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.

Splunk SPL users

In Splunk SPL, you would need to use complex eval statements with mvfilter and mvindex to extract assistant messages.

Splunk example

| eval assistant_msgs=mvfilter(match(role, "assistant"))
| eval response=mvindex(assistant_msgs, -1)

ANSI SQL users

In ANSI SQL, you would need to unnest arrays, filter by role, and select the last message, which is more verbose.

SQL example

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

Usage

Syntax

genai_extract_assistant_response(messages)

Parameters

• messages (dynamic, required): 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.

Use case examples

Log analysis

Extract AI responses from conversation logs to analyze response quality and patterns.

Query

['sample-http-logs']
| where uri contains '/api/chat'
| extend ai_response = genai_extract_assistant_response(todynamic(response_body)['messages'])
| where strlen(ai_response) > 0
| project _time, id, req_duration_ms, ai_response

Run in Playground

Output

_time	id	req_duration_ms	ai_response
2024-01-15T10:30:00Z	user_123	1250	To reset your password, click on the ‘Forgot Password’ link on the login page.
2024-01-15T10:31:00Z	user_456	980	Our business hours are Monday to Friday, 9 AM to 5 PM EST.

This query extracts AI responses and correlates them with response times, helping you analyze performance.

List of related functions

• genai_extract_user_prompt: Extracts the user’s prompt. Use this to analyze what users are asking.
• genai_extract_system_prompt: Extracts the system prompt. Use this to understand how the AI is configured.
• genai_get_content_by_role: Gets content by any role. Use this when you need messages from roles other than assistant.
• 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: Checks for tool calls in messages. Use this to detect when the assistant made function calls.