L2-normalized, shared image/text space)
Generate embedding and store with table/column/ID tracking
Per-row — runs once for each row.
| name | type | description |
|---|---|---|
| text | VARCHAR | Text to embed |
| model(optional) | VARCHAR | Optional model |
| source_table | VARCHAR | Source table name |
| column_name | VARCHAR | Source column name |
| source_id | VARCHAR | Source row ID |
Generate 768-dim embedding vector from text (on-box nomic-embed-text-v1.5)
Batch embed rows and store in lars_embeddings
Batch embed rows and store in Elasticsearch for hybrid search
Batch embed rows and store in Pinecone for vector search
Check embedding coverage for a table/column
SigLIP 2 embedding for an image (L2-normalized, shared image/text space)