batch_create_embeddings
Create batch embedding generation jobs for large-scale AI tasks at reduced cost. Process multiple text inputs simultaneously for semantic similarity, classification, clustering, and retrieval applications using Google's Gemini embedding model.
Instructions
CREATE EMBEDDINGS BATCH JOB - Create async embeddings generation batch job. COST: 50% cheaper than standard API. MODEL: gemini-embedding-001 (1536 dimensions). WORKFLOW: 1) Prepare content (use batch_ingest_embeddings for conversion), 2) Select task type (use batch_query_task_type if unsure), 3) Upload file, 4) Call batch_create_embeddings, 5) Monitor with batch_get_status, 6) Download with batch_download_results. TASK TYPES: See batch_query_task_type for descriptions and recommendations.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Embedding model | gemini-embedding-001 |
| requests | No | Inline embedding requests (for small batches) | |
| inputFileUri | No | URI of uploaded JSONL file with embedding requests | |
| taskType | Yes | Embedding task type (affects model optimization). Use batch_query_task_type for guidance. | |
| displayName | No | Optional display name for the batch job | |
| outputLocation | No | Output directory for results |