AWS bedrock high security documentation change
Summary
Restructured documentation with new sections added including 'Thinking encryption', updated timeout guidance for Claude 3.7/4 models, added security warnings for Computer Use beta feature, and removed detailed tool use implementation examples in favor of linked documentation
Security assessment
Added explicit security warnings about Computer Use beta risks including information theft prevention, VM isolation recommendations, and prompt injection risks. The 'Thinking encryption' section addition indicates new security-related documentation. The timeout change addresses potential operational security issues from premature termination.
Diff
diff --git a/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.md b/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.md index e3cb50c8a..d5d05b9a9 100644 --- a//bedrock/latest/userguide/model-parameters-anthropic-claude-messages.md +++ b//bedrock/latest/userguide/model-parameters-anthropic-claude-messages.md @@ -5 +5 @@ -Anthropic Claude Messages API overviewSupported modelsRequest and ResponseCode examples +Anthropic Claude Messages API overview @@ -15 +15 @@ This section provides inference parameters and code examples for using the Anthr - * Supported models + * [Tool use](./model-parameters-anthropic-claude-messages-tool-use.html) @@ -17 +17 @@ This section provides inference parameters and code examples for using the Anthr - * Request and Response + * [Extended thinking](./claude-messages-extended-thinking.html) @@ -19 +19,9 @@ This section provides inference parameters and code examples for using the Anthr - * Code examples + * [Thinking encryption](./claude-messages-thinking-encryption.html) + + * [Differences in thinking across model versions](./claude-messages-thinking-differences.html) + + * [Request and Response](./model-parameters-anthropic-claude-messages-request-response.html) + + * [Code examples](./api-inference-examples-claude-messages-code-examples.html) + + * [Supported models](./claude-messages-supported-models.html) @@ -34 +42 @@ Anthropic trains Claude models to operate on alternating user and assistant conv -Each input message must be an object with a role and content. You can specify a single user-role message, or you can include multiple user and assistant messages. The first message must always use the user role. +Each input message must be an object with a role and content. You can specify a single user-role message, or you can include multiple user and assistant messages. @@ -71,0 +80,4 @@ For information about creating prompts for Anthropic Claude models, see [Intro t +###### Important + +The timeout period for inference calls to Anthropic Claude 3.7 Sonnet and Claude 4 models is 60 minutes. By default, AWS SDK clients timeout after 1 minute. We recommend that you increase the read timeout period of your AWS SDK client to at least 60 minutes. For example, in the AWS Python botocore SDK, change the value of the `read_timeout` field in [botocore.config](https://botocore.amazonaws.com/v1/documentation/api/latest/reference/config.html#) to at least 3600. + @@ -85 +97 @@ For more information, see [System prompts](https://docs.anthropic.com/en/docs/sy -A multimodal prompt combines multiple modalities (images and text) in a single prompt. You specify the modalities in the `content` input field. The following example shows how you could ask Anthropic Claude to describe the content of a supplied image. For example code, see Multimodal code examples. +A multimodal prompt combines multiple modalities (images and text) in a single prompt. You specify the modalities in the `content` input field. The following example shows how you could ask Anthropic Claude to describe the content of a supplied image. For example code, see [Multimodal code examples](./api-inference-examples-claude-messages-code-examples.html#api-inference-examples-claude-multimodal-code-example). @@ -127,788 +138,0 @@ Each image you include in a request counts towards your token usage. For more in -### Tool use (function calling) - -With Anthropic Claude 3 models, you can specify a tool that the model can use to answer a message. For example, you could specify a tool that gets the most popular song on a radio station. If the user passes the message _What's the most popular song on WZPZ?_ , the model determines that the tool you specifed can help answer the question. In its response, the model requests that you run the tool on its behalf. You then run the tool and pass the tool result to the model, which then generates a response for the original message. For more information, see [Tool use (function calling)](https://docs.anthropic.com/en/docs/tool-use) in the Anthropic Claude documentation. - -###### Tip - -We recommend that you use the Converse API for integrating tool use into your application. For more information, see [Use a tool to complete an Amazon Bedrock model response](./tool-use.html). - -You specify the tools that you want to make available to a model in the `tools` field. The following example is for a tool that gets the most popular songs on a radio station. - - - [ - { - "name": "top_song", - "description": "Get the most popular song played on a radio station.", - "input_schema": { - "type": "object", - "properties": { - "sign": { - "type": "string", - "description": "The call sign for the radio station for which you want the most popular song. Example calls signs are WZPZ and WKRP." - } - }, - "required": [ - "sign" - ] - } - } - ] - -When the model needs a tool to generate a response to a message, it returns information about the requested tool, and the input to the tool, in the message `content` field. It also sets the stop reason for the response to `tool_use`. - - - { - "id": "msg_bdrk_01USsY5m3XRUF4FCppHP8KBx", - "type": "message", - "role": "assistant", - "model": "claude-3-sonnet-20240229", - "stop_sequence": null, - "usage": { - "input_tokens": 375, - "output_tokens": 36 - }, - "content": [ - { - "type": "tool_use", - "id": "toolu_bdrk_01SnXQc6YVWD8Dom5jz7KhHy", - "name": "top_song", - "input": { - "sign": "WZPZ" - } - } - ], - "stop_reason": "tool_use" - } - -In your code, you call the tool on the tools behalf. You then pass the tool result (`tool_result`) in a user message to the model. - - - { - "role": "user", - "content": [ - { - "type": "tool_result", - "tool_use_id": "toolu_bdrk_01SnXQc6YVWD8Dom5jz7KhHy", - "content": "Elemental Hotel" - } - ] - } - -In its response, the model uses the tool result to generate a response for the original message. - - - { - "id": "msg_bdrk_012AaqvTiKuUSc6WadhUkDLP", - "type": "message", - "role": "assistant", - "model": "claude-3-sonnet-20240229", - "content": [ - { - "type": "text", - "text": "According to the tool, the most popular song played on radio station WZPZ is \"Elemental Hotel\"." - } - ], - "stop_reason": "end_turn" - } - -### Computer use (Beta) - -Computer use is a new Anthropic Claude model capability (in beta) available with Claude 3.5 Sonnet v2 and Claude 3.7 Sonnet. With computer use, Claude can help you automate tasks through basic GUI actions. - -###### Warning - -Computer use feature is made available to you as a ‘Beta Service’ as defined in the AWS Service Terms. It is subject to your Agreement with AWS and the AWS Service Terms, and the applicable model EULA. Please be aware that the Computer Use API poses unique risks that are distinct from standard API features or chat interfaces. These risks are heightened when using the Computer Use API to interact with the Internet. To minimize risks, consider taking precautions such as: - - * Operate computer use functionality in a dedicated Virtual Machine or container with minimal privileges to prevent direct system attacks or accidents. - - * To prevent information theft, avoid giving the Computer Use API access to sensitive accounts or data. - - * Limiting the computer use API’s internet access to required domains to reduce exposure to malicious content. - - * To ensure proper oversight, keep a human in the loop for sensitive tasks (such as making decisions that could have meaningful real-world consequences) and for anything requiring affirmative consent (such as accepting cookies, executing financial transactions, or agreeing to terms of service). - - - - -Any content that you enable Claude to see or access can potentially override instructions or cause Claude to make mistakes or perform unintended actions. Taking proper precautions, such as isolating Claude from sensitive surfaces, is essential — including to avoid risks related to prompt injection. Before enabling or requesting permissions necessary to enable computer use features in your own products, please inform end users of any relevant risks, and obtain their consent as appropriate. - -The computer use API offers several pre-defined computer use tools (_computer_20241022_ , _bash_20241022_ , and _text_editor_20241022_) for you to use. You can then create a prompt with your request, such as “send an email to Ben with the notes from my last meeting” and a screenshot (when required). The response contains a list of `tool_use` actions in JSON format (for example, scroll_down, left_button_press, screenshot). Your code runs the computer actions and provides Claude with screenshot showcasing outputs (when requested). - -The tools parameter has been updated to accept polymorphic tool types; a new `tool.type` property is being added to distinguish them. `type` is optional; if omitted, the tool is assumed to be a custom tool (previously the only tool type supported). Additionally, a new parameter, `anthropic_beta`, has been added, with a corresponding enum value: `computer-use-2024-10-22`. Only requests made with this parameter and enum can use the new computer use tools. It can be specified as follows: `"anthropic_beta": ["computer-use-2024-10-22"]`. - -For more information, see [Computer use (beta)](https://docs.anthropic.com/en/docs/build-with-claude/computer-use) in the Anthropic documentation. - -The following is an example response that assumes the request contained a screenshot of your desktop with a Firefox icon. - - - { - "id": "msg_123", - "type": "message", - "role": "assistant", - "model": "anthropic.claude-3-5-sonnet-20241022-v2:0", - "content": [ - { - "type": "text", - "text": "I see the Firefox icon. Let me click on it and then navigate to a weather website." - }, - { - "type": "tool_use", - "id": "toolu_123", - "name": "computer", - "input": { - "action": "mouse_move", - "coordinate": [ - 708, - 736 - ] - } - }, - { - "type": "tool_use", - "id": "toolu_234", - "name": "computer", - "input": { - "action": "left_click" - } - } - ], - "stop_reason": "tool_use", - "stop_sequence": null, - "usage": { - "input_tokens": 3391, - "output_tokens": 132 - } - } - -## Supported models - -You can use the Messages API with the following Anthropic Claude models. - - * Anthropic Claude Instant v1.2 - - * Anthropic Claude 2 v2 -