Technology Preview
Artificial Intelligence (AI) Assist provides answers to just about any question you may have about working with FME, such as what transformer to use for a certain operation, or how to set the right parameters for a desired result.
When invoked from applicable dialogs, AI Assist can also help you create SQL queries, regular expression search patterns, or Python code.
To use AI Assist requires the following:
Use the AI Assist window to ask for assistance with any aspect of working with FME. This window appears by default. To control its appearance, select or unselect View > Windows > AI Assist from the menu bar.
Here are some tips for using AI Assist for general help with FME:
Before submitting a request, click to highlight the AI Assist widget on the mini-toolbar for each item on the canvas on which you want to base your inquiry. For example, for information about how a particular transformer works, highlight its widget on the mini-toolbar, then enter "What does this transformer do?"

With an open workspace, instruct AI Assist to "Summarize this workspace." In the AI Workspace Summary pane that appears, click Add as Annotation.
Note The Add as Annotation button persists in the AI Assist window if another workspace is opened. To add a summary annotation to a newly-opened workspace, click Add as Annotation again. AI Assist generates and adds a new summary annotation that is applicable to the current workspace.
When AI Assist is opened from an applicable dialog, you can get help creating SQL queries, regular expression search patterns, or Python code. To open AI Assist from one of these dialogs, click the AI Assist button:
.
|
Pattern |
Description |
Example FME Workbench Locations |
|---|---|---|
|
In transformers that support Python code, AI Assist allows you to generate Python from a description, existing code, or a combination of both, and then refine, explain, or add comments to the generated Python code. |
PythonCaller, PythonCreator [...] |
|
|
In parameters that support regular expressions, you can input a description in plain English, and AI Assist will generate a recommended expression to use, and a description of the results. |
StringReplacer [...] |
|
|
In parameters that support SQL queries, you can input a description of a query in plain English, and AI Assist will generate a recommended SQL Query, and a description of the results. |
InlineQuerier [...]
|
When working with AI Assist, keep in mind the following:
AI Assist is available in transformers that require Python code. You can Generate Python from a description (plus any existing code), and Refine, Explain, or Add Comments to the generated Python code.
Select an Action from the drop-down list.
|
Action |
Generate Code – Sends a request to generate code based on a combination of input request in the Python Description field and any existing code in the AI Results field. Refine Code – Refines any existing Python Code. This action is most useful for code that is automatically copied from the Python editor when AI Assist is opened, or code that is manually written or edited directly in AI Assist. Explain Code – Adds explanations of any existing Python Code to the Explanation section. This action is most useful for code that is automatically copied from the Python editor when AI Assist is opened, or code that is manually written or edited directly in AI Assist. Add Comments – Adds comments to any existing Python Code. |
If Action is Generate Code, use this section to describe the requirement in plain English.
For best results:
|
Pattern |
Description |
Results |
|---|---|---|
|
Python |
Create a new attribute called 'timestamp' that gives me the timestamp of each feature's entry into PythonCaller in FME.
|
Click the Apply button to copy the results to the Python code editor. |
Displays the status of the AI Service.
Generated results appear in this section.

When the feedback panel opens, you can enter additional comments.
The AI server generates an explanation of the Python code.
In parameters that support regular expressions, you can input a description in plain English, and AI Assist will generate a recommended expression to use, and a description of the results.
Use this section to describe the requirement in plain English, and then click the Generate button.
|
Pattern |
Description |
Results |
|---|---|---|
|
RegEx |
Create a regular expression to match all mailing addresses on FRONT ST.
Click the Generate button to send the request. |
Click Apply to copy the results to the RegEx parameter. |
Displays the status of the AI Service.
Generated results appear in this section.

When the feedback panel opens, you can enter additional comments.
AI Assist will generate strings to test the regular expression. You can also enter your own strings in this section.
The AI server generates an explanation of the regular expression.
In parameters that support SQL queries, AI Assist will generate a recommended SQL Query, and an explanation of the results.
Use this section to describe the requirement in plain English, and then click the Generate button.
Send database schema to AI: If checked, the schema of the database you are querying is sent to the AI service along with the query description. Schema information includes relevant metadata about the database, such as table names, column names, and column data types. It does not include any actual data.
|
Pattern |
Description |
Results |
|---|---|---|
|
SQL |
Find all postal codes that contain 981.
Click the Generate button to send the request. |
Click the Apply button to copy the results to the SQL Query editor:
|
Displays the status of the AI Service.
Generated results appear in this section.

When the feedback panel opens, you can enter additional comments.
The AI server generates an explanation of the SQL query.