Group logs

Group LLM logs together

You can group LLM logs together by using the group_identifier parameter in the request body. This is useful when you want to group logs together for a specific user or a specific task.

How to group logs?

You can group logs by using the group_identifier parameter in the request body.

AI gateway

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://api.keywordsai.co/api/",
    api_key="YOUR_KEYWORDSAI_API_KEY",
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role":"user", "content":"Tell me a long story"}],
    extra_body={
        "group_identifier": "group_123"
    }
)

Logging API

Python

import requests

url = "https://api.keywordsai.co/api/request-logs/create/"
payload = {
    "model": "claude-3-5-sonnet-20240620",
    "prompt_messages": [
        {
            "role": "user",
            "content": "Hi"
        },
    ],
    "completion_message": {
        "role": "assistant",
        "content": "Hi, how can I assist you today?"
    },
    "group_identifier": "group_123"
    # ... other parameters
}
headers = {
    "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
    "Content-Type": "application/json"
}

response = requests.request("POST", url, headers=headers, json=payload)

View grouped logs

Once you attach a group_identifier to a request, you can view those logs in Logs.