There are more AWS SDK examples available in the [AWS Doc SDK Examples](https://github.com/awsdocs/aws-doc-sdk-examples) GitHub repo. # Actions for Amazon Bedrock Agents using AWS SDKs The following code examples demonstrate how to perform individual Amazon Bedrock Agents actions with AWS SDKs. Each example includes a link to GitHub, where you can find instructions for setting up and running the code. These excerpts call the Amazon Bedrock Agents API and are code excerpts from larger programs that must be run in context. You can see actions in context in [Scenarios for Amazon Bedrock Agents using AWS SDKs](bedrock-agent_code_examples_scenarios.md). The following examples include only the most commonly used actions. For a complete list, see the [Amazon Bedrock Agents API Reference](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_Operations_Agents_for_Amazon_Bedrock.html). **Topics** + [`CreateAgent`](bedrock-agent_example_bedrock-agent_CreateAgent_section.md) + [`CreateAgentActionGroup`](bedrock-agent_example_bedrock-agent_CreateAgentActionGroup_section.md) + [`CreateAgentAlias`](bedrock-agent_example_bedrock-agent_CreateAgentAlias_section.md) + [`CreateFlow`](bedrock-agent_example_bedrock-agent_CreateFlow_section.md) + [`CreateFlowAlias`](bedrock-agent_example_bedrock-agent_CreateFlowAlias_section.md) + [`CreateFlowVersion`](bedrock-agent_example_bedrock-agent_CreateFlowVersion_section.md) + [`CreateKnowledgeBase`](bedrock-agent_example_bedrock-agent_CreateKnowledgeBase_section.md) + [`CreatePrompt`](bedrock-agent_example_bedrock-agent_CreatePrompt_section.md) + [`CreatePromptVersion`](bedrock-agent_example_bedrock-agent_CreatePromptVersion_section.md) + [`DeleteAgent`](bedrock-agent_example_bedrock-agent_DeleteAgent_section.md) + [`DeleteAgentAlias`](bedrock-agent_example_bedrock-agent_DeleteAgentAlias_section.md) + [`DeleteFlow`](bedrock-agent_example_bedrock-agent_DeleteFlow_section.md) + [`DeleteFlowAlias`](bedrock-agent_example_bedrock-agent_DeleteFlowAlias_section.md) + [`DeleteFlowVersion`](bedrock-agent_example_bedrock-agent_DeleteFlowVersion_section.md) + [`DeleteKnowledgeBase`](bedrock-agent_example_bedrock-agent_DeleteKnowledgeBase_section.md) + [`DeletePrompt`](bedrock-agent_example_bedrock-agent_DeletePrompt_section.md) + [`GetAgent`](bedrock-agent_example_bedrock-agent_GetAgent_section.md) + [`GetFlow`](bedrock-agent_example_bedrock-agent_GetFlow_section.md) + [`GetFlowVersion`](bedrock-agent_example_bedrock-agent_GetFlowVersion_section.md) + [`GetKnowledgeBase`](bedrock-agent_example_bedrock-agent_GetKnowledgeBase_section.md) + [`GetPrompt`](bedrock-agent_example_bedrock-agent_GetPrompt_section.md) + [`ListAgentActionGroups`](bedrock-agent_example_bedrock-agent_ListAgentActionGroups_section.md) + [`ListAgentKnowledgeBases`](bedrock-agent_example_bedrock-agent_ListAgentKnowledgeBases_section.md) + [`ListAgents`](bedrock-agent_example_bedrock-agent_ListAgents_section.md) + [`ListFlowAliases`](bedrock-agent_example_bedrock-agent_ListFlowAliases_section.md) + [`ListFlowVersions`](bedrock-agent_example_bedrock-agent_ListFlowVersions_section.md) + [`ListFlows`](bedrock-agent_example_bedrock-agent_ListFlows_section.md) + [`ListKnowledgeBases`](bedrock-agent_example_bedrock-agent_ListKnowledgeBases_section.md) + [`ListPrompts`](bedrock-agent_example_bedrock-agent_ListPrompts_section.md) + [`PrepareAgent`](bedrock-agent_example_bedrock-agent_PrepareAgent_section.md) + [`PrepareFlow`](bedrock-agent_example_bedrock-agent_PrepareFlow_section.md) + [`UpdateFlow`](bedrock-agent_example_bedrock-agent_UpdateFlow_section.md) + [`UpdateFlowAlias`](bedrock-agent_example_bedrock-agent_UpdateFlowAlias_section.md) + [`UpdateKnowledgeBase`](bedrock-agent_example_bedrock-agent_UpdateKnowledgeBase_section.md) # Use `CreateAgent` with an AWS SDK The following code examples show how to use `CreateAgent`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ JavaScript ] **SDK for JavaScript (v3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/bedrock-agent#code-examples). Create an agent. ``` import { fileURLToPath } from "node:url"; import { checkForPlaceholders } from "../lib/utils.js"; import { BedrockAgentClient, CreateAgentCommand, } from "@aws-sdk/client-bedrock-agent"; /** * Creates an Amazon Bedrock Agent. * * @param {string} agentName - A name for the agent that you create. * @param {string} foundationModel - The foundation model to be used by the agent you create. * @param {string} agentResourceRoleArn - The ARN of the IAM role with permissions required by the agent. * @param {string} [region='us-east-1'] - The AWS region in use. * @returns {Promise} An object containing details of the created agent. */ export const createAgent = async ( agentName, foundationModel, agentResourceRoleArn, region = "us-east-1", ) => { const client = new BedrockAgentClient({ region }); const command = new CreateAgentCommand({ agentName, foundationModel, agentResourceRoleArn, }); const response = await client.send(command); return response.agent; }; // Invoke main function if this file was run directly. if (process.argv[1] === fileURLToPath(import.meta.url)) { // Replace the placeholders for agentName and accountId, and roleName with a unique name for the new agent, // the id of your AWS account, and the name of an existing execution role that the agent can use inside your account. // For foundationModel, specify the desired model. Ensure to remove the brackets '[]' before adding your data. // A string (max 100 chars) that can include letters, numbers, dashes '-', and underscores '_'. const agentName = "[your-bedrock-agent-name]"; // Your AWS account id. const accountId = "[123456789012]"; // The name of the agent's execution role. It must be prefixed by `AmazonBedrockExecutionRoleForAgents_`. const roleName = "[AmazonBedrockExecutionRoleForAgents_your-role-name]"; // The ARN for the agent's execution role. // Follow the ARN format: 'arn:aws:iam::account-id:role/role-name' const roleArn = `arn:aws:iam::${accountId}:role/${roleName}`; // Specify the model for the agent. Change if a different model is preferred. const foundationModel = "anthropic.claude-v2"; // Check for unresolved placeholders in agentName and roleArn. checkForPlaceholders([agentName, roleArn]); console.log("Creating a new agent..."); const agent = await createAgent(agentName, foundationModel, roleArn); console.log(agent); } ``` + For API details, see [CreateAgent](https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/bedrock-agent/command/CreateAgentCommand) in *AWS SDK for JavaScript API Reference*. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create an agent. ``` def create_agent(self, agent_name, foundation_model, role_arn, instruction): """ Creates an agent that orchestrates interactions between foundation models, data sources, software applications, user conversations, and APIs to carry out tasks to help customers. :param agent_name: A name for the agent. :param foundation_model: The foundation model to be used for orchestration by the agent. :param role_arn: The ARN of the IAM role with permissions needed by the agent. :param instruction: Instructions that tell the agent what it should do and how it should interact with users. :return: The response from Amazon Bedrock Agents if successful, otherwise raises an exception. """ try: response = self.client.create_agent( agentName=agent_name, foundationModel=foundation_model, agentResourceRoleArn=role_arn, instruction=instruction, ) except ClientError as e: logger.error(f"Error: Couldn't create agent. Here's why: {e}") raise else: return response["agent"] ``` + For API details, see [CreateAgent](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreateAgent) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `CreateAgentActionGroup` with an AWS SDK The following code example shows how to use `CreateAgentActionGroup`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create an agent action group. ``` def create_agent_action_group( self, name, description, agent_id, agent_version, function_arn, api_schema ): """ Creates an action group for an agent. An action group defines a set of actions that an agent should carry out for the customer. :param name: The name to give the action group. :param description: The description of the action group. :param agent_id: The unique identifier of the agent for which to create the action group. :param agent_version: The version of the agent for which to create the action group. :param function_arn: The ARN of the Lambda function containing the business logic that is carried out upon invoking the action. :param api_schema: Contains the OpenAPI schema for the action group. :return: Details about the action group that was created. """ try: response = self.client.create_agent_action_group( actionGroupName=name, description=description, agentId=agent_id, agentVersion=agent_version, actionGroupExecutor={"lambda": function_arn}, apiSchema={"payload": api_schema}, ) agent_action_group = response["agentActionGroup"] except ClientError as e: logger.error(f"Error: Couldn't create agent action group. Here's why: {e}") raise else: return agent_action_group ``` + For API details, see [CreateAgentActionGroup](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreateAgentActionGroup) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `CreateAgentAlias` with an AWS SDK The following code example shows how to use `CreateAgentAlias`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create an agent alias. ``` def create_agent_alias(self, name, agent_id): """ Creates an alias of an agent that can be used to deploy the agent. :param name: The name of the alias. :param agent_id: The unique identifier of the agent. :return: Details about the alias that was created. """ try: response = self.client.create_agent_alias( agentAliasName=name, agentId=agent_id ) agent_alias = response["agentAlias"] except ClientError as e: logger.error(f"Couldn't create agent alias. {e}") raise else: return agent_alias ``` + For API details, see [CreateAgentAlias](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreateAgentAlias) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `CreateFlow` with an AWS SDK The following code example shows how to use `CreateFlow`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create an Amazon Bedrock flow. ``` def create_flow(client, flow_name, flow_description, role_arn, flow_def): """ Creates an Amazon Bedrock flow. Args: client: Amazon Bedrock agent boto3 client. flow_name (str): The name for the new flow. role_arn (str): The ARN for the IAM role that use flow uses. flow_def (json): The JSON definition of the flow that you want to create. Returns: dict: The response from CreateFlow. """ try: logger.info("Creating flow: %s.", flow_name) response = client.create_flow( name=flow_name, description=flow_description, executionRoleArn=role_arn, definition=flow_def ) logger.info("Successfully created flow: %s. ID: %s", flow_name, {response['id']}) return response except ClientError as e: logger.exception("Client error creating flow: %s", {str(e)}) raise except Exception as e: logger.exception("Unexepcted error creating flow: %s", {str(e)}) raise ``` + For API details, see [CreateFlow](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreateFlow) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `CreateFlowAlias` with an AWS SDK The following code example shows how to use `CreateFlowAlias`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create an alias for an Amazon Bedrock flow. ``` def create_flow_alias(client, flow_id, flow_version, name, description): """ Creates an alias for an Amazon Bedrock flow. Args: client: bedrock agent boto3 client. flow_id (str): The identifier of the flow. Returns: str: The ID for the flow alias. """ try: logger.info("Creating flow alias for flow: %s.", flow_id) response = client.create_flow_alias( flowIdentifier=flow_id, name=name, description=description, routingConfiguration=[ { "flowVersion": flow_version } ] ) logger.info("Successfully created flow alias for %s.", flow_id) return response['id'] except ClientError as e: logging.exception("Client error creating alias for flow: %s - %s", flow_id, str(e)) raise except Exception as e: logging.exception("Unexpected error creating alias for flow : %s - %s", flow_id, str(e)) raise ``` + For API details, see [CreateFlowAlias](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreateFlowAlias) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `CreateFlowVersion` with an AWS SDK The following code example shows how to use `CreateFlowVersion`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create a version of an Amazon Bedrock flow. ``` def create_flow_version(client, flow_id, description): """ Creates a version of an Amazon Bedrock flow. Args: client: Amazon Bedrock agent boto3 client. flow_id (str): The identifier of the flow. description (str) : A description for the flow. Returns: str: The version for the flow. """ try: logger.info("Creating flow version for flow: %s.", flow_id) # Call CreateFlowVersion operation response = client.create_flow_version( flowIdentifier=flow_id, description=description ) logging.info("Successfully created flow version %s for flow %s.", response['version'], flow_id) return response['version'] except ClientError as e: logging.exception("Client error creating flow: %s", str(e)) raise except Exception as e: logging.exception("Unexpected error creating flow : %s", str(e)) raise ``` + For API details, see [CreateFlowVersion](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreateFlowVersion) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `CreateKnowledgeBase` with an AWS SDK The following code example shows how to use `CreateKnowledgeBase`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create an Amazon Bedrock knowledge base. ``` def create_knowledge_base(bedrock_agent_client, name, role_arn, description=None): """ Creates a new knowledge base. Args: bedrock_agent_client: The Boto3 Bedrock Agent client. name (str): The name of the knowledge base. role_arn (str): The ARN of the IAM role that the knowledge base assumes to access resources. description (str, optional): A description of the knowledge base. Returns: dict: The details of the created knowledge base. """ try: kwargs = { "name": name, "roleArn": role_arn, "knowledgeBaseConfiguration": { "type": "VECTOR", "vectorKnowledgeBaseConfiguration": { "embeddingModelArn": "arn:aws:bedrock:us-east-1::foundation-model/amazon.titan-embed-text-v1" } }, "storageConfiguration": { "type": "OPENSEARCH_SERVERLESS", # Note: You will need to create an OpenSearch Serverless collection first and replace this ARN # with your actual collection ARN from the OpenSearch console. If you use the console instead, # you can use the quick-create flow to have Knowledge Bases create the collection for you. "opensearchServerlessConfiguration": { "collectionArn": "arn:aws:aoss:us-east-1::123456789012:collection/abcdefgh12345678defgh", "fieldMapping": { "metadataField": "metadata", "textField": "text", "vectorField": "vector" }, "vectorIndexName": "test-uuid" }, }, "clientToken": "test-client-token-" + str(uuid.uuid4()) } if description: kwargs["description"] = description response = bedrock_agent_client.create_knowledge_base(**kwargs) logger.info("Created knowledge base with ID: %s", response["knowledgeBase"]["knowledgeBaseId"]) return response["knowledgeBase"] except ClientError as err: logger.error( "Couldn't create knowledge base. Here's why: %s: %s", err.response["Error"]["Code"], err.response["Error"]["Message"], ) raise ``` + For API details, see [CreateKnowledgeBase](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreateKnowledgeBase) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `CreatePrompt` with an AWS SDK The following code example shows how to use `CreatePrompt`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a managed prompt](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockPrompts_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create an Amazon Bedrock managed prompt. ``` def create_prompt(client, prompt_name, prompt_description, prompt_template, model_id=None): """ Creates an Amazon Bedrock managed prompt. Args: client: Amazon Bedrock Agent boto3 client. prompt_name (str): The name for the new prompt. prompt_description (str): The description for the new prompt. prompt_template (str): The template for the prompt. model_id (str, optional): The model ID to associate with the prompt. Returns: dict: The response from CreatePrompt. """ try: logger.info("Creating prompt: %s.", prompt_name) # Create a variant with the template variant = { "name": "default", "templateType": "TEXT", "templateConfiguration": { "text": { "text": prompt_template, "inputVariables": [] } } } # Extract input variables from the template # Look for patterns like {{variable_name}} variables = re.findall(r'{{(.*?)}}', prompt_template) for var in variables: variant["templateConfiguration"]["text"]["inputVariables"].append({"name": var.strip()}) # Add model ID if provided if model_id: variant["modelId"] = model_id # Create the prompt with the variant create_params = { 'name': prompt_name, 'description': prompt_description, 'variants': [variant] } response = client.create_prompt(**create_params) logger.info("Successfully created prompt: %s. ID: %s", prompt_name, response['id']) return response except ClientError as e: logger.exception("Client error creating prompt: %s", str(e)) raise except Exception as e: logger.exception("Unexpected error creating prompt: %s", str(e)) raise ``` + For API details, see [CreatePrompt](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreatePrompt) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `CreatePromptVersion` with an AWS SDK The following code example shows how to use `CreatePromptVersion`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a managed prompt](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockPrompts_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Create a version of an Amazon Bedrock managed prompt. ``` def create_prompt_version(client, prompt_id, description=None): """ Creates a version of an Amazon Bedrock managed prompt. Args: client: Amazon Bedrock Agent boto3 client. prompt_id (str): The identifier of the prompt to create a version for. description (str, optional): A description for the version. Returns: dict: The response from CreatePromptVersion. """ try: logger.info("Creating version for prompt ID: %s.", prompt_id) create_params = { 'promptIdentifier': prompt_id } if description: create_params['description'] = description response = client.create_prompt_version(**create_params) logger.info("Successfully created prompt version: %s", response['version']) logger.info("Prompt version ARN: %s", response['arn']) return response except ClientError as e: logger.exception("Client error creating prompt version: %s", str(e)) raise except Exception as e: logger.exception("Unexpected error creating prompt version: %s", str(e)) raise ``` + For API details, see [CreatePromptVersion](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/CreatePromptVersion) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `DeleteAgent` with an AWS SDK The following code examples show how to use `DeleteAgent`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ JavaScript ] **SDK for JavaScript (v3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/bedrock-agent#code-examples). Delete an agent. ``` import { fileURLToPath } from "node:url"; import { checkForPlaceholders } from "../lib/utils.js"; import { BedrockAgentClient, DeleteAgentCommand, } from "@aws-sdk/client-bedrock-agent"; /** * Deletes an Amazon Bedrock Agent. * * @param {string} agentId - The unique identifier of the agent to delete. * @param {string} [region='us-east-1'] - The AWS region in use. * @returns {Promise} An object containing the agent id, the status, and some additional metadata. */ export const deleteAgent = (agentId, region = "us-east-1") => { const client = new BedrockAgentClient({ region }); const command = new DeleteAgentCommand({ agentId }); return client.send(command); }; // Invoke main function if this file was run directly. if (process.argv[1] === fileURLToPath(import.meta.url)) { // Replace the placeholders for agentId with an existing agent's id. // Ensure to remove the brackets (`[]`) before adding your data. // The agentId must be an alphanumeric string with exactly 10 characters. const agentId = "[ABC123DE45]"; // Check for unresolved placeholders in agentId. checkForPlaceholders([agentId]); console.log(`Deleting agent with ID ${agentId}...`); const response = await deleteAgent(agentId); console.log(response); } ``` + For API details, see [DeleteAgent](https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/bedrock-agent/command/DeleteAgentCommand) in *AWS SDK for JavaScript API Reference*. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Delete an agent. ``` def delete_agent(self, agent_id): """ Deletes an Amazon Bedrock agent. :param agent_id: The unique identifier of the agent to delete. :return: The response from Amazon Bedrock Agents if successful, otherwise raises an exception. """ try: response = self.client.delete_agent( agentId=agent_id, skipResourceInUseCheck=False ) except ClientError as e: logger.error(f"Couldn't delete agent. {e}") raise else: return response ``` + For API details, see [DeleteAgent](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/DeleteAgent) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `DeleteAgentAlias` with an AWS SDK The following code example shows how to use `DeleteAgentAlias`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Delete an agent alias. ``` def delete_agent_alias(self, agent_id, agent_alias_id): """ Deletes an alias of an Amazon Bedrock agent. :param agent_id: The unique identifier of the agent that the alias belongs to. :param agent_alias_id: The unique identifier of the alias to delete. :return: The response from Amazon Bedrock Agents if successful, otherwise raises an exception. """ try: response = self.client.delete_agent_alias( agentId=agent_id, agentAliasId=agent_alias_id ) except ClientError as e: logger.error(f"Couldn't delete agent alias. {e}") raise else: return response ``` + For API details, see [DeleteAgentAlias](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/DeleteAgentAlias) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `DeleteFlow` with an AWS SDK The following code example shows how to use `DeleteFlow`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Delete an Amazon Bedrock flow. ``` def delete_flow(client, flow_id): """ Deletes an Amazon Bedrock flow. Args: client: Amazon Bedrock agent boto3 client. flow_id (str): The identifier of the flow that you want to delete. Returns: dict: The response from the DeleteFLow operation. """ try: logger.info("Deleting flow ID: %s.", flow_id) # Call DeleteFlow operation response = client.delete_flow( flowIdentifier=flow_id, skipResourceInUseCheck=True ) logger.info("Finished deleting flow ID: %s", flow_id) return response except ClientError as e: logger.exception("Client error deleting flow: %s", {str(e)}) raise except Exception as e: logger.exception("Unexepcted error deleting flow: %s", {str(e)}) raise ``` + For API details, see [DeleteFlow](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/DeleteFlow) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `DeleteFlowAlias` with an AWS SDK The following code example shows how to use `DeleteFlowAlias`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Delete an alias for an Amazon Bedrock flow. ``` def delete_flow_alias(client, flow_id, flow_alias_id): """ Deletes an Amazon Bedrock flow alias. Args: client: bedrock agent boto3 client. flow_id (str): The identifier of the flow. Returns: dict: The response from the call to DetectFLowAlias """ try: logger.info("Deleting flow alias %s for flow: %s.", flow_alias_id, flow_id) # Delete the flow alias. response = client.delete_flow_alias( aliasIdentifier=flow_alias_id, flowIdentifier=flow_id ) logging.info("Successfully deleted flow version for %s.", flow_id) return response except ClientError as e: logging.exception("Client error deleting flow version: %s", str(e)) raise except Exception as e: logging.exception("Unexpected deleting flow version: %s", str(e)) raise ``` + For API details, see [DeleteFlowAlias](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/DeleteFlowAlias) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `DeleteFlowVersion` with an AWS SDK The following code example shows how to use `DeleteFlowVersion`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Delete a version of an Amazon Bedrock flow. ``` def delete_flow_version(client, flow_id, flow_version): """ Deletes a version of an Amazon Bedrock flow. Args: client: Amazon Bedrock agent boto3 client. flow_id (str): The identifier of the flow. Returns: dict: The response from DeleteFlowVersion. """ try: logger.info("Deleting flow version %s for flow: %s.",flow_version, flow_id) # Call DeleteFlowVersion operation response = client.delete_flow_version( flowIdentifier=flow_id, flowVersion=flow_version ) logging.info("Successfully deleted flow version %s for %s.", flow_version, flow_id) return response except ClientError as e: logging.exception("Client error deleting flow version: %s ", str(e)) raise except Exception as e: logging.exception("Unexpected deleting flow version: %s", str(e)) raise ``` + For API details, see [DeleteFlowVersion](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/DeleteFlowVersion) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `DeleteKnowledgeBase` with an AWS SDK The following code example shows how to use `DeleteKnowledgeBase`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Delete an Amazon Bedrock knowledge base. ``` def delete_knowledge_base(bedrock_agent_client, knowledge_base_id): """ Deletes a knowledge base. Args: bedrock_agent_client: The Boto3 Bedrock Agent client. knowledge_base_id (str): The ID of the knowledge base to delete. Returns: bool: True if the deletion was successful. """ try: bedrock_agent_client.delete_knowledge_base( knowledgeBaseId=knowledge_base_id ) logger.info("Deleted knowledge base: %s", knowledge_base_id) return True except ClientError as err: logger.error( "Couldn't delete knowledge base %s. Here's why: %s: %s", knowledge_base_id, err.response["Error"]["Code"], err.response["Error"]["Message"], ) raise ``` + For API details, see [DeleteKnowledgeBase](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/DeleteKnowledgeBase) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `DeletePrompt` with an AWS SDK The following code example shows how to use `DeletePrompt`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a managed prompt](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockPrompts_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Delete an Amazon Bedrock managed prompt. ``` def delete_prompt(client, prompt_id): """ Deletes an Amazon Bedrock managed prompt. Args: client: Amazon Bedrock Agent boto3 client. prompt_id (str): The identifier of the prompt that you want to delete. Returns: dict: The response from the DeletePrompt operation. """ try: logger.info("Deleting prompt ID: %s.", prompt_id) response = client.delete_prompt( promptIdentifier=prompt_id ) logger.info("Finished deleting prompt ID: %s", prompt_id) return response except ClientError as e: logger.exception("Client error deleting prompt: %s", str(e)) raise except Exception as e: logger.exception("Unexpected error deleting prompt: %s", str(e)) raise ``` + For API details, see [DeletePrompt](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/DeletePrompt) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `GetAgent` with an AWS SDK The following code examples show how to use `GetAgent`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ JavaScript ] **SDK for JavaScript (v3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/bedrock-agent#code-examples). Get an agent. ``` import { fileURLToPath } from "node:url"; import { checkForPlaceholders } from "../lib/utils.js"; import { BedrockAgentClient, GetAgentCommand, } from "@aws-sdk/client-bedrock-agent"; /** * Retrieves the details of an Amazon Bedrock Agent. * * @param {string} agentId - The unique identifier of the agent. * @param {string} [region='us-east-1'] - The AWS region in use. * @returns {Promise} An object containing the agent details. */ export const getAgent = async (agentId, region = "us-east-1") => { const client = new BedrockAgentClient({ region }); const command = new GetAgentCommand({ agentId }); const response = await client.send(command); return response.agent; }; // Invoke main function if this file was run directly. if (process.argv[1] === fileURLToPath(import.meta.url)) { // Replace the placeholders for agentId with an existing agent's id. // Ensure to remove the brackets '[]' before adding your data. // The agentId must be an alphanumeric string with exactly 10 characters. const agentId = "[ABC123DE45]"; // Check for unresolved placeholders in agentId. checkForPlaceholders([agentId]); console.log(`Retrieving agent with ID ${agentId}...`); const agent = await getAgent(agentId); console.log(agent); } ``` + For API details, see [GetAgent](https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/bedrock-agent/command/GetAgentCommand) in *AWS SDK for JavaScript API Reference*. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Get an agent. ``` def get_agent(self, agent_id, log_error=True): """ Gets information about an agent. :param agent_id: The unique identifier of the agent. :param log_error: Whether to log any errors that occur when getting the agent. If True, errors will be logged to the logger. If False, errors will still be raised, but not logged. :return: The information about the requested agent. """ try: response = self.client.get_agent(agentId=agent_id) agent = response["agent"] except ClientError as e: if log_error: logger.error(f"Couldn't get agent {agent_id}. {e}") raise else: return agent ``` + For API details, see [GetAgent](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/GetAgent) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `GetFlow` with an AWS SDK The following code example shows how to use `GetFlow`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Get an Amazon Bedrock flow. ``` def get_flow(client, flow_id): """ Gets an Amazon Bedrock flow. Args: client: bedrock agent boto3 client. flow_id (str): The identifier of the flow that you want to get. Returns: dict: The response from the GetFlow operation. """ try: logger.info("Getting flow ID: %s.", flow_id) # Call GetFlow operation. response = client.get_flow( flowIdentifier=flow_id ) logger.info("Retrieved flow ID: %s. Name: %s", flow_id, response['name']) return response except ClientError as e: logger.exception("Client error getting flow: %s", {str(e)}) raise except Exception as e: logger.exception("Unexepcted error getting flow: %s", {str(e)}) raise ``` + For API details, see [GetFlow](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/GetFlow) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `GetFlowVersion` with an AWS SDK The following code example shows how to use `GetFlowVersion`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Get a version of an Amazon Bedrock flow. ``` def get_flow_version(client, flow_id, flow_version): """ Gets information about a version of an Amazon Bedrock flow. Args: client: Amazon Bedrock agent boto3 client. flow_id (str): The identifier of the flow. flow_version (str): The flow version of the flow. Returns: dict: The response from the call to GetFlowVersion. """ try: logger.info("Deleting flow version for flow: %s.", flow_id) # Call GetFlowVersion operation response = client.get_flow_version( flowIdentifier=flow_id, flowVersion=flow_version ) logging.info("Successfully got flow version %s information for flow %s.", flow_version, flow_id) return response except ClientError as e: logging.exception("Client error getting flow version: %s", str(e)) raise except Exception as e: logging.exception("Unexpected error getting flow version: %s", str(e)) raise ``` + For API details, see [GetFlowVersion](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/GetFlowVersion) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `GetKnowledgeBase` with an AWS SDK The following code example shows how to use `GetKnowledgeBase`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Get an Amazon Bedrock knowledge base. ``` def get_knowledge_base(bedrock_agent_client, knowledge_base_id): """ Gets details about a specific knowledge base. Args: bedrock_agent_client: The Boto3 Bedrock Agent client. knowledge_base_id (str): The ID of the knowledge base. Returns: dict: The details of the knowledge base. """ try: response = bedrock_agent_client.get_knowledge_base( knowledgeBaseId=knowledge_base_id ) logger.info("Retrieved knowledge base: %s", knowledge_base_id) return response["knowledgeBase"] except ClientError as err: logger.error( "Couldn't get knowledge base %s. Here's why: %s: %s", knowledge_base_id, err.response["Error"]["Code"], err.response["Error"]["Message"], ) raise ``` + For API details, see [GetKnowledgeBase](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/GetKnowledgeBase) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `GetPrompt` with an AWS SDK The following code example shows how to use `GetPrompt`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Get an Amazon Bedrock managed prompt. ``` def get_prompt(client, prompt_id): """ Gets an Amazon Bedrock managed prompt. Args: client: Amazon Bedrock Agent boto3 client. prompt_id (str): The identifier of the prompt that you want to get. Returns: dict: The response from the GetPrompt operation. """ try: logger.info("Getting prompt ID: %s.", prompt_id) response = client.get_prompt( promptIdentifier=prompt_id ) logger.info("Retrieved prompt ID: %s. Name: %s", prompt_id, response['name']) return response except ClientError as e: logger.exception("Client error getting prompt: %s", str(e)) raise except Exception as e: logger.exception("Unexpected error getting prompt: %s", str(e)) raise ``` + For API details, see [GetPrompt](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/GetPrompt) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `ListAgentActionGroups` with an AWS SDK The following code examples show how to use `ListAgentActionGroups`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ JavaScript ] **SDK for JavaScript (v3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/bedrock-agent#code-examples). List the action groups for an agent. ``` import { fileURLToPath } from "node:url"; import { checkForPlaceholders } from "../lib/utils.js"; import { BedrockAgentClient, ListAgentActionGroupsCommand, paginateListAgentActionGroups, } from "@aws-sdk/client-bedrock-agent"; /** * Retrieves a list of Action Groups of an agent utilizing the paginator function. * * This function leverages a paginator, which abstracts the complexity of pagination, providing * a straightforward way to handle paginated results inside a `for await...of` loop. * * @param {string} agentId - The unique identifier of the agent. * @param {string} agentVersion - The version of the agent. * @param {string} [region='us-east-1'] - The AWS region in use. * @returns {Promise} An array of action group summaries. */ export const listAgentActionGroupsWithPaginator = async ( agentId, agentVersion, region = "us-east-1", ) => { const client = new BedrockAgentClient({ region }); // Create a paginator configuration const paginatorConfig = { client, pageSize: 10, // optional, added for demonstration purposes }; const params = { agentId, agentVersion }; const pages = paginateListAgentActionGroups(paginatorConfig, params); // Paginate until there are no more results const actionGroupSummaries = []; for await (const page of pages) { actionGroupSummaries.push(...page.actionGroupSummaries); } return actionGroupSummaries; }; /** * Retrieves a list of Action Groups of an agent utilizing the ListAgentActionGroupsCommand. * * This function demonstrates the manual approach, sending a command to the client and processing the response. * Pagination must manually be managed. For a simplified approach that abstracts away pagination logic, see * the `listAgentActionGroupsWithPaginator()` example below. * * @param {string} agentId - The unique identifier of the agent. * @param {string} agentVersion - The version of the agent. * @param {string} [region='us-east-1'] - The AWS region in use. * @returns {Promise} An array of action group summaries. */ export const listAgentActionGroupsWithCommandObject = async ( agentId, agentVersion, region = "us-east-1", ) => { const client = new BedrockAgentClient({ region }); let nextToken; const actionGroupSummaries = []; do { const command = new ListAgentActionGroupsCommand({ agentId, agentVersion, nextToken, maxResults: 10, // optional, added for demonstration purposes }); /** @type {{actionGroupSummaries: ActionGroupSummary[], nextToken?: string}} */ const response = await client.send(command); for (const actionGroup of response.actionGroupSummaries || []) { actionGroupSummaries.push(actionGroup); } nextToken = response.nextToken; } while (nextToken); return actionGroupSummaries; }; // Invoke main function if this file was run directly. if (process.argv[1] === fileURLToPath(import.meta.url)) { // Replace the placeholders for agentId and agentVersion with an existing agent's id and version. // Ensure to remove the brackets '[]' before adding your data. // The agentId must be an alphanumeric string with exactly 10 characters. const agentId = "[ABC123DE45]"; // A string either containing `DRAFT` or a number with 1-5 digits (e.g., '123' or 'DRAFT'). const agentVersion = "[DRAFT]"; // Check for unresolved placeholders in agentId and agentVersion. checkForPlaceholders([agentId, agentVersion]); console.log("=".repeat(68)); console.log( "Listing agent action groups using ListAgentActionGroupsCommand:", ); for (const actionGroup of await listAgentActionGroupsWithCommandObject( agentId, agentVersion, )) { console.log(actionGroup); } console.log("=".repeat(68)); console.log( "Listing agent action groups using the paginateListAgents function:", ); for (const actionGroup of await listAgentActionGroupsWithPaginator( agentId, agentVersion, )) { console.log(actionGroup); } } ``` + For API details, see [ListAgentActionGroups](https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/bedrock-agent/command/ListAgentActionGroupsCommand) in *AWS SDK for JavaScript API Reference*. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). List the action groups for an agent. ``` def list_agent_action_groups(self, agent_id, agent_version): """ List the action groups for a version of an Amazon Bedrock Agent. :param agent_id: The unique identifier of the agent. :param agent_version: The version of the agent. :return: The list of action group summaries for the version of the agent. """ try: action_groups = [] paginator = self.client.get_paginator("list_agent_action_groups") for page in paginator.paginate( agentId=agent_id, agentVersion=agent_version, PaginationConfig={"PageSize": 10}, ): action_groups.extend(page["actionGroupSummaries"]) except ClientError as e: logger.error(f"Couldn't list action groups. {e}") raise else: return action_groups ``` + For API details, see [ListAgentActionGroups](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/ListAgentActionGroups) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `ListAgentKnowledgeBases` with an AWS SDK The following code example shows how to use `ListAgentKnowledgeBases`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). List the knowledge bases associated with an agent. ``` def list_agent_knowledge_bases(self, agent_id, agent_version): """ List the knowledge bases associated with a version of an Amazon Bedrock Agent. :param agent_id: The unique identifier of the agent. :param agent_version: The version of the agent. :return: The list of knowledge base summaries for the version of the agent. """ try: knowledge_bases = [] paginator = self.client.get_paginator("list_agent_knowledge_bases") for page in paginator.paginate( agentId=agent_id, agentVersion=agent_version, PaginationConfig={"PageSize": 10}, ): knowledge_bases.extend(page["agentKnowledgeBaseSummaries"]) except ClientError as e: logger.error(f"Couldn't list knowledge bases. {e}") raise else: return knowledge_bases ``` + For API details, see [ListAgentKnowledgeBases](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/ListAgentKnowledgeBases) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `ListAgents` with an AWS SDK The following code examples show how to use `ListAgents`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ JavaScript ] **SDK for JavaScript (v3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/bedrock-agent#code-examples). List the agents belonging to an account. ``` import { fileURLToPath } from "node:url"; import { BedrockAgentClient, ListAgentsCommand, paginateListAgents, } from "@aws-sdk/client-bedrock-agent"; /** * Retrieves a list of available Amazon Bedrock agents utilizing the paginator function. * * This function leverages a paginator, which abstracts the complexity of pagination, providing * a straightforward way to handle paginated results inside a `for await...of` loop. * * @param {string} [region='us-east-1'] - The AWS region in use. * @returns {Promise} An array of agent summaries. */ export const listAgentsWithPaginator = async (region = "us-east-1") => { const client = new BedrockAgentClient({ region }); const paginatorConfig = { client, pageSize: 10, // optional, added for demonstration purposes }; const pages = paginateListAgents(paginatorConfig, {}); // Paginate until there are no more results const agentSummaries = []; for await (const page of pages) { agentSummaries.push(...page.agentSummaries); } return agentSummaries; }; /** * Retrieves a list of available Amazon Bedrock agents utilizing the ListAgentsCommand. * * This function demonstrates the manual approach, sending a command to the client and processing the response. * Pagination must manually be managed. For a simplified approach that abstracts away pagination logic, see * the `listAgentsWithPaginator()` example below. * * @param {string} [region='us-east-1'] - The AWS region in use. * @returns {Promise} An array of agent summaries. */ export const listAgentsWithCommandObject = async (region = "us-east-1") => { const client = new BedrockAgentClient({ region }); let nextToken; const agentSummaries = []; do { const command = new ListAgentsCommand({ nextToken, maxResults: 10, // optional, added for demonstration purposes }); /** @type {{agentSummaries: AgentSummary[], nextToken?: string}} */ const paginatedResponse = await client.send(command); agentSummaries.push(...(paginatedResponse.agentSummaries || [])); nextToken = paginatedResponse.nextToken; } while (nextToken); return agentSummaries; }; // Invoke main function if this file was run directly. if (process.argv[1] === fileURLToPath(import.meta.url)) { console.log("=".repeat(68)); console.log("Listing agents using ListAgentsCommand:"); for (const agent of await listAgentsWithCommandObject()) { console.log(agent); } console.log("=".repeat(68)); console.log("Listing agents using the paginateListAgents function:"); for (const agent of await listAgentsWithPaginator()) { console.log(agent); } } ``` + For API details, see [ListAgents](https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/bedrock-agent/command/ListAgentsCommand) in *AWS SDK for JavaScript API Reference*. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). List the agents belonging to an account. ``` def list_agents(self): """ List the available Amazon Bedrock Agents. :return: The list of available bedrock agents. """ try: all_agents = [] paginator = self.client.get_paginator("list_agents") for page in paginator.paginate(PaginationConfig={"PageSize": 10}): all_agents.extend(page["agentSummaries"]) except ClientError as e: logger.error(f"Couldn't list agents. {e}") raise else: return all_agents ``` + For API details, see [ListAgents](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/ListAgents) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `ListFlowAliases` with an AWS SDK The following code example shows how to use `ListFlowAliases`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). List the aliases for an Amazon Bedrock flow. ``` def list_flow_aliases(client, flow_id): """ Lists the aliases of an Amazon Bedrock flow. Args: client: bedrock agent boto3 client. flow_id (str): The identifier of the flow. Returns: dict: The response from ListFlowAliases. """ try: finished = False logger.info("Listing flow aliases for flow: %s.", flow_id) print(f"Aliases for flow: {flow_id}") response = client.list_flow_aliases( flowIdentifier=flow_id, maxResults=10) while finished is False: for alias in response['flowAliasSummaries']: print(f"Alias Name: {alias['name']}") print(f"ID: {alias['id']}") print(f"Description: {alias.get('description', 'No description')}\n") if 'nextToken' in response: next_token = response['nextToken'] response = client.list_flow_aliases(maxResults=10, nextToken=next_token) else: finished = True logging.info("Successfully listed flow aliases for flow %s.", flow_id) return response except ClientError as e: logging.exception("Client error listing flow aliases: %s", str(e)) raise except Exception as e: logging.exception("Unexpected error listing flow aliases: %s", str(e)) raise ``` + For API details, see [ListFlowAliases](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/ListFlowAliases) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `ListFlowVersions` with an AWS SDK The following code example shows how to use `ListFlowVersions`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). List the versions of an Amazon Bedrock flow. ``` def list_flow_versions(client, flow_id): """ Lists the versions of an Amazon Bedrock flow. Args: client: Amazon bedrock agent boto3 client. flow_id (str): The identifier of the flow. Returns: dict: The response from ListFlowVersions. """ try: finished = False logger.info("Listing flow versions for flow: %s.", flow_id) response = client.list_flow_versions( flowIdentifier=flow_id, maxResults=10) while finished is False: print(f"Versions for flow:{flow_id}") for version in response['flowVersionSummaries']: print(f"Version: {version['version']}") print(f"Status: {version['status']}\n") if 'nextToken' in response: next_token = response['nextToken'] response = client.list_flow_versions(maxResults=10, nextToken=next_token) else: finished = True logging.info("Successfully listed flow versions for flow %s.", flow_id) return response except ClientError as e: logging.exception("Client error listing flow versions: %s", str(e)) raise except Exception as e: logging.exception("Unexpected error listing flow versions: %s", str(e)) raise ``` + For API details, see [ListFlowVersions](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/ListFlowVersions) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `ListFlows` with an AWS SDK The following code example shows how to use `ListFlows`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). List Amazon Bedrock flows. ``` def list_flows(client): """ Lists versions of an Amazon Bedrock flow. Args: client: Amazon Bedrock agent boto3 client. flow_id (str): The identifier of the flow. Returns: Nothing. """ try: finished = False logger.info("Listing flows:") response = client.list_flows(maxResults=10) while finished is False: for flow in response['flowSummaries']: print(f"ID: {flow['id']}") print(f"Name: {flow['name']}") print( f"Description: {flow.get('description', 'No description')}") print(f"Latest version: {flow['version']}") print(f"Status: {flow['status']}\n") if 'nextToken' in response: next_token = response['nextToken'] response = client.list_flows(maxResults=10, nextToken=next_token) else: finished = True logging.info("Successfully listed flows.") except ClientError as e: logging.exception("Client error listing flow versions: %s", str(e)) raise except Exception as e: logging.exception("Unexpected error listing flow versions: %s", str(e)) raise ``` + For API details, see [ListFlows](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/ListFlows) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `ListKnowledgeBases` with an AWS SDK The following code example shows how to use `ListKnowledgeBases`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). List Amazon Bedrock knowledge Bases. ``` def list_knowledge_bases(bedrock_agent_client, max_results=None): """ Lists the knowledge bases in your AWS account. Args: bedrock_agent_client: The Boto3 Bedrock Agent client. max_results (int, optional): The maximum number of knowledge bases to return. Returns: list: A list of knowledge base details. """ try: kwargs = {} if max_results is not None: kwargs["maxResults"] = max_results # Initialize an empty list to store all knowledge bases all_knowledge_bases = [] # Use paginator to handle pagination automatically paginator = bedrock_agent_client.get_paginator('list_knowledge_bases') page_iterator = paginator.paginate(**kwargs) # Iterate through each page of results for page in page_iterator: all_knowledge_bases.extend(page.get('knowledgeBaseSummaries', [])) logger.info("Found %s knowledge bases.", len(all_knowledge_bases)) return all_knowledge_bases except ClientError as err: logger.error( "Couldn't list knowledge bases. Here's why: %s: %s", err.response["Error"]["Code"], err.response["Error"]["Message"], ) raise ``` + For API details, see [ListKnowledgeBases](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/ListKnowledgeBases) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `ListPrompts` with an AWS SDK The following code example shows how to use `ListPrompts`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). List Amazon Bedrock managed prompts. ``` def list_prompts(client, max_results=10): """ Lists Amazon Bedrock managed prompts. Args: client: Amazon Bedrock Agent boto3 client. max_results (int): Maximum number of results to return per page. Returns: list: A list of prompt summaries. """ try: logger.info("Listing prompts:") # Create a paginator for the list_prompts operation paginator = client.get_paginator('list_prompts') # Create the pagination parameters pagination_config = { 'maxResults': max_results } # Initialize an empty list to store all prompts all_prompts = [] # Iterate through all pages for page in paginator.paginate(**pagination_config): all_prompts.extend(page.get('promptSummaries', [])) logger.info("Successfully listed %s prompts.", len(all_prompts)) return all_prompts except ClientError as e: logger.exception("Client error listing prompts: %s", str(e)) raise except Exception as e: logger.exception("Unexpected error listing prompts: %s", str(e)) raise ``` + For API details, see [ListPrompts](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/ListPrompts) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `PrepareAgent` with an AWS SDK The following code example shows how to use `PrepareAgent`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke an agent](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockAgents_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Prepare an agent for internal testing. ``` def prepare_agent(self, agent_id): """ Creates a DRAFT version of the agent that can be used for internal testing. :param agent_id: The unique identifier of the agent to prepare. :return: The response from Amazon Bedrock Agents if successful, otherwise raises an exception. """ try: prepared_agent_details = self.client.prepare_agent(agentId=agent_id) except ClientError as e: logger.error(f"Couldn't prepare agent. {e}") raise else: return prepared_agent_details ``` + For API details, see [PrepareAgent](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/PrepareAgent) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `PrepareFlow` with an AWS SDK The following code example shows how to use `PrepareFlow`. Action examples are code excerpts from larger programs and must be run in context. You can see this action in context in the following code example: + [Create and invoke a flow](bedrock-agent_example_bedrock-agent_GettingStartedWithBedrockFlows_section.md) ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Prepare an Amazon Bedrock flow. ``` def prepare_flow(client, flow_id): """ Prepares an Amazon Bedrock Flow. Args: client: Amazon Bedrock agent boto3 client. flow_id (str): The identifier of the flow that you want to prepare. Returns: str: The status of the flow preparation """ try: # Prepare the flow. logger.info("Preparing flow ID: %s", flow_id) response = client.prepare_flow( flowIdentifier=flow_id ) status = response.get('status') while status == "Preparing": logger.info("Preparing flow ID: %s. Status %s", flow_id, status) sleep(5) response = client.get_flow( flowIdentifier=flow_id ) status = response.get('status') print(f"Flow Status: {status}") if status == "Prepared": logger.info("Finished preparing flow ID: %s. Status %s", flow_id, status) else: logger.warning("flow ID: %s not prepared. Status %s", flow_id, status) return status except ClientError as e: logger.exception("Client error preparing flow: %s", {str(e)}) raise except Exception as e: logger.exception("Unexepcted error preparing flow: %s", {str(e)}) raise ``` + For API details, see [PrepareFlow](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/PrepareFlow) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `UpdateFlow` with an AWS SDK The following code example shows how to use `UpdateFlow`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Update an Amazon Bedrock Flow. ``` def update_flow(client, flow_id, flow_name, flow_description, role_arn, flow_def): """ Updates an Amazon Bedrock flow. Args: client: bedrock agent boto3 client. flow_id (str): The ID for the flow that you want to update. flow_name (str): The name for the flow. role_arn (str): The ARN for the IAM role that use flow uses. flow_def (json): The JSON definition of the flow that you want to create. Returns: dict: Flow information if successful. """ try: logger.info("Updating flow: %s.", flow_id) response = client.update_flow( flowIdentifier=flow_id, name=flow_name, description=flow_description, executionRoleArn=role_arn, definition=flow_def ) logger.info("Successfully updated flow: %s. ID: %s", flow_name, {response['id']}) return response except ClientError as e: logger.exception("Client error updating flow: %s", {str(e)}) raise except Exception as e: logger.exception("Unexepcted error updating flow: %s", {str(e)}) raise ``` + For API details, see [UpdateFlow](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/UpdateFlow) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `UpdateFlowAlias` with an AWS SDK The following code example shows how to use `UpdateFlowAlias`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Update an alias for an Amazon Bedrock flow. ``` def update_flow_alias(client, flow_id, alias_id, flow_version, name, description): """ Updates an alias for an Amazon Bedrock flow. Args: client: bedrock agent boto3 client. flow_id (str): The identifier of the flow. Returns: str: The response from UpdateFlowAlias. """ try: logger.info("Updating flow alias %s for flow: %s.", alias_id, flow_id) response = client.update_flow_alias( aliasIdentifier=alias_id, flowIdentifier=flow_id, name=name, description=description, routingConfiguration=[ { "flowVersion": flow_version } ] ) logger.info("Successfully updated flow alias %s for %s.", alias_id, flow_id) return response except ClientError as e: logging.exception("Client error updating alias %s for flow: %s - %s", alias_id, flow_id, str(e)) raise except Exception as e: logging.exception("Unexpected error updating alias %s for flow : %s - %s", alias_id, flow_id, str(e)) raise ``` + For API details, see [UpdateFlowAlias](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/UpdateFlowAlias) in *AWS SDK for Python (Boto3) API Reference*. ------ # Use `UpdateKnowledgeBase` with an AWS SDK The following code example shows how to use `UpdateKnowledgeBase`. ------ #### [ Python ] **SDK for Python (Boto3)** There's more on GitHub. Find the complete example and learn how to set up and run in the [AWS Code Examples Repository](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/bedrock-agent#code-examples). Update an Amazon Bedrock knowledge base. ``` def update_knowledge_base(bedrock_agent_client, knowledge_base_id, name=None, description=None, role_arn=None): """ Updates an existing knowledge base. Args: bedrock_agent_client: The Boto3 Bedrock Agent client. knowledge_base_id (str): The ID of the knowledge base to update. name (str, optional): The new name for the knowledge base. description (str, optional): The new description for the knowledge base. role_arn (str, optional): The new IAM role ARN for the knowledge base. Returns: dict: The details of the updated knowledge base. """ try: kwargs = { "knowledgeBaseId": knowledge_base_id, "knowledgeBaseConfiguration": { "type": "VECTOR", "vectorKnowledgeBaseConfiguration": { "embeddingModelArn": "arn:aws:bedrock:us-east-1::foundation-model/amazon.titan-embed-text-v1" } } } if name: kwargs["name"] = name if description: kwargs["description"] = description if role_arn: kwargs["roleArn"] = role_arn response = bedrock_agent_client.update_knowledge_base(**kwargs) logger.info("Updated knowledge base: %s", knowledge_base_id) return response["knowledgeBase"] except ClientError as err: logger.error( "Couldn't update knowledge base %s. Here's why: %s: %s", knowledge_base_id, err.response["Error"]["Code"], err.response["Error"]["Message"], ) raise ``` + For API details, see [UpdateKnowledgeBase](https://docs.aws.amazon.com/goto/boto3/bedrock-agent-2023-12-12/UpdateKnowledgeBase) in *AWS SDK for Python (Boto3) API Reference*. ------