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

<AgentInstructions>

## Submitting Feedback

If you encounter incorrect, outdated, or confusing documentation on this page, submit feedback:

POST https://axiom.co/docs/feedback

```json
{
  "path": "/apl/scalar-functions/genai-functions/genai-extract-assistant-response",
  "feedback": "Description of the issue"
}
```

Only submit feedback when you have something specific and actionable to report.

</AgentInstructions>

# genai_extract_assistant_response

> This page explains how to use the genai_extract_assistant_response function in APL.

The `genai_extract_assistant_response` function extracts the assistant’s response from a GenAI messages array. It returns the content of the last message with the 'assistant' role, which typically contains the AI model’s generated response to the user.

You can use this function to analyze AI responses, evaluate response quality, perform sentiment analysis on AI outputs, or track specific response patterns for monitoring and debugging.

## For users of other query languages

If you come from other query languages, this section explains how to adjust your existing queries to achieve the same results in APL.

<AccordionGroup>
  <Accordion title="Splunk SPL users">
    In Splunk SPL, you would need to use complex eval statements with mvfilter and mvindex to extract assistant messages.

    <CodeGroup>
      ```sql Splunk example theme={null}
      | eval assistant_msgs=mvfilter(match(role, "assistant"))
      | eval response=mvindex(assistant_msgs, -1)
      ```

      ```kusto APL equivalent theme={null}
      ['ai-logs']
      | extend response = genai_extract_assistant_response(messages)
      ```
    </CodeGroup>
  </Accordion>

  <Accordion title="ANSI SQL users">
    In ANSI SQL, you would need to unnest arrays, filter by role, and select the last message, which is more verbose.

    <CodeGroup>
      ```sql SQL example theme={null}
      SELECT 
        conversation_id,
        content as assistant_response
      FROM (
        SELECT *, ROW_NUMBER() OVER (PARTITION BY conversation_id ORDER BY msg_index DESC) as rn
        FROM conversations
        CROSS JOIN UNNEST(messages) WITH OFFSET AS msg_index
        WHERE role = 'assistant'
      ) WHERE rn = 1
      ```

      ```kusto APL equivalent theme={null}
      ['ai-logs']
      | extend assistant_response = genai_extract_assistant_response(messages)
      ```
    </CodeGroup>
  </Accordion>
</AccordionGroup>

## Usage

### Syntax

```kusto theme={null}
genai_extract_assistant_response(messages)
```

### Parameters

| Name     | Type    | Required | Description                                                                                                         |
| -------- | ------- | -------- | ------------------------------------------------------------------------------------------------------------------- |
| messages | dynamic | Yes      | An array of message objects from a GenAI conversation. Each message typically contains `role` and `content` fields. |

### Returns

Returns a string containing the content of the last assistant message in the conversation, or an empty string if no assistant message is found.

## Example

Extract the assistant's response from a GenAI conversation.

**Query**

```kusto theme={null}
['otel-demo-genai']
| extend ai_response = genai_extract_assistant_response(['attributes.gen_ai.input.messages'])
| where strlen(ai_response) > 0
| project _time, ai_response
| limit 3
```

[Run in Playground](https://play.axiom.co/axiom-play-qf1k/query?initForm=%7B%22apl%22%3A%22%5B%27otel-demo-genai%27%5D%20%7C%20extend%20ai_response%20%3D%20genai_extract_assistant_response\(%5B%27attributes.gen_ai.input.messages%27%5D\)%20%7C%20where%20strlen\(ai_response\)%20%3E%200%20%7C%20project%20_time%2C%20ai_response%20%7C%20limit%203%22%7D)

**Output**

| \_time               | ai\_response                                                                   |
| -------------------- | ------------------------------------------------------------------------------ |
| 2024-01-15T10:30:00Z | To reset your password, click on the 'Forgot Password' link on the login page. |
| 2024-01-15T10:31:00Z | Our business hours are Monday to Friday, 9 AM to 5 PM EST.                     |

This query extracts AI responses, helping you analyze response quality and patterns.

## List of related functions

* [genai\_extract\_user\_prompt](/apl/scalar-functions/genai-functions/genai-extract-user-prompt): Extracts the user's prompt. Use this to analyze what users are asking.
* [genai\_extract\_system\_prompt](/apl/scalar-functions/genai-functions/genai-extract-system-prompt): Extracts the system prompt. Use this to understand how the AI is configured.
* [genai\_get\_content\_by\_role](/apl/scalar-functions/genai-functions/genai-get-content-by-role): Gets content by any role. Use this when you need messages from roles other than assistant.
* [genai\_concat\_contents](/apl/scalar-functions/genai-functions/genai-concat-contents): Concatenates all message contents. Use this when you need the full conversation instead of just the assistant's response.
* [genai\_has\_tool\_calls](/apl/scalar-functions/genai-functions/genai-has-tool-calls): Checks for tool calls in messages. Use this to detect when the assistant made function calls.