Upload file

POST /api/files/

Python

import requests

url = "https://api.keywordsai.co/api/files/"
headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

with open("batch_input.jsonl", "rb") as f:
    files = {"file": f}
    data = {"purpose": "batch"}
    response = requests.post(url, headers=headers, files=files, data=data)

print(response.json())

200 OK

{
  "id": "file-abc123",
  "object": "file",
  "bytes": 1024,
  "created_at": 1677610602,
  "filename": "batch_input.jsonl",
  "purpose": "batch"
}

Upload a file for use with OpenAI Batch API. The uploaded file is stored on OpenAI’s servers and can be used to create batch jobs for asynchronous LLM request processing.

Customer credentials required: This endpoint requires your own OpenAI API key configured in Keywords AI dashboard (Settings → Providers). Keywords AI passes the request through to OpenAI’s infrastructure.

Request body

The request must use multipart/form-data encoding.

file · file · required

The file to upload. Must be a valid JSONL (JSON Lines) file for batch processing.

Example JSONL format

{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-4", "messages": [{"role": "user", "content": "Hello!"}]}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "How are you?"}]}}

purpose · string · required

The intended purpose of the file. For batch jobs, use "batch".

Supported values:

• "batch" - For use with the Batch API

Response

Returns a file object with metadata about the uploaded file.

200 OK

{
  "id": "file-abc123",
  "object": "file",
  "bytes": 1024,
  "created_at": 1677610602,
  "filename": "batch_input.jsonl",
  "purpose": "batch"
}

Python

import requests

url = "https://api.keywordsai.co/api/files/"
headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

with open("batch_input.jsonl", "rb") as f:
    files = {"file": f}
    data = {"purpose": "batch"}
    response = requests.post(url, headers=headers, files=files, data=data)

print(response.json())