Easy Heading Free | ||||
---|---|---|---|---|
|
Launch Aspire (if it's not already running). See:
To add a Azure OpenAI Chat Completions an Aspire Text Splitter application, drag it from the Applicationssection to the desired Workflow event. This will automatically open the Azure OpenAI Chat Completions Aspire Text Splitter configuration for the application.
Image Added
Image Added
In the "General" “General” configuration section, specify the type of prompt to use. Currently, "User", "System" and "Assistant" types are supported.Field or Fields that need to be split. If multiple fields are being split, separate the names with commas.
Image Added
In the "General" “General” configuration section, specify the text for your prompt. It can be plain text or a groovy script that must have text as its final output.
Optionally, in the "General" section, you can add as many prompts as desired. You must then again, specify a prompt type and a prompt text for each of them.
field that will be created to hold the result of the field(s) splitting.
Image Added
In the “General” configuration section, specify the type of split to be performed:
Image Added
In the “General” configuration section, specify the character threshold: if each split section's character length for the split field(s) is less than the specified threshold, it will not be taken into consideration in the output
In the "Endpoint Configuration" section, specify the API version and Model to be used.
In the "Model Parameters" section, specify parameters to be used with the Model specified in the previous step.
After this, you can press the add button to finish the workflow.
Now the workflow component is ready to be used in your Aspire Seeds.
Image Added
Here is an example are a couple of examples of the output. The application will add a "chatCompletionsResponse" object to the document which in turn will have the response content in a "content" field, a "responseProperties" field with response properties, including usage statistics, a "requestProperties" field, with the corresponding request properites and finally, a "modelProperties" field with the properties with which the model was configured.was set up to split the “content” field by sentences and save the result in the “segments” field. The first example was done with a threshold of 2 characters and the second with a threshold of 10.
Threshold of 2:
Image Added
Threshold of 10:
Image Added
Info |
---|
For details on using the Workflow section, please refer to the Workflow introduction. |