Contains details of the inline agent's action group. Syntax To declare this entity in your AWS CloudFormation template, use the following syntax: JSON { "ActionGroupExecutor" : ActionGroupExecutor, "ActionGroupName" : String, "ActionGroupState" : String, "ApiSchema" : APISchema, "...
那我们稍微深入地讲一下这个 action group 或者操作里面都有哪些内容。这个就是主要包括三个关键的要素。第一就是 action group 的描述,这个描述就是说我们用自然语言去帮助这个智能体了解我们这个操作组适用哪些情况,就是告诉这个智能体好,你现在要做这个 group,要做这些事情。然后我们需要去定义这个 API 的架构。...
alias: 'Agent', }); 我们可以从上面的代码中看到,我们给Agent赋予了如下的关键属性:会话应持续多久,链接至我们的Amazon Bedrock知识库,FM类型(我们的情况为Claud V2),以及该Agent的指令。 我们接下来按照下面的方式创建我们的工作组: // 添加用于预订的操作组 new bedrock.AgentActionGroup(this, 'AgentActionGro...
Amazon Bedrock Agent 模型使用者輸入是內建 ActionGroup,您需要將 做為動作群組新增至您的代理程式。 下一個主題:啟用使用者輸入 上一個主題:停用多代理程式協同合作 需要協助? 嘗試AWS re:Post 與AWS IQ 專家聯絡 Related resources Amazon Bedrock API 參考 AWS CLI 的 命令 Amazon Bedrock SDK 與工具 此...
Agents automatically create a prompt template from the user instructions, action group, and knowledge bases. You can use this template as a baseline to further refine the automatically generated prompt template to enhance the user experience. You can also update the user input, orchestration plan, ...
Add the Amazon Bedrock Agents supported computer use action groups to your agent using CreateAgentActionGroup API. Invoke the agent with a user query that requires computer use tools, for example, “What is Amazon Bedrock, can you search the web?” The Amazon Bedrock agent uses the too...
return agent_finishinvocation_inputs = return_control.get("invocationInputs") if not invocation_inputs: return agent_finishtry: invocation_input = invocation_inputs[0].get("functionInvocationInput", {}) action_group = invocation_input.get("actionGroup", "") ...
This solution uses two AWS Lambda functions; the CustomResourceFunction creates the necessary vector index in the OpenSearch Serverless collection, while the ActionGroupFunction serves as a proxy to give the agent programatic access to the EKS Cluster. Run the lambda-build.sh script to install, pa...
['ability', 'able', 'about', 'above', 'accept', 'according', 'account', 'across', 'action', 'activity', 'actually', 'address', 'administration', 'admit', 'adult', 'affect', 'after', 'again', 'against', 'agency', 'agent', 'ago', 'agree', 'agreement', 'ahead', 'air',...
FILE_NAME") def lambda_handler(event, context): agent = event['agent'] actionGroup = event['actionGroup'] function = event['function'] parameters = event.get('parameters, []) print(event) print(parameters) # パラメータからPythonコードを取得 python_code = next((item["value"] for ...