ALTK

Bundles contain custom components that support specific third-party integrations with Langflow.

tip

The ALTK contains features called components. These are different from Langflow components. All components within ALTK are available through Langflow's ALTK Agent component.

The ALTK Agent implements components from the Agent Lifecycle Toolkit. ALTK features can be enabled or disabled independently.

• Pre-tool validation: Validates tool calls before execution to check for appropriateness and correctness using the SPARC reflection component. This validation prevents agents from executing invalid tool calls.

• Post-tool JSON processing: Processes large JSON tool responses by generating Python code on the fly to extract relevant data. This helps reduce context size and improves the agent's ability to work with large tool responses, especially when dealing with APIs that return extensive JSON data. The component outputs a Message containing the agent's response, which is passed to the next component in the flow instead of the full JSON data that isn't needed.

For more information, see the Agent Lifecycle Toolkit documentation.

For an example of the ALTK component in Langflow, see the video tutorial ALTK in Langflow: Reliably handle JSON responses in your AI agent.

ALTK Agent parameters

Some parameters are hidden by default in the visual editor. You can modify all parameters through the Controls in the component's header menu.

Name	Type	Description
agent_llm	Dropdown	Input parameter. The model provider the agent uses to generate responses.
enable_tool_validation	Boolean	Input parameter. If enabled, tool calls are validated using SPARC before execution to check for appropriateness and correctness. Default: true.
enable_post_tool_reflection	Boolean	Input parameter. If enabled, tool outputs are automatically processed through JSON processing when the output is JSON and exceeds the size threshold. Default: true.
response_processing_size_threshold	Integer	Input parameter. Tool output is post-processed only if the response length exceeds this character threshold. Default: 100. Advanced parameter.
tools	List[Tool]	Input parameter. The list of tools available to the agent.
system_prompt	String	Input parameter. The system prompt to provide context to the agent.
input_value	String	Input parameter. The user's input to the agent.
memory	Memory	Input parameter. The memory for the agent to use for context persistence.
max_iterations	Integer	Input parameter. The maximum number of iterations to allow the agent to execute.
verbose	Boolean	Input parameter. This determines whether to print out the agent's intermediate steps.
handle_parsing_errors	Boolean	Input parameter. This determines whether to handle parsing errors in the agent.