bedrock_agents_sdk.models package

Submodules

bedrock_agents_sdk.models.action_group module

ActionGroup model for Bedrock Agents SDK.

class bedrock_agents_sdk.models.action_group.ActionGroup(*, name: str, description: str, functions: List[Function | Callable] = [])

Bases: BaseModel

Represents an action group in the agent

description: str

functions: List[Function | Callable]

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str

bedrock_agents_sdk.models.agent module

Agent model for Bedrock Agents SDK.

class bedrock_agents_sdk.models.agent.Agent(**data)

Bases: object

Agent configuration for Amazon Bedrock Agents

action_groups: List[ActionGroup]

add_action_group(action_group: ActionGroup)

Add an action group to the agent

Parameters:

action_group – The action group to add

Returns:

For method chaining

Return type:

self

add_dependency(dependency: str, version: str | None = None, action_group: str | None = None)

Add a custom dependency for deployment

This method allows you to specify dependencies that should be included in the requirements.txt file when deploying the agent to AWS Lambda.

Parameters:

• dependency – The name of the dependency (e.g., “pandas”)

• version – Optional version constraint (e.g., “>=1.0.0”)

• action_group – Optional action group to add the dependency to. If not provided, the dependency will be added to all action groups.

Returns:

For method chaining

Return type:

self

add_file(name: str, content: bytes, media_type: str, use_case: str = 'CODE_INTERPRETER') → InputFile

Add a file to be sent to the agent

add_file_from_path(file_path: str, use_case: str = 'CODE_INTERPRETER') → InputFile

Add a file from a local path

add_function(function: Callable, description: str | None = None, action_group: str | None = None)

Add a function to the agent

add_plugin(plugin: AgentPlugin)

Add a plugin to the agent

Parameters:

plugin – The plugin to add

advanced_config: Dict[str, Any] | None = None

deploy(output_dir: str | None = None, foundation_model: str | None = None, parameters: Dict[str, Dict[str, str]] | None = None, description: str | None = None, auto_build: bool = False, auto_deploy: bool = False) → str

Deploy the agent to AWS using SAM

Parameters:

• output_dir – The directory to output the SAM template and code to. If None, defaults to “./[agent_name]_deployment”

• foundation_model – The foundation model to use (defaults to the agent’s model)

• parameters – Additional parameters to add to the template

• description – Description for the SAM template

• auto_build – Whether to automatically run ‘sam build’

• auto_deploy – Whether to automatically run ‘sam deploy –guided’

Returns:

Path to the generated template file

Return type:

str

enable_code_interpreter: bool = False

files: List[InputFile]

functions: List[Callable] | Dict[str, List[Callable]]

instructions: str

model: str

model_config = {'arbitrary_types_allowed': True}

name: str

plugins: List[AgentPlugin]

bedrock_agents_sdk.models.files module

File models for Bedrock Agents SDK.

class bedrock_agents_sdk.models.files.InputFile(*, name: str, content: bytes, media_type: str, use_case: str = 'CODE_INTERPRETER')

Bases: BaseModel

Represents a file to be sent to the agent

content: bytes

media_type: str

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str

to_dict() → Dict[str, Any]

Convert to API parameters format

use_case: str

class bedrock_agents_sdk.models.files.OutputFile(name: str, content: bytes, file_type: str)

Bases: object

Represents a file received from the agent

classmethod from_response(file_data: Dict[str, Any]) → OutputFile

Create an OutputFile from API response data

save(directory: str = '.') → str

Save the file to disk

bedrock_agents_sdk.models.function module

Function model for Bedrock Agents SDK.

class bedrock_agents_sdk.models.function.Function(*, name: str, description: str, function: Callable, action_group: str | None = None)

Bases: BaseModel

Represents a function that can be called by the agent

action_group: str | None

description: str

function: Callable

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str

bedrock_agents_sdk.models.message module

Message model for Bedrock Agents SDK.

class bedrock_agents_sdk.models.message.Message(*, role: str, content: str)

Bases: BaseModel

Represents a message in the conversation

content: str

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

role: str

Module contents