genai_has_tool_calls

This page explains how to use the genai_has_tool_calls function in APL.

The genai_has_tool_calls function checks whether a GenAI messages array contains any tool calls or function calls. It returns a boolean value indicating if the AI model requested to use external tools or functions during the conversation.

You can use this function to filter conversations that use function calling, monitor tool usage patterns, identify integration opportunities, or track feature adoption of function calling capabilities.

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 check if tool-related fields exist in the messages.

Splunk example

| eval has_tools=if(isnotnull(tool_calls), "true", "false")

ANSI SQL users

In ANSI SQL, you would check for existence of tool calls in the messages array.

SQL example

SELECT 
  conversation_id,
  EXISTS(
    SELECT 1 FROM UNNEST(messages) 
    WHERE JSON_EXTRACT(content, '$.tool_calls') IS NOT NULL
  ) as has_tools
FROM conversations

Usage

Syntax

genai_has_tool_calls(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 boolean value: true if the messages contain tool calls, false otherwise.

Use case examples

Log analysis

Analyze the adoption rate of function calling features in your AI application.

Query

['sample-http-logs']
| where uri contains '/api/chat'
| extend uses_tools = genai_has_tool_calls(todynamic(response_body)['messages'])
| summarize 
    conversations_with_tools = countif(uses_tools),
    total_conversations = count(),
    adoption_rate = round(100.0 * countif(uses_tools) / count(), 2)
by bin(_time, 1d)

Run in Playground

Output

_time	conversations_with_tools	total_conversations	adoption_rate
2024-01-15	345	1450	23.79
2024-01-16	389	1523	25.54

This query tracks function calling adoption over time, helping you understand feature usage trends.

List of related functions

• genai_extract_tool_calls: Extracts the actual tool calls. Use this after confirming tool calls exist to analyze what tools are being called.
• genai_extract_function_results: Extracts function results. Use this to analyze the outcomes of tool calls.
• genai_message_roles: Lists all message roles. Use this to understand conversation structure when tool calls are present.
• genai_conversation_turns: Counts conversation turns. Analyze this alongside tool usage to understand complexity.