[Image] Generate

The Image generate operation generates an image based on a prompt sent to the LLM. Currently, MuleSoft AI Chain connector supports only OpenAI Image Models.

Input Fields

XML Configuration

Below is the XML configuration for this operation:

<ms-aichain:image-generate 
  doc:name="Image generate" 
  doc:id="a5ae05e2-3cbb-4b89-b3e1-07030a3649b8" 
  config-ref="MAC_AI_Llm_configuration" 
  data="#[payload.prompt]"
/>

Output Field for v0.2.0

This operation responds with a string payload which needs to be converted into a json, this can be achieved with a Transform Message component with the following dataweave expression:

%dw 2.0
output application/json
---
read(payload,"application/json").

Output Field

This operation responds with a json payload.

Once converted into JSON, you can use the following dataweave expression to extract the generated images URL.

The image URL can be extracted with the following DataWeave expression:

%dw 2.0
output application/json
---
{ imageURL: payload.response as String }

Example Use Cases

This operation is particularly useful in scenarios where you need to generate an image based on a plain text prompt, such as:

• Marketing and Advertising: Creating visuals for campaigns based on specific descriptions.
• Content Creation: Generating images for blog posts, articles, or social media based on given prompts.
• Prototyping and Design: Quickly generating concept images from textual descriptions.

[Image] Read

The Image read operation read an image based on a prompt. Currently, MuleSoft AI Chain connector supports only OpenAI Image Models.

Input Fields

XML Configuration

Below is the XML configuration for this operation:

<ms-aichain:image-read 
doc:name="Image read" 
doc:id="a6a11fd7-6f48-4063-820c-1d9d488dd033" 
config-ref="OPENAI-GPT4-TURBO" data="#[payload.prompt]" 
contextURL="#[payload.imageUrl]" />

Output Field for v0.2.0

This operation responds with a string payload which needs to be converted into a json, this can be achieved with a Transform Message component with the following dataweave expression:

%dw 2.0
output application/json
---
read(payload,"application/json").

Output Field

This operation responds with a json payload.

{
    "response": "I see a group of eight people who appear to be posing for a photo together. They are all smiling and seem to be happy. The group includes both men and women, and they are arranged closely together, suggesting a sense of camaraderie or friendship. The background is not very clear, but the focus is on the people in the foreground.",
    "tokenUsage": {
        "outputCount": 69,
        "totalCount": 166,
        "inputCount": 97
    }
}