OpenAIConnector

Connects to OpenAI or OpenAI-compatible services to access OpenAI or provider-specific models.

Typical Uses

Generate text responses, summaries, classifications, or reasoning output from text prompts
Generate images from text prompts
Generate vector embeddings from text for similarity search, clustering, or downstream analytics

How does it work?

The OpenAIConnector uses an endpoint URL and, optionally, an API key to perform various tasks:

Action	Task
Create Response	Generate model responses given a text prompt. The model can also use tools such as Web Search.
Create Image	Generate new images given a text prompt.
Edit Image	Generate an edited or extended image given a text prompt and one or more source images.
Create Embedding	Generate an embedding vector from text input.

Optional Input Port

This transformer has two modes, depending on whether a connector is attached to the Input port or not:

Input-driven: When input features are connected, the transformer runs once for each feature it receives in the Input port.
Run Once: When no input features are connected, the transformer runs one time.

When the Input port is in use, the Initiator output port is also enabled.

Usage Notes

To continue a Create Response workflow across multiple requests, use Conversation State > Conversation or Previous Response.

Configuration

Input Ports

Output Ports

Output

Features with added attributes, as specified in parameters and according to Action:

Action	Output - Input-Driven	Output - Run Once
Create Response	Input feature with the generated response.	New feature with the generated response.
Create Image	Input feature with the generated image.	New feature with the generated image.
Edit Image	Input feature with the revised image.	New feature with the revised image.
Create Embedding	Input feature with the generated embedding vector.	New feature with the generated embedding vector.

Parameters

Action > Create Response

Input Options

Model	Provide or select a model to use. Some OpenAI models are included as choices, such as gpt-5.4. When using Azure OpenAI, this value must match your Azure deployment name. Model names may also be entered directly or provided as attribute values or user parameters.
Instructions	(Optional) Provide a message to insert into the model’s context. Note that when Conversation State is Previous Response, Instructions from previous responses are not carried over.
Prompt	Provide text input used to generate a response.
Conversation State	Select an option for carrying forward conversation context: None (default): No previous context is included in the request. Conversation: Context is included via a Conversation ID. Previous Response: Context is included via a Previous Response ID.
Conversation ID	When Conversation State is Conversation, provide the id of an existing conversation to continue. Typically obtained from the provider's conversations API.
Previous Response ID	When Conversation State is Previous Response, provide the id of a previous response to continue from, typically set to the _response_id attribute value from an earlier Create Response action.

Response Options

Verbosity

(Optional) Select a verbosity constraint to apply to the response:

Low
Medium
High

Structured Output

When enabled, constrains the model's response to conform to a given JSON Schema.

Schema Name

Specify the name of the response format schema.

Schema Description

(Optional) Provide a description of what the response format is for.

Used by the model to determine how to respond in the format.

JSON Schema

Provide the JSON Schema that the model's response must conform to.

The transformer sets strict to true on the request where possible, to ensure the model's output conforms exactly to the provided schema. As part of this, additionalProperties is set to false on any object schema in the JSON Schema that does not already include it. This is required by the API when strict mode is enabled.

Strict mode is disabled in the following cases:

The JSON Schema contains keywords not supported by strict mode.
The JSON Schema contains additionalProperties explicitly set to true.

Tools

Web Search

When enabled, the model may use the built-in web search tool to generate a response.

Advanced

Temperature	(Optional) Specify the sampling temperature to use, between 0 and 2 (inclusive). Higher values make the output more random, while lower make it more focused and deterministic.
Top-P	(Optional) Specify the nucleus sampling value, between 0 and 1 (inclusive). Top-P is an alternative to sampling with Temperature. The model considers the results of the tokens with top_p probability mass. For example, 0.2 means that the tokens comprising the top 20% probability mass are considered.
Reasoning Effort	(Optional) Select a level of reasoning effort : none minimal low medium high xhigh This should only be set for models that support reasoning. See OpenAI API - Reasoning.
Timeout(s)	Specify the read timeout in seconds. Default is 120.
Include Response JSON	Select an option: No (default): Do nothing. Yes: A _json_response attribute is added to Output features, containing the raw JSON of the response.

Added Attributes

Output features will receive these attributes:

_response_id	Unique identifier for this Response.
_model	Language model used to generate the response. For example gpt-5.4.
_completed_at	ISO 8601 date-time string indicating when the Response was completed. Only present when _status is completed.
_status	Status of the response generation. One of completed or incomplete.
_incomplete_reason	Details on why the response is incomplete. max_output_tokens: the response is incomplete because the maximum number of tokens allowed in the request, i.e. the output length limit, was reached. content_filter: the response is incomplete because it was blocked or removed by the provider’s safety filters.
_input_tokens	The number of input tokens used.
_output_tokens	The number of output tokens used.
_output{}	List attribute containing JSON objects representing the content items generated by the model.
_output_text	Aggregated text output from all output_text items in the _output{} attribute.
_json_response	Added when Include Response JSON is Yes. Contains the complete JSON response.

Action > Create Image

Create Image Options

Model

Provide or select a model to use. Some OpenAI models are included as choices, such as chatgpt-image-latest.

Model names may also be entered directly or provided as attribute values or user parameters.

Prompt

Provide a text description of the desired image.

Image Output Options

Size

Select a size for the output image:

Auto (default): Uses the optimal image dimensions based on the prompt
Landscape
Portrait
Square

Custom values may be entered if supported by the API.

Moderation

Select a content-moderation level for images generated by the GPT image models:

Auto (default)
Low

Advanced

Timeout(s)

Specify the read timeout in seconds. Default is 120.

Include Response JSON

Select an option:

No (default): Do nothing.
Yes: A _json_response attribute is added to Output features, containing the raw JSON of the response.

Added Attributes

Output features will receive these attributes:

_created_at	ISO 8601 date-time string indicating when the image was created.
_background	The background parameter used for the image generation (e.g. transparent, opaque).
_output_format	The output format of the image generation (e.g. png, webp, jpeg).
_quality	The quality of the image generated (e.g. low, medium, high)
_size	The size of the image generated (e.g. 1024x1024, 1024x1536, 1536x1024).
_image	The generated image, encoded in base64.
_json_response	Added when Include Response JSON is Yes. Contains the complete JSON response.

Action > Edit Image

Edit Image Options

Model

Provide or select a model to use. Some OpenAI models are included as choices, such as chatgpt-image-latest.

Model names may also be entered directly or provided as attribute values or user parameters.

Input Image(s)

Specify the path and filenames of 1 to 16 source images to edit.

Supported formats are PNG, JPG, JPEG, and WEBP.

Prompt

Provide a text description of the desired edits to apply to the image.

Image Output Options

Size

Select a size for the output image:

Auto (default): Uses the optimal image dimensions based on the prompt
Landscape
Portrait
Square

Custom values may be entered if supported by the API.

Moderation

Select a content-moderation level for images generated by the GPT image models:

Auto (default)
Low

Advanced

Timeout(s)

Specify the read timeout in seconds. Default is 120.

Include Response JSON

Select an option:

No (default): Do nothing.
Yes: A _json_response attribute is added to Output features, containing the raw JSON of the response.

Added Attributes

Output features will receive these attributes:

_created_at	ISO 8601 date-time string indicating when the image was created.
_background	The background parameter used for the image generation (e.g. transparent, opaque).
_output_format	The output format of the image generation (e.g. png, webp, jpeg).
_quality	The quality of the image generated (e.g. low, medium, high)
_size	The size of the image generated (e.g. 1024x1024, 1024x1536, 1536x1024).
_image	The generated image, encoded in base64.
_json_response	Added when Include Response JSON is Yes. Contains the complete JSON response.

Action > Create Embedding

Create Embedding Options

Model

Provide or select a model to use. Some OpenAI models are included as choices, such as text-embedding-3-small.

Model names may also be entered directly or provided as attribute values or user parameters.

Input

Provide text to convert into an embedding.

If the resolved value is a list, it must contain only integers.

Dimensions

(Optional) Specify the number of dimensions for the generated embedding.

Advanced

Timeout(s)

Specify the read timeout in seconds. Default is 120.

Include Response JSON

Select an option:

No (default): Do nothing.
Yes: A _json_response attribute is added to Output features, containing the raw JSON of the response.

Added Attributes

Output features will receive these attributes:

_model	Embedding model used to generate the vector. For example text-embedding-3-small.
_embedding{}	List attribute containing the embedding vector as floating-point values.
_json_response	Added when Include Response JSON is Yes. Contains the complete JSON response.

Editing Transformer Parameters

Transformer parameters can be set by directly entering values, using expressions, or referencing other elements in the workspace such as attribute values or user parameters. Various editors and context menus are available to assist. To see what is available, click beside the applicable parameter.

How to Set Parameter Values

Defining Values

There are several ways to define a value for use in a Transformer. The simplest is to simply type in a value or string, which can include functions of various types such as attribute references, math and string functions, and workspace parameters.

Using the Text Editor

The Text Editor provides a convenient way to construct text strings (including regular expressions) from various data sources, such as attributes, parameters, and constants, where the result is used directly inside a parameter.

Text Editor

Using the Arithmetic Editor

The Arithmetic Editor provides a convenient way to construct math expressions from various data sources, such as attributes, parameters, and feature functions, where the result is used directly inside a parameter.

Arithmetic Editor

Conditional Values

Set values depending on one or more test conditions that either pass or fail.

Parameter Condition Definition Dialog

Content

Expressions and strings can include a number of functions, characters, parameters, and more.

When setting values - whether entered directly in a parameter or constructed using one of the editors - strings and expressions containing String, Math, Date/Time or FME Feature Functions will have those functions evaluated. Therefore, the names of these functions (in the form @<function_name>) should not be used as literal string values.

Content Types

String Functions	These functions manipulate and format strings.
Special Characters	A set of control characters is available in the Text Editor.
Math Functions	Math functions are available in both editors.
Date/Time Functions	Date and time functions are available in the Text Editor.
Math Operators	These operators are available in the Arithmetic Editor.
FME Feature Functions	These return primarily feature-specific values.
FME Parameters	FME and workspace-specific parameters may be used.
Creating and Modifying User Parameters	Create your own editable parameters.

Dialog Options - Tables

Table Tools

Transformers with table-style parameters have additional tools for populating and manipulating values.

Row Reordering

Enabled once you have clicked on a row item. Choices include:

Add a row
Remove a row
Move current row up one
Move current row down one
Move current row to top
Move current row to bottom

Cut, Copy, and Paste

Enabled once you have clicked on a row item. Choices include:

Cut a row - delete and copy to clipboard
Copy a row to the clipboard
Paste a row from the clipboard

Cut, copy, and paste may be used within a transformer, or between transformers.

Filter

Start typing a string, and the matrix will only display rows matching those characters. Searches all columns. This only affects the display of attributes within the transformer - it does not alter which attributes are output.

Import

Import populates the table with a set of new attributes read from a dataset. Specific application varies between transformers.

Reset/Refresh

Generally resets the table to its initial state, and may provide additional options to remove invalid entries. Behavior varies between transformers.

Note: Not all tools are available in all transformers.

For more information, see Transformer Parameter Menu Options.

Reference

Processing Behavior	Feature-Based
Feature Holding	No
Dependencies
Aliases
History

FME Online Resources

The FME Community and Support Center Knowledge Base have a wealth of information, including active forums with 35,000+ members and thousands of articles.

Search for all results about the OpenAIConnector on the FME Community.

Examples may contain information licensed under the Open Government Licence – Vancouver, Open Government Licence - British Columbia, and/or Open Government Licence – Canada.