Guide du format JSONL pour l'API Batch OpenAI

{"custom_id": "req-001", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-4o-mini", "messages": [{"role": "user", "content": "Hello"}]}}

{"custom_id": "embed-001", "method": "POST", "url": "/v1/embeddings", "body": {"model": "text-embedding-3-small", "input": "JSONL is a text format for storing structured data."}}
{"custom_id": "embed-002", "method": "POST", "url": "/v1/embeddings", "body": {"model": "text-embedding-3-small", "input": "Each line contains one valid JSON object."}}
{"custom_id": "embed-003", "method": "POST", "url": "/v1/embeddings", "body": {"model": "text-embedding-3-small", "input": "JSONL files use the .jsonl extension."}}

from openai import OpenAI
import json
import time

client = OpenAI()

# Step 1: Create the JSONL batch file
prompts = [
    "Summarize the benefits of renewable energy.",
    "Classify this text as positive or negative: Great product!",
    "Translate to French: Hello, how are you?",
]

requests = [
    {
        "custom_id": f"req-{i}",
        "method": "POST",
        "url": "/v1/chat/completions",
        "body": {
            "model": "gpt-4o-mini",
            "messages": [{"role": "user", "content": prompt}],
            "max_tokens": 200,
        },
    }
    for i, prompt in enumerate(prompts)
]

with open("batch_input.jsonl", "w") as f:
    for req in requests:
        f.write(json.dumps(req) + "\n")

# Step 2: Upload the file
batch_file = client.files.create(
    file=open("batch_input.jsonl", "rb"),
    purpose="batch",
)

# Step 3: Create the batch
batch = client.batches.create(
    input_file_id=batch_file.id,
    endpoint="/v1/chat/completions",
    completion_window="24h",
)
print(f"Batch created: {batch.id}")

# Step 4: Poll for completion
while True:
    status = client.batches.retrieve(batch.id)
    print(f"Status: {status.status}")
    if status.status in ("completed", "failed", "cancelled"):
        break
    time.sleep(60)

# Step 5: Download results
if status.output_file_id:
    content = client.files.content(status.output_file_id)
    with open("batch_output.jsonl", "wb") as f:
        f.write(content.read())