Chat with a model in the Amazon Bedrock IDE chat playground - Amazon SageMaker Unified Studio

Amazon SageMaker Unified Studio is in preview release and is subject to change.

Chat with a model in the Amazon Bedrock IDE chat playground

The Amazon Bedrock IDE chat playground allows you chat with an Amazon Bedrock IDE model and try chat agent apps that are shared to you. A chat provides a back-and-forth, dialogue-like interaction between you and an Amazon Bedrock model. The model is able to retain context during a chat allowing for coherent and relevant responses from the model. You chat with a model by sending a prompt to the model and by receiving the response that the model generates. You continue the chat by sending further prompts.

If a model supports multimodal prompts, you can send prompts that contain text, images, and videos. A chat can contain multiple text and image prompts, but you can only add one video to a chat. After you finish a chat, you can reset the playground to begin a new chat. Amazon Bedrock models support differing modalities. For more information, see Supported foundation models in Amazon Bedrock.

The maximum image file size is 5MB. You can upload images that are in JPG, PNG, GIF, and WebP format. The maximum video size is 1GB. You can upload videos is MP4 and .MOV format.

When you run a prompt in the chat playground, you get the following information about the request:

  • Input tokens — The number of input tokens used by the foundation model during inference.

  • Output tokens — The number of tokens generated in a response by the foundation model.

  • Latency — The amount of time the foundation model uses to generate each token in a sequence, based on the on-demand throughput.

The chat playground provides quick start prompts that illustrate the kinds of prompt that you can send to a model.

Optionally, you can compare the outputs from up to 3 shared apps and models. You can make configuration changes for models, such as inference parameters and compare the results. You can't make configuration changes for shared apps.

To chat with a model

  1. Navigate to the Amazon SageMaker Unified Studio landing page by using the URL from your admininstrator.

  2. Access Amazon SageMaker Unified Studio using your IAM or single sign-on (SSO) credentials. For more information, see Access Amazon SageMaker Unified Studio.

  3. At the top of the page, choose the Discover.

  4. In the Generative AI section, choose Chat playground to open the chat playground.

    Open Amazon Bedrock IDE chat playground.

  5. In Type select Model and then select a model to use in Model. If you don't see a model, contact your administrator.

  6. In the Enter prompt text box, enter What is Avebury stone circle?.

  7. Press Enter on your keyboard, or choose the run button, to send the prompt to the model. Amazon Bedrock IDE shows the response from the model in the playground.

    Run prompt in Amazon Bedrock IDE chat playground.

  8. Continue the chat by entering the prompt Is there a museum there? and pressing Enter.

    The response shows how the model uses the previous prompt as context for generating its next response.

  9. Choose Reset to start a new chat with the model.

  10. Influence the model response by doing the following:

    1. Enter and run a prompt. Note the response from the model.

    2. Choose the configurations menu to open the Configurations pane.

      Inference parameters in Amazon Bedrock IDE chat playground.

    3. Influence the model response by making inference parameters changes.

    4. Run the prompt again and compare the response with the previous response.

  11. Choose Reset to start a new chat with the model.

  12. Try sending an image or video to a model by doing the following:

    1. For Model, choose one of the following:

      • If you want to use an image in your prompt, choose a model that supports images.

      • If you want to use a video in your prompt, choose a model that supports videos.

    2. Choose the attachment button at the left of the Enter prompt text box.

      Run prompt in Amazon Bedrock IDE chat playground.

    3. In the open file dialog box, choose an image or a video from your local computer.

    4. In the text box, next to the image or video that you uploaded, enter What's in this image?. If you uploaded a video, enter What's in this video?.

    5. Press Enter on your keyboard enter to send the prompt to the model. The response from the models describes the model or image.

  13. (Optional) Try using another model and different prompts. Different models have different recommendations for creating, or engineering, prompts. For more information, see Prompt engineering guides.

  14. (Optional) Compare the output from multiple models, or shared apps.

    1. In the playground, turn on Compare mode.

    2. In both panes, select the model that you want to compare. If you want to use a shared app, select App in Type and then select the app in App.

    3. Enter a prompt in the text box and run the prompt. The output from each model is shown. You can choose the copy icon to copy the prompt or model response to the clipboard.

    4. (Optional) Choose View configs to make configuration changes, such as inference parameters. Choose View chats to return to the chat page.

    5. (Optional) Choose Add chat window to add a third window. You can compare up to 3 models or apps.

    6. Turn off Compare mode to stop comparing models.

Now that you are familiar with the explorer playground, try creating a Amazon Bedrock IDE app next. For more information, see Build a chat agent app with Amazon Bedrock IDE.