Generate Text Completion

Description

Generates a text completion response based on the given prompt and large language model (LLM).

Project compatibility

Windows | Cross-platform

Configuration

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

• Model name - The model used for generating text completions. Select one of the available options: Anthropic Claude Instant, Anthropic Claude, Anthropic Claude 2.1, Anthropic Claude 3 Sonnet, Anthropic Claude 3 Haiku, Anthropic Claude 3 Opus, Anthropic Claude 3.5 Sonnet, Meta Llama 3 8b Instruct, Meta Llama 3 70b Instruct, AI21 Labs Jamba-Instruct, Amazon Titan Text G1-Express, Amazon Titan G1 - Lite, Amazon Titan Text Premier, Mistral 7B Instruct, Mistral 8X7B Instruct, Mistral Large, Mistral Small.
  Note: Ensure the selected model is deployed to successfully make text completion requests. To check your model access, see Manage access to Amazon Bedrock foundation models.
• File - The file attachment input allows for the inclusion of both document and image attachments along with the text prompt. For a successful generation, make sure the selected file type is compatible with the selected model. This field supports IResource type input.
  Note: Not all models support using attachments.
• Prompt - The input prompt to use for the text completion generation. This field supports String type input.
• Max tokens - The maximum tokens to use for the completion. If not set, the model uses as many tokens as necessary for the completion, up to, but not exceeding the maximum tokens supported by the selected model. Check the vendor documentation for the maximum tokens for each model. This field supports Int64 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 properties (in Studio Web).

Additional properties

• 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. This field supports Double type input.
• Top p - A number between 0 and 1. The lower the number, the fewer tokens are used. This field supports Double type input.
• Stop sequences - A list of stop sequences. A stop sequence is a sequence of characters that cause the model to stop generating completion text. This field supports String[] type input.

Output

• Top generated text - The output message context text. Automatically generated output variable.
• Text completion object - Automatically generated output variable.