Set AI Call Logging

Controls whether details of AI calls are saved to a log file.

Options 

  • On starts logging all AI script step or function calls in the specified log file. AI calls continue to be logged for all scripts in the current FileMaker Pro file until the file is closed or this script step is run with the Off option for the same log file.

  • Off stops logging in all AI call log files. No log filename needs to be specified.

  • Filename is a text expression for the log filename to use. If not specified, the filename is LLMDebug.log.

  • Verbose logs additional information, such as the embedding vectors from a model, the number of tokens used, and semantic find return count and similarity condition.

Compatibility 

Product Supported
FileMaker Pro Yes
FileMaker Go Yes
FileMaker WebDirect Yes
FileMaker Server Yes
FileMaker Cloud Yes
FileMaker Data API Yes
Custom Web Publishing Yes

Originated in version 

21.0

Description 

This script step logs all AI script step and function calls in the filename specified by the Filename option. If the file already exists, new log entries are added at the end of the file.

For scripts that run on FileMaker Pro and FileMaker Go clients, the AI call log is saved in the current user's Documents folder. For scripts that run on a FileMaker host, the log is saved in the host's Logs folder.

Example 1 

Turns on AI call logging in the ai-calls.log file in the Documents folder with verbose log entries, configures an AI account, goes to the Meeting Details layout, then uses the model to get embedding vectors for the text in the Meetings::Note field for the current record and stores it as text in the Meetings::Note_Embedding_Text text field. Logging remains enabled, so other scripts in this FileMaker Pro file can log AI calls as well.

Copy
Set AI Call Logging [ On ; Filename: "ai-calls.log" ; Verbose ]

Configure AI Account [ Account Name: "my-account" ; Model Provider: OpenAI ; API key: "sk-RZCtpWT..." ]

Go to Layout [ "Meeting Details" (Meetings) ; Animation: None ]

Insert Embedding [ Account Name: "my-account" ; Embedding Model: "text-embedding-3-small" ; Input: Meetings::Note ; Target: Meetings::Note_Embedding_Text ]