Skip to main content Startseite Ersteller akrindev google-studio-skills gemini-batch
gemini-batch Process large volumes of requests using Gemini Batch API via scripts/. Use for batch processing, bulk text generation, processing JSONL files, async job execution, and cost-efficient high-volume AI tasks. Triggers on "batch processing", "bulk requests", "JSONL", "async job", "batch job".
Zur Installation springen Skills Marktplatz Entdecken und erkunden Sie KI-Skills, die von der Community erstellt wurden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Prompt-Details anzeigen Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
npx skills add https://github.com/akrindev/google-studio-skills --skill gemini-batchDer Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.
Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.
ZIP herunterladen Herunterladen... Mehr aus diesem Repository
Upload and manage files using Google Gemini File API via scripts/. Use for uploading images, audio, video, PDFs, and other files for use with Gemini models. Supports file upload, status checking, and file management. Triggers on "upload file", "file API", "upload image", "upload PDF", "upload video", "file management".
Generate images using Google Gemini and Imagen models via scripts/. Use for AI image generation, text-to-image, creating visuals from prompts, generating multiple images, custom aspect ratios, and high-resolution output up to 4K. Triggers on "generate image", "create image", "imagen", "text to image", "AI art", "nano banana".
Verwandte Berufe SOC
Basierend auf der SOC-Berufsklassifikation
name gemini-batch description Process large volumes of requests using Gemini Batch API via scripts/. Use for batch processing, bulk text generation, processing JSONL files, async job execution, and cost-efficient high-volume AI tasks. Triggers on "batch processing", "bulk requests", "JSONL", "async job", "batch job". license MIT version 1.0.0 keywords batch processing, bulk generation, JSONL, async jobs, cost-efficient, high volume, scalable, parallel processing
Gemini Batch Processing
Process large volumes of requests efficiently using Gemini Batch API through executable scripts for cost savings and high throughput.
When to Use This Skill
Use this skill when you need to:
Process hundreds/thousands of requests
Generate content in bulk (blogs, emails, descriptions)
Reduce costs for high-volume tasks
Run async jobs without blocking
Process large datasets with AI
Generate multiple documents at once
Create scalable content pipelines
Process requests that don't need real-time responses
Available Scripts
scripts/create_batch.js
Purpose : Create a batch job from a JSONL file
Starting any batch processing task
Uploading multiple requests for processing
Creating async jobs for large workloads
Parameter Description Example input_fileJSONL file path (required) requests.jsonl--model, -mModel to use gemini-3-flash-preview--name, -nDisplay name for job "my-batch-job"
Output : Job name/ID to track with check_status.js
scripts/check_status.js Purpose : Monitor batch job progress and completion
Checking if a batch job is complete
Polling job status until finished
Monitoring async job execution
Parameter Description Example job_nameBatch job name/ID (required) batches/abc123--wait, -wPoll until completion Flag
Output : Job status and final state
scripts/get_results.js Purpose : Retrieve completed batch job results
Downloading completed batch results
Parsing batch job output
Extracting generated content
Parameter Description Example job_nameBatch job name/ID (required) batches/abc123--output, -oOutput file path results.jsonl
Output : Results content or file
Workflows
Workflow 1: Basic Batch Processing
echo '{"key": "req1", "request": {"contents": [{"parts": [{"text": "Explain photosynthesis"}]}]}}' > requests.jsonl
echo '{"key": "req2", "request": {"contents": [{"parts": [{"text": "What is gravity?"}]}}]}' >> requests.jsonl
node scripts/create_batch.js requests.jsonl --name "science-questions"
node scripts/check_status.js <job-name> --wait
node scripts/get_results.js <job-name> --output results.jsonl
Best for: Basic bulk processing, cost efficiency
Typical time: Minutes to hours depending on job size
Workflow 2: Bulk Content Generation
python3 << 'EOF'
import json
topics = ["sustainable energy" , "AI in healthcare" , "space exploration" ]
with open("content-requests.jsonl" , "w" ) as f:
for i, topic in enumerate(topics):
req = {
"key" : f"blog-{i}" ,
"request" : {
"contents" : [{
"parts" : [{
"text" : f"Write a 500-word blog post about {topic}"
}]
}]
}
}
f.write(json.dumps(req) + "\n" )
EOF
node scripts/create_batch.js content-requests.jsonl --name "blog-posts" --model gemini-3-flash-preview
node scripts/check_status.js <job-name> --wait
node scripts/get_results.js <job-name> --output blog-posts.jsonl
Best for: Blog generation, article creation, bulk writing
Combines with: gemini-text for content needs
Workflow 3: Dataset Processing
python3 << 'EOF'
import json
data = [
{"product" : "laptop" , "features" : ["fast" , "lightweight" ]},
{"product" : "headphones" , "features" : ["wireless" , "noise-cancelling" ]},
]
with open("product-descriptions.jsonl" , "w" ) as f:
for item in data:
features = ", " .join (item["features" ])
prompt = f"Write a product description for {item['product']} with these features: {features}"
req = {
"key" : item["product" ],
"request" : {
"contents" : [{"parts" : [{"text" : prompt}]}]
}
}
f.write(json.dumps(req) + "\n" )
EOF
node scripts/create_batch.js product-descriptions.jsonl
node scripts/check_status.js <job-name> --wait
node scripts/get_results.js <job-name> --output results.jsonl
Best for: Product descriptions, dataset enrichment, bulk analysis
Workflow 4: Email Campaign Generation
python3 << 'EOF'
import json
customers = [
{"name" : "Alice" , "product" : "premium plan" },
{"name" : "Bob" , "product" : "basic plan" },
]
with open("emails.jsonl" , "w" ) as f:
for cust in customers:
prompt = f"Write a personalized email to {cust['name']} about upgrading to our {cust['product']}"
req = {
"key" : f"email-{cust['name'].lower()}" ,
"request" : {
"contents" : [{"parts" : [{"text" : prompt}]}]
}
}
f.write(json.dumps(req) + "\n" )
EOF
node scripts/create_batch.js emails.jsonl --name "email-campaign"
node scripts/check_status.js <job-name> --wait
node scripts/get_results.js <job-name> --output email-results.jsonl
Best for: Marketing campaigns, personalized outreach
Combines with: gemini-text for email content
Workflow 5: Async Job Monitoring
node scripts/create_batch.js large-batch.jsonl --name "big-job"
while true ; do
node scripts/check_status.js <job-name>
sleep 60
done
node scripts/get_results.js <job-name> --output final-results.jsonl
Best for: Long-running jobs, background processing
Use when: You don't need immediate results
Workflow 6: Cost-Optimized Bulk Processing
node scripts/create_batch.js requests.jsonl --model gemini-3-flash-preview --name "cost-optimized"
node scripts/check_status.js <job-name> --wait
node scripts/get_results.js <job-name>
Best for: High-volume, cost-sensitive applications
Savings: Batch API typically 50%+ cheaper than real-time
Workflow 7: Multi-Stage Pipeline
node scripts/create_batch.js content-requests.jsonl --name "stage1-content"
node scripts/check_status.js <job1> --wait
node scripts/create_batch.js summaries.jsonl --name "stage2-summaries"
node scripts/check_status.js <job2> --wait
Best for: Complex workflows, multi-step processing
Combines with: Other Gemini skills for complete pipelines
Parameters Reference
JSONL Format Each line is a separate JSON object:
{
"key" : "unique-identifier" ,
"request" : {
"contents" : [
{
"parts" : [
{
"text" : "Your prompt here"
}
]
}
]
}
}
Model Selection Model Best For Cost Speed gemini-3-flash-previewGeneral bulk processing Lowest Fast gemini-3-pro-previewComplex reasoning tasks Medium Medium gemini-2.5-flashStable, reliable Low Fast gemini-2.5-proCode/math/STEM Medium Slow
Job States State Description JOB_STATE_PENDINGJob queued, waiting to start JOB_STATE_RUNNINGJob actively processing JOB_STATE_SUCCEEDEDJob completed successfully JOB_STATE_FAILEDJob failed (check error message) JOB_STATE_CANCELLEDJob was cancelled JOB_STATE_EXPIREDJob timed out
Size Limits Method Max Size Best For File upload Unlimited Large batches (recommended) Inline requests <20MB Small batches
Output Interpretation
Results JSONL {
"key" : "your-identifier" ,
"response" : {
"text" : "Generated content here..."
}
}
Error Handling
Failed requests appear in results with error information
Check for error field in response
Partial failures don't stop entire job
Result Access
Use --output to save to file
Script prints preview of results
Parse JSONL line by line for processing
Common Issues
"google-genai not installed" npm install @google/genai@latest dotenv@latest
"JSONL file not found"
Verify file path is correct
Check file extension is .jsonl (not .json)
Use absolute paths if relative paths fail
"Invalid JSONL format"
Each line must be valid JSON
No trailing commas between objects
Check for syntax errors in JSON
Use JSON validator if unsure
"Job failed"
Check error message in status
Verify request format is correct
Check model availability
Review API quota limits
"No results found"
Ensure job state is JOB_STATE_SUCCEEDED
Wait for job completion before retrieving
Check job status first with check_status.js
"Processing stuck in RUNNING state"
Large jobs can take hours
Use --wait flag for automated polling
Check job size and model choice
Contact support if stuck >24 hours
Best Practices
JSONL Creation
Use unique keys for each request
Validate JSON before uploading
Test with small batch first (5-10 requests)
Include error handling in your scripts
Job Management
Use descriptive display names (--name)
Save job names for tracking
Monitor status before retrieving results
Keep backup of original JSONL file
Performance Optimization
Use flash models for cost efficiency
Batch as many requests as possible
File upload preferred over inline
Process during off-peak hours if timing sensitive
Error Handling
Check for failed requests in results
Retry failed requests individually
Log job names for audit trails
Validate output format before use
Cost Management
Batch API is 50%+ cheaper than real-time
Use flash models when possible
Monitor token usage
Process in chunks if quota limited
Related Skills
gemini-text : Generate individual text requestsgemini-image : Batch image generationgemini-tts : Batch audio generationgemini-embeddings : Batch embedding creation
Quick Reference
node scripts/create_batch.js requests.jsonl
node scripts/check_status.js <job-name> --wait
node scripts/get_results.js <job-name> --output results.jsonl
node scripts/create_batch.js requests.jsonl --model gemini-3-flash-preview --name "my-job"
echo '{"key":"1","request":{"contents":[{"parts":[{"text":"Prompt"}]}]}}' > batch.jsonl
Reference 