batch_process
Process content files through Gemini AI models in a single operation. Uploads files, creates batch jobs, monitors completion, and downloads results automatically for large-scale content generation tasks.
Instructions
COMPLETE BATCH WORKFLOW - End-to-end content generation batch processing. WORKFLOW: 1) Ingests content file (CSV, JSON, TXT, etc.), 2) Converts to JSONL, 3) Uploads to Gemini, 4) Creates batch job, 5) Polls until complete, 6) Downloads and parses results. BEST FOR: Users who want simple one-call solution. RETURNS: Final results with metadata. For more control, use individual tools (batch_ingest_content, batch_create, batch_get_status, batch_download_results).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| inputFile | Yes | Path to content file (CSV, JSON, TXT, MD, JSONL) | |
| model | No | Gemini model for content generation | gemini-2.5-flash |
| outputLocation | No | Output directory for results (defaults to current working directory) | |
| pollIntervalSeconds | No | Seconds between status checks (default: 30) | |
| config | No | Optional generation config |
Input Schema (JSON Schema)
{
"properties": {
"config": {
"description": "Optional generation config",
"type": "object"
},
"inputFile": {
"description": "Path to content file (CSV, JSON, TXT, MD, JSONL)",
"type": "string"
},
"model": {
"default": "gemini-2.5-flash",
"description": "Gemini model for content generation",
"enum": [
"gemini-2.5-pro",
"gemini-2.5-flash",
"gemini-2.0-flash-exp"
],
"type": "string"
},
"outputLocation": {
"description": "Output directory for results (defaults to current working directory)",
"type": "string"
},
"pollIntervalSeconds": {
"default": 30,
"description": "Seconds between status checks (default: 30)",
"minimum": 10,
"type": "number"
}
},
"required": [
"inputFile"
],
"type": "object"
}