Prompt components in LLM Controls

A prompt is a structured input to a language model that instructs the model how to handle user inputs and variables. Prompt components create prompt templates with custom fields and dynamic variables for providing your model structured, repeatable prompts.

​

Use a prompt component in a flow

An example of modifying a prompt can be found in Vector RAG starter flow, where a basic chatbot flow is extended to include a full vector RAG pipeline. The default prompt in the Prompt component is Answer the user as if you were a GenAI expert, enthusiastic about helping them get started building something fresh. This prompt creates a “personality” for your LLM’s chat interactions, but it doesn’t include variables that you may find useful when templating prompts. To modify the prompt template, in the Prompt component, click the Template field. For example, the {context} variable gives the LLM model access to embedded vector data to return better answers. When variables are added to a prompt template, new fields are automatically created in the component. These fields can be connected to receive text input from other components to automate prompting, or to output instructions to other components. An example of prompts controlling agents behavior is available in the sequential tasks agent starter flow.

Parameters

Inputs

Name	Display Name	Info
template	Template	Create a prompt template with dynamic variables.

Outputs

Name	Display Name	Info
prompt	Prompt Message	The built prompt message returned by the build_prompt method.

​

Results

This component displays and compares model performance based on evaluation metrics from the Prompt Optimizer. It stores ranked results in a leaderboard with accuracy, speed, cost, and detailed feedback.

Parameters

Inputs

Name	Display Name	Info
evaluator_input	Evaluator Input	The evaluation results from the Evaluator component.
prompt_selection	Select Prompt/Model	Choose a prompt/model config from the leaderboard.
top_k	Top K Results	Number of top results to include in the output.
include_details	Include Details	Whether to include detailed metrics in the output.

Outputs

Name	Display Name	Info
leaderboard	Leaderboard	The ranked results as a DataFrame containing Rank, Model, Token Size, Accuracy, Speed, Cost, Prompt, and optionally Strengths, Weaknesses, and Suggestions.