Summarize Text

Description

Summarize text using a suitable Large Language Model (LLM).

Project compatibility

Windows | Cross-platform

Configuration

• Connection ID - The connection established in Integration Service. Access the drop-down menu to choose, add, or manage connections.

• Model name - The large language model (LLM) to utilize for the chat completion request. Defaults to the Azure OpenAI's GPT-3.5-Turbo model.
• Text to summarize - The text you want to summarize using the LLM. This field supports String type input.
• Number of summary words - The maximum word count for the summary of the provided text. Defaults to 150 and is limited to 1000. This field supports Int32 type input.

Manage Properties

Use the Manage Properties wizard to configure or use any of the object's standard or custom fields. You can select fields to add them to the activity canvas. The added standard or custom fields are available in the Properties panel (in Studio Desktop) or under Show additional options (in Studio Web).

Additional options

• Summary format - The format for the generated summarized text, e.g., organized in paragraph form or as a bulleted item list, etc. Select one of the following options from the drop-down menu: paragraph, bulleted list, numbered list.
• Maximum tokens count - The maximum number of tokens to use for the summarization of the text and the response summary. Fewer tokens are less expensive. Defaults to 512. This field supports Int32 type input.
• Temperature - A number between 0.0 and 2.0 indicating the creativity factor or sampling temperature to use. Higher values result in higher creativity from the model, but also more risks, which could lead to more variance from the input text. Defaults to 1.0.

Output

• Summary - The summary generated by the AI for the provided input text. Automatically generated output variable.
• Summarize text - Automatically generated output variable.