> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keywordsai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Logging via API

> Send your LLM logs to Keywords AI and monitor them in real-time

## What is logging?

1. Send a `POST` request to log your AI conversations
2. See them appear instantly on your Keywords AI platform

<Frame className="rounded-md">
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/observability/overview/logs.jpg" />
</Frame>

## Use logging API

### 1. Get your Keywords AI API key

After you create an account on [Keywords AI](https://platform.keywordsai.co), you can get your API key from the [API keys page](https://platform.keywordsai.co/platform/api/api-keys).

<Frame className="rounded-md">
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/get-started/api-keys.png" alt="Create API key placeholder" />
</Frame>

### 2. Integrate Async Logging into your codebase

<CodeGroup>
  ```python Python {22} theme={"system"}
  import requests
  import json

  url = "https://api.keywordsai.co/api/request-logs/create/"
  payload = {
      "model": "gpt-4o",
      "log_type": "chat",
      "input": json.dumps([
          {
              "role": "user",
              "content": "How can I help a customer with a billing issue?"
          }
      ]),
      "output": json.dumps({
          "role": "assistant",
          "content": "I'd be happy to help with billing issues. First, let me check your account details..."
      }),
      "customer_identifier": "support_agent_001"
  }

  headers = {
      "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
      "Content-Type": "application/json"
  }

  response = requests.post(url, headers=headers, json=payload)
  ```

  ```typescript TypeScript {3} theme={"system"}
  const url = 'https://api.keywordsai.co/api/request-logs/create/';
  const headers = {
      'Authorization': 'Bearer YOUR_KEYWORDS_AI_API_KEY',
      'Content-Type': 'application/json'
  };

  const payload = {
      model: 'gpt-4o',
      log_type: 'chat',
      input: JSON.stringify([
          {
              role: "user",
              content: "How can I help a customer with a billing issue?"
          }
      ]),
      output: JSON.stringify({
          role: "assistant",
          content: "I'd be happy to help with billing issues. First, let me check your account details..."
      }),
      customer_identifier: "support_agent_001"
  };

  fetch(url, {
      method: 'POST',
      headers: headers,
      body: JSON.stringify(payload)
  })
  .then(response => response.json())
  .then(data => {
      console.log(data);
  });
  ```

  ```bash cURL {3} theme={"system"}
  curl -X POST "https://api.keywordsai.co/api/request-logs/create/" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_KEYWORDS_AI_API_KEY" \
  -d '{
      "model": "gpt-4o",
      "log_type": "chat",
      "input": "[{\"role\":\"user\",\"content\":\"How can I help a customer with a billing issue?\"}]",
      "output": "{\"role\":\"assistant\",\"content\":\"I'\''d be happy to help with billing issues. First, let me check your account details...\"}",
      "customer_identifier": "support_agent_001"
  }'
  ```
</CodeGroup>

### 3. Check your logs on the platform

After you integrate the async logging into your codebase and send the request successfully, you can check your logs on the [Logs page](https://platform.keywordsai.co/platform/requests).

<Frame className="rounded-md">
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/documentation/get-started/logging_showlog.png" alt="Logs page placeholder" />
</Frame>