How do I process a CSV file with the Model API in Python?

import csv, os, time
from openai import OpenAI

client = OpenAI(base_url="https://api.gateway.clatterlabs.xyz/v1", api_key=os.environ["CLATTER_API_KEY"],
                default_headers={"X-Clatter-Account": os.environ["CLATTER_ACCOUNT_ID"]}, max_retries=5)

with open("reviews.csv") as f, open("labelled.csv", "w", newline="") as out:
    w = csv.writer(out)
    w.writerow(["review", "label", "tokens"])
    for row in csv.DictReader(f):
        r = client.chat.completions.create(
            model="supercosmos-flash",
            messages=[{"role": "system", "content": "Label the review as positive, negative or mixed. One word."},
                      {"role": "user", "content": row["review"]}],
            max_tokens=5, temperature=0,
        )
        w.writerow([row["review"], r.choices[0].message.content.strip(), r.usage.total_tokens])
        time.sleep(0.5)  # ~120 requests per minute

Size the delay to your key's limit, and estimate the total cost before you start so the run doesn't stop at 402 out_of_credits.

Good to know#

• Retry only 429 and 5xx errors, with backoff; honour Retry-After when it's sent. Which errors to retry
• Every response has an X-Request-Id; log it so a request can be found later. Why log it
• Every call shows in Console › Logs and Usage as Model API, with its price. See what you spent

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.