Enable user analytics

How does user analytics work?

On Keywords AI, we built a Users page to help you understand your users and their behavior on your LLM applications. With our user analytics feature, you can;

Track user LLM usage
Set user budget
Filter logs by user identifier

Enable user analytics in the code

You can pass a customer_params to the request to track the user’s behavior on your LLM applications.

Here is an example of how to send a user’s data with the parameter customer_params to Keywords AI in the 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={
        "customer_params": {
            "customer_identifier": "customer_1",
            "name": "Hendrix Liu", # optional parameter 
            "email": "hendrix@keywordsai.co" # optional parameter
        }
    }
)

Here is an example of how to send a user’s data with the parameter customer_params to Keywords AI in the 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={
        "customer_params": {
            "customer_identifier": "customer_1",
            "name": "Hendrix Liu", # optional parameter 
            "email": "hendrix@keywordsai.co" # optional parameter
        }
    }
)

Here is an example of how to send a user’s data with the parameter customer_params to Keywords AI in the OpenAI TypeScript SDK. In OpenAI TypeScript SDK, you should add a // @ts-expect-error before the metadata field.

import { OpenAI } from "openai";

const client = new OpenAI({
  baseURL: "https://api.keywordsai.co/api",
  apiKey: "YOUR_KEYWORDSAI_API_KEY",
});

const response = await client.chat.completions
  .create({
    messages: [{ role: "user", content: "Say this is a test" }],
    model: "gpt-4o-mini",
    // @ts-expect-error
    customer_params: {
        "customer_identifier": "customer_1",
        "name": "Hendrix Liu", // optional parameter
        "email": "hendrix@keywordsai.co" // optional parameter
    }
  })
  .asResponse();

console.log(await response.json());

import requests
def demo_call(input, 
              model="gpt-4o-mini",
              token="YOUR_KEYWORDS_AI_API_KEY",
              ):
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {token}',
    }

    data = {
        'model': model,
        'messages': [{'role': 'user', 'content': input}],
        'customer_params': {
            "customer_identifier": "customer_1",
            "name": "Hendrix Liu", # optional parameter
            "email": "hendrix@keywordsai.co" # optional parameter
        }
    }

    response = requests.post('https://api.keywordsai.co/api/chat/completions', headers=headers, json=data)
    return response

messages = "Say 'Hello World'"
print(demo_call(messages).json())

We also support adding credentials in other SDKs or languages, please check out our integration section for more information.

See user data on the platform

After you send the user’s data to Keywords AI, there are 3 places you can see the user’s data on the platform.

1. Users page

You will see each user’s detail information and their LLM usage on the Users page and the side panel.

2. Dashboard page

There are several charts on the Dashboard page to help you understand your users’ behavior, including;

Top users
Daily active users count
LLM cost by user

3. Logs page

For each LLM log, you can see the corresponding user’s data in the side panel. You can also filter logs by choosing a User Identifier.

Get started

AI observability

Prompt engineering

Evaluations

AI gateway

Organization management

Resources

Enable user analytics

How does user analytics work?