AWS sagemaker-unified-studio high security documentation change
Summary
Updated terminology from 'document data source' to 'knowledge base', added model reasoning and stop sequence controls, removed single-file data source option, and updated deployment/export instructions
Security assessment
Added documentation for 'Stop sequences' to prevent unwanted text generation (security control) and 'Model reasoning' to improve transparency. These changes help mitigate risks of sensitive data exposure and uncontrolled outputs. Removal of single-file data sources may enforce more secure knowledge base usage, though not explicitly stated.
Diff
diff --git a/sagemaker-unified-studio/latest/userguide/create-chat-app-with-components.md b/sagemaker-unified-studio/latest/userguide/create-chat-app-with-components.md index dddd5c9cb..a7e157821 100644 --- a//sagemaker-unified-studio/latest/userguide/create-chat-app-with-components.md +++ b//sagemaker-unified-studio/latest/userguide/create-chat-app-with-components.md @@ -5 +5 @@ -Step 1: Create the initial chat agent appAdd a guardrailAdd a document data sourceAdd a function call +Step 1: Create the initial chat agent appAdd a guardrailAdd a knowledge baseAdd a function call @@ -15 +15 @@ The app can generate playlists and get the dates and locations of upcoming shows - * A data source that lets the app create playlists using your unique song information. + * A knowledge base that lets the app create playlists using your unique song information. @@ -28 +28 @@ The app can generate playlists and get the dates and locations of upcoming shows - * Step 3: Add a document data source to your chat agent app + * Step 3: Add a knowledge base to your chat agent app @@ -39 +39 @@ In this step you create a chat agent app that generates playlists for a radio st -To create the app, you first need to create an Amazon SageMaker Unified Studio [project](./projects.html). A project can contain multiple apps and is also where you can add the Amazon Bedrock components that you want your apps to use. Later you will add guardail, data source, and function components to your app. You can share a project with other users and groups of users. For more information, see [Share an Amazon Bedrock chat agent app](./app-share.html). +To create the app, you first need to create an Amazon SageMaker Unified Studio [project](./projects.html). A project can contain multiple apps and is also where you can add the Amazon Bedrock components that you want your apps to use. Later you will add guardail, knowledge base, and function components to your app. You can share a project with other users and groups of users. For more information, see [Share an Amazon Bedrock chat agent app](./app-share.html). @@ -91 +91 @@ Generative AI may give inaccurate responses. Avoid sharing sensitive information - 7. Choose **Save** to save the current draft of your app. + 7. Choose **Save** to save the current working draft of your app. @@ -101,3 +101 @@ The app shows the prompt and the response from the model in the **Preview** pane - 11. Experiment with influencing the model response by doing the following: - - 1. In the **Inference parameters** section change the inference parameters. For example, include less familiar songs in the playlist by increasing the **Temperature** inference parameter. + 11. (Optional) In the **Inference parameters** section change the inference parameters. For example, include less familiar songs in the playlist by increasing the **Temperature** inference parameter. @@ -107 +105,3 @@ The inference parameters you can change are _Temperature_ , _Top P_ , and _Top K - 2. Run the prompt again to see the effect of your changes. + 12. (Optional) In **Stop sequences** , add one or more stop sequences for the model. A stop sequence ensures that the model stops generating text immediately after it generates text that matches the stop sequence. Stop sequences are useful for getting precise answers without unnecessary additional text. Not all models support stop sequences. + + 13. (Optional) In **Reasoning** select **Model reasoning** to enable model reasoning. Model reasoning is when a model uses chain of thought reasoning to take a large, complex task and break it down into smaller, simpler steps. You can only enable or disable model reasoning at the start of a new chat. You can specify the number of tokens to use, which includes both output and reasoning tokens. Not all models support model reasoning. For more information, see [Enhance model responses with model reasoning](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-reasoning.html) in the _Amazon Bedrock user guide_. @@ -109 +109 @@ The inference parameters you can change are _Temperature_ , _Top P_ , and _Top K - 12. (Optional) Share a snapshot of your app with others by following the instructions at [Share an Amazon Bedrock chat agent app](./app-share.html). + 14. (Optional) Share your app with others by following the instructions at [Share an Amazon Bedrock chat agent app](./app-share.html). @@ -111 +111 @@ The inference parameters you can change are _Temperature_ , _Top P_ , and _Top K - 13. (Optional) Export your snapshot from Amazon SageMaker Unified Studio by following the instructions at [Use your app outside of Amazon SageMaker Unified Studio](./app-export.html). + 15. (Optional) Deploy your app for use in a flow app by following the instructions at [Deploy an Amazon Bedrock chat agent app](./app-deploy.html). @@ -113 +113,3 @@ The inference parameters you can change are _Temperature_ , _Top P_ , and _Top K - 14. Next step: Add a guardrail to your app by following the instructions at Step 2: Add a guardrail to your chat agent app. + 16. (Optional) Export your snapshot from Amazon SageMaker Unified Studio by following the instructions at [Use your app outside of Amazon SageMaker Unified Studio](./app-export.html). + + 17. Next step: Add a guardrail to your app by following the instructions at Step 2: Add a guardrail to your chat agent app. @@ -184 +186 @@ To add the filter, do the following. - 14. Next step: Add a data source to your app by following the instructions at Step 3: Add a document data source to your chat agent app. + 14. Next step: Add a data source to your app by following the instructions at Step 3: Add a knowledge base to your chat agent app. @@ -189 +191 @@ To add the filter, do the following. -## Step 3: Add a document data source to your chat agent app +## Step 3: Add a knowledge base to your chat agent app @@ -191 +193 @@ To add the filter, do the following. -You can use your own data into your application by adding a data source to your app. Doing this allows your app to access to information that is only available to you. When your app passes a query to a data source, Amazon Bedrock in SageMaker Unified Studio generates a response that includes the query results from the data source. A data source can be a single file or an Amazon Bedrock Knowledge Base. For more information, see [Add a data source to your Amazon Bedrock app](./data-sources.html). +You can use your own data into your application by adding a knowledge base to your app. Doing this allows your app to access to information that is only available to you. When your app passes a query, Amazon Bedrock in SageMaker Unified Studio generates a response that includes the query results from the knowledge base. For more information, see [Add a data source to your Amazon Bedrock app](./data-sources.html). @@ -193 +195 @@ You can use your own data into your application by adding a data source to your -In this topic, you update the app you created in Step 1: Create the initial chat agent app to use a CSV file as a data source. You can add the CSV file as single file data source, or use the CSV file to create a knowledge base data source. The CSV file includes information about bands that don't have public metadata such as song length, or music genre. The user can use the app to create a playlist based on criteria such as song length or music genre. +In this topic, you update the app you created in Step 1: Create the initial chat agent app to use a CSV file as a document (local file) data source for a knowledge base. The CSV file includes information about bands that don't have public metadata such as song length, or music genre. The user can use the app to create a playlist based on criteria such as song length or music genre. @@ -233,11 +235 @@ In this topic, you update the app you created in Step 1: Create the initial chat - 3. If you don't want to create a knowledge base, do the following: - - 1. In **Data** choose **Use single file**. Not all models support the use of a single file as a data source. - - 2. Choose **Click to upload** and upload the CSV file that you created in step 1. Alternatively, add the CSV by dragging and dropping the document from your computer. - -For more information, see [Single file in a chat agent app](./data-sources.html#chat-app-data-source-document). - - 4. If you do want to use a knowledge base: - - 1. In **Data** choose **Use Knowledge Base** and then **Create Knowledge Base**. The **Create Knowledge Base** pane is shown. If you've previously created the knowledge base, go to step _4.h._ and select the knowledge base. + 3. In **Data** choose **Use Knowledge Base** and then **Create Knowledge Base**. The **Create Knowledge Base** pane is shown. If you've previously created the knowledge base, go to step _10_ and select the knowledge base. @@ -245 +237 @@ For more information, see [Single file in a chat agent app](./data-sources.html# - 2. For **Name** , enter a name for the Knowledge Base. + 4. For **Name** , enter a name for the Knowledge Base. @@ -247 +239 @@ For more information, see [Single file in a chat agent app](./data-sources.html# - 3. For **Description** , enter a description for the Knowledge Base. + 5. For **Description** , enter a description for the Knowledge Base. @@ -249 +241 @@ For more information, see [Single file in a chat agent app](./data-sources.html# - 4. In **Add data sources** , choose **Local file**. + 6. In **Add data sources** , choose **Local file**. @@ -251 +243 @@ For more information, see [Single file in a chat agent app](./data-sources.html# - 5. Choose **Click to upload** and upload the CSV file that you created in step 1. Alternatively, add the CSV by dragging and dropping the document from your computer. + 7. Choose **Click to upload** and upload the CSV file that you created in step 1. Alternatively, add the CSV by dragging and dropping the document from your computer. @@ -255 +247 @@ For more information, see [Document data source](./data-source-document.html). - 6. For **Embeddings model** , choose a model for converting your data into vector embeddings. + 8. For **Embeddings model** , choose a model for converting your data into vector embeddings. @@ -257 +249 @@ For more information, see [Document data source](./data-source-document.html). - 7. Choose **Create**. It might take Amazon Bedrock in SageMaker Unified Studio a few minutes to create the knowledge base. + 9. Choose **Create**. It might take Amazon Bedrock in SageMaker Unified Studio a few minutes to create the knowledge base. @@ -259 +251 @@ For more information, see [Document data source](./data-source-document.html). - 8. For **Select Knowledge Base** , select the Knowledge Base that you just created. + 10. For **Select Knowledge Base** , select the Knowledge Base that you just created. @@ -261 +253 @@ For more information, see [Document data source](./data-source-document.html). - 5. Test the data source by entering `Create a playlist of songs in the Lyrical Flow genre` in the prompt text box. + 11. Test the data source by entering `Create a playlist of songs in the Lyrical Flow genre` in the prompt text box. @@ -263 +255 @@ For more information, see [Document data source](./data-source-document.html). - 6. Choose the run button to send the prompt to the model. The model should respond with a playlist of songs from the Lyrical Flow genre that the CSV file contains. + 12. Choose the run button to send the prompt to the model. The model should respond with a playlist of songs from the Lyrical Flow genre that the CSV file contains. @@ -265 +257 @@ For more information, see [Document data source](./data-source-document.html). - 7. Choose **Save** to save the app. + 13. Choose **Save** to save the app. @@ -384 +376 @@ Build a chat agent app -Share a chat agent app +Deploy a chat agent app