This example pipeline demonstrates how to generate a descriptive text
from an infographic and extract key information from the second image with Azure OpenAI.
Downlaod this pipeline.
-
Configure the Multi File Reader Snap to pass
your image files. For example,
-
Configure the Azure OpenAI Multimodal Content Generator Snap with the
Type set to image and Content
type with image/jpeg to retreive the image from the
usptream Snap for multimodal content processing.
On validation, the Snap outputs a structured response that includes
sl_content
(the actual content), sl_contentType
(content format), and sl_type
(indicating the modality) for each
uploaded image.
Azure OpenAI Multimodal Content Generator Snap
configuration |
Azure OpenAI Multimodal Content Generator Snap
output |
|
|
-
Configure the Azure OpenAI Prompt Generator Snap with
the upstream multimodal content and set the prompt to Explain the infographic
in bullet points and list down the Application Integration patterns.
On validation, the Snap displays the upstream multimodal content passed, including the
prompt details.
Azure OpenAI Prompt Generator Snap configuration |
Azure OpenAI Prompt Generator Snap output |
|
|
-
Configure the Azure OpenAI Chat Completions Snap to
process incoming multimodal content and generate the responses based on the prompt.
On validation, the Snap displays the response with the summary of the infographic and
a list of the Application Integration patterns with their descriptions.
Azure OpenAI Chat Completions Snap configuration |
Azure OpenAI Chat Completions Snap output |
|
|
To successfully reuse pipelines:
- Download and import the pipeline into the SnapLogic Platform.
- Configure Snap accounts, as applicable.
- Provide pipeline parameters, as applicable.