View Source AWS.BedrockAgentRuntime (aws-elixir v1.0.6)

Contains APIs related to model invocation and querying of knowledge bases.

Link to this section Summary

Functions

Creates a new invocation within a session.

Creates a session to temporarily store conversations for generative AI (GenAI) applications built with open-source frameworks such as LangGraph and LlamaIndex.

Deletes memory from the specified memory identifier.

Generates an SQL query from a natural language query.

Retrieves the details of a specific invocation step within an invocation in a session.

Retrieves details about a specific session.

Sends a prompt for the agent to process and respond to.

Invokes an alias of a flow to run the inputs that you specify and return the output of each node as a stream.

Invokes an inline Amazon Bedrock agent using the configurations you provide with the request.

Lists all invocation steps associated with a session and optionally, an invocation within the session.

Lists all invocations associated with a specific session.

Lists all sessions in your Amazon Web Services account.

List all the tags for the resource you specify.

Optimizes a prompt for the task that you specify.

Add an invocation step to an invocation in a session.

Reranks the relevance of sources based on queries.

Queries a knowledge base and retrieves information from it.

Queries a knowledge base and generates responses based on the retrieved results and using the specified foundation model or inference profile.

Queries a knowledge base and generates responses based on the retrieved results, with output in streaming format.

Updates the metadata or encryption settings of a session.

Link to this section Functions

Link to this function

create_invocation(client, session_identifier, input, options \\ [])

View Source

Creates a new invocation within a session.

An invocation groups the related invocation steps that store the content from a conversation. For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Related APIs

*

ListInvocations

*

ListSessions

*

GetSession

Link to this function

create_session(client, input, options \\ [])

View Source

Creates a session to temporarily store conversations for generative AI (GenAI) applications built with open-source frameworks such as LangGraph and LlamaIndex.

Sessions enable you to save the state of conversations at checkpoints, with the added security and infrastructure of Amazon Web Services. For more information, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

By default, Amazon Bedrock uses Amazon Web Services-managed keys for session encryption, including session metadata, or you can use your own KMS key. For more information, see Amazon Bedrock session encryption.

You use a session to store state and conversation history for generative AI applications built with open-source frameworks. For Amazon Bedrock Agents, the service automatically manages conversation context and associates them with the agent-specific sessionId you specify in the InvokeAgent API operation.

Related APIs:

*

ListSessions

*

GetSession

*

EndSession

*

DeleteSession

Link to this function

delete_agent_memory(client, agent_alias_id, agent_id, input, options \\ [])

View Source

Deletes memory from the specified memory identifier.

Link to this function

delete_session(client, session_identifier, input, options \\ [])

View Source

Deletes a session that you ended.

You can't delete a session with an ACTIVE status. To delete an active session, you must first end it with the EndSession API operation. For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Link to this function

end_session(client, session_identifier, input, options \\ [])

View Source

Ends the session.

After you end a session, you can still access its content but you can’t add to it. To delete the session and it's content, you use the DeleteSession API operation. For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Link to this function

generate_query(client, input, options \\ [])

View Source

Generates an SQL query from a natural language query.

For more information, see Generate a query for structured data in the Amazon Bedrock User Guide.

Link to this function

get_agent_memory(client, agent_alias_id, agent_id, max_items \\ nil, memory_id, memory_type, next_token \\ nil, options \\ [])

View Source

Gets the sessions stored in the memory of the agent.

Link to this function

get_invocation_step(client, invocation_step_id, session_identifier, input, options \\ [])

View Source

Retrieves the details of a specific invocation step within an invocation in a session.

For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Link to this function

get_session(client, session_identifier, options \\ [])

View Source

Retrieves details about a specific session.

For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Link to this function

invoke_agent(client, agent_alias_id, agent_id, session_id, input, options \\ [])

View Source

Sends a prompt for the agent to process and respond to.

Note the following fields for the request:

* To continue the same conversation with an agent, use the same sessionId value in the request.

* To activate trace enablement, turn enableTrace to true. Trace enablement helps you follow the agent's reasoning process that led it to the information it processed, the actions it took, and the final result it yielded. For more information, see Trace enablement.

* End a conversation by setting endSession to true.

* In the sessionState object, you can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group.

The response contains both chunk and trace attributes.

The final response is returned in the bytes field of the chunk object. The InvokeAgent returns one chunk for the entire interaction.

* The attribution object contains citations for parts of the response.

* If you set enableTrace to true in the request, you can trace the agent's steps and reasoning process that led it to the response.

* If the action predicted was configured to return control, the response returns parameters for the action, elicited from the user, in the returnControl field.

* Errors are also surfaced in the response.

Link to this function

invoke_flow(client, flow_alias_identifier, flow_identifier, input, options \\ [])

View Source

Invokes an alias of a flow to run the inputs that you specify and return the output of each node as a stream.

If there's an error, the error is returned. For more information, see Test a flow in Amazon Bedrock in the Amazon Bedrock User Guide.

The CLI doesn't support streaming operations in Amazon Bedrock, including InvokeFlow.

Link to this function

invoke_inline_agent(client, session_id, input, options \\ [])

View Source

Invokes an inline Amazon Bedrock agent using the configurations you provide with the request.

* Specify the following fields for security purposes.

*

(Optional) customerEncryptionKeyArn – The Amazon Resource Name (ARN) of a KMS key to encrypt the creation of the agent.

*

(Optional) idleSessionTTLinSeconds – Specify the number of seconds for which the agent should maintain session information. After this time expires, the subsequent InvokeInlineAgent request begins a new session.

* To override the default prompt behavior for agent orchestration and to use advanced prompts, include a promptOverrideConfiguration object. For more information, see Advanced prompts.

* The agent instructions will not be honored if your agent has only one knowledge base, uses default prompts, has no action group, and user input is disabled.

Link to this function

list_invocation_steps(client, session_identifier, input, options \\ [])

View Source

Lists all invocation steps associated with a session and optionally, an invocation within the session.

For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Link to this function

list_invocations(client, session_identifier, input, options \\ [])

View Source

Lists all invocations associated with a specific session.

For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Link to this function

list_sessions(client, input, options \\ [])

View Source

Lists all sessions in your Amazon Web Services account.

For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Link to this function

list_tags_for_resource(client, resource_arn, options \\ [])

View Source

List all the tags for the resource you specify.

Link to this function

optimize_prompt(client, input, options \\ [])

View Source

Optimizes a prompt for the task that you specify.

For more information, see Optimize a prompt in the Amazon Bedrock User Guide.

Link to this function

put_invocation_step(client, session_identifier, input, options \\ [])

View Source

Add an invocation step to an invocation in a session.

An invocation step stores fine-grained state checkpoints, including text and images, for each interaction. For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.

Related APIs:

*

GetInvocationStep

*

ListInvocationSteps

*

ListInvocations

*

ListSessions

Link to this function

rerank(client, input, options \\ [])

View Source

Reranks the relevance of sources based on queries.

For more information, see Improve the relevance of query responses with a reranker model.

Link to this function

retrieve(client, knowledge_base_id, input, options \\ [])

View Source

Queries a knowledge base and retrieves information from it.

Link to this function

retrieve_and_generate(client, input, options \\ [])

View Source

Queries a knowledge base and generates responses based on the retrieved results and using the specified foundation model or inference profile.

The response only cites sources that are relevant to the query.

Link to this function

retrieve_and_generate_stream(client, input, options \\ [])

View Source

Queries a knowledge base and generates responses based on the retrieved results, with output in streaming format.

The CLI doesn't support streaming operations in Amazon Bedrock, including InvokeModelWithResponseStream.

This operation requires permission for the bedrock:RetrieveAndGenerate action.

Link to this function

tag_resource(client, resource_arn, input, options \\ [])

View Source

Associate tags with a resource.

For more information, see Tagging resources in the Amazon Bedrock User Guide.

Link to this function

untag_resource(client, resource_arn, input, options \\ [])

View Source

Remove tags from a resource.

Link to this function

update_session(client, session_identifier, input, options \\ [])

View Source

Updates the metadata or encryption settings of a session.

For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.