Get Text Completion Using AI21 Labs

UiPath.Bedrock.IntegrationService.Activities.TextCompletionUsingAi21labs

Description

Generates a text completion response based on a given prompt using AI21Labs.

Project Compatibility

Windows | Cross-Platform

Configuration

• Connection - The connection established in Integration Service. Access the drop-down to choose, add or manage connections.
• Model - The model you want to use for the text completion generation.
• Prompt - The prompt to use for the text completion generation.

Advanced

Options

• Max tokens - The maximum number of tokens allowed for the prompt and generated answer. By default, this field is set to 200.
• Stop sequences - Sequences that cause the model to stop generating completion text.
• Temperature - The amount of randomness injected into the response. This field accepts ranges between 0 and 1. Use a temperature closer to 0 for analytical / multiple choice, and closer to 1 for creative and generative tasks. By default, this field is set to 0.
• Top P - A number between 0 and 1. The lower the number, the fewer tokens are used. By default, this field is set to 1.
• Count penalty - A penalty applied to tokens based on their frequency in the generated responses.
• Frequency penalty - A penalty applied to tokens that are frequently generated.
• Presence penalty - A penalty applied to tokens that are already present in the prompt.

Output

• Response - The text completion performed using AI21, returned in an Invoke_model_ai21 object.
• Completion - Top generated text completion.