Pipelines: processing data in bulk

You need: a separate fetch_... key (create one), a balance — $1 covers 10,000 reviews on DeepSeek (top up), Python 3.10+, a CSV with the columns id and text.

1. 1
   Put a limit on the key

   Dashboard → API keys: set a daily spend limit (say, $3) and allow only the models you need. The limit stops the script if it goes in circles.

2. 2
   Install the library and set the key

   bashCopy

   pip install openai
   export ZUKKO_API_KEY="fetch_your_key"

   Windows (PowerShell): $env:ZUKKO_API_KEY="fetch_your_key".

3. 3
   Save the script

   File classify_reviews.py, next to reviews.csv:

   classify_reviews.pyCopy

   """
   Classify customer reviews from a CSV file through the Zukko API.
   
   Run:
       pip install openai
       export ZUKKO_API_KEY="fetch_..."
       python classify_reviews.py reviews.csv results.csv --limit 50   # a trial run first
       python classify_reviews.py reviews.csv results.csv              # then everything
   
   The input CSV needs the columns id and text. You can stop the script and run it
   again: rows already present in results.csv are skipped.
   """
   import argparse
   import asyncio

   Show all code · 179 lines
4. 4
   Test on 50 rows

   bashCopy

   python classify_reviews.py reviews.csv results.csv --limit 50

   Check results.csv by eye. Multiply the amount spent by 200 to get the price of all 10,000 rows.

5. 5
   Run the whole file

   bashCopy

   python classify_reviews.py reviews.csv results.csv

   Finished rows are skipped. If it stops, run the same command again.

1Which model to use

Change the model in MODEL. Pick by trial: the same 50 rows through two candidates.

2No code: n8n and Make

1. 1
   Set up the HTTP request

   n8n: HTTP Request node, Make: HTTP → Make a request. POST to https://api.zukko.pro/v1/chat/completions. Headers: Authorization: Bearer fetch_your_key, Content-Type: application/json, Idempotency-Key — for example reviews-v1- plus the row id.

2. 2
   Set the request body

   jsonCopy

   {
     "model": "deepseek-v4.1-flash",
     "response_format": { "type": "json_object" },
     "max_tokens": 200,
     "messages": [
       { "role": "system", "content": "You classify customer reviews. Reply with JSON only: {\"sentiment\": \"positive|neutral|negative\", \"topic\": \"delivery|quality|price|support|other\", \"summary\": \"gist in up to 15 words\"}" },
       { "role": "user", "content": "REVIEW TEXT" }
     ]
   }

   Replace REVIEW TEXT with the sheet field. In n8n use JSON.stringify(...), or a quote mark in a review breaks the JSON.

3. 3
   Parse the answer

   choices[0].message.content is a string with JSON. Make: JSON → Parse JSON, n8n: a Code or Edit Fields node.

4. 4
   Turn on retries

   Retry on error in the node settings, batches of 5–10 rows, a spend limit on the key.

3If it doesn't work