IVYXSTUDIO · IVY NODE

Prompt Generator

ivy.node.prompt-generator · v0.0.0

ivyx✓

Generates formatted prompts using a prompt creator function and validates token limits. This node takes a creator function (from default-prompt-creator, json-prompt-creator, or xml-prompt-creator), context, and question to produce a formatted prompt string. It enforces maximum token limits to prevent exceeding LLM input constraints. The output prompt is typically used with open-ai-client or hugging-face-llm-client nodes for AI interactions.

#Prompt#Generator

Inputs

Field	Type	Description
creatorrequired	object	A function that generates prompts based on context and question (Node reference)
max_tokensrequired	number	The maximum number of tokens allowed in the prompt
contextrequired	string	The context or background information
questionrequired	string	The question to be answered
features	object	Features
labels	object	Labels

Outputs

Field	Type	Description
promptrequired	string	Not declared
features	object	Features
labels	object	Labels

Source

python

# Input preparation
inp = __ivy_ctx__["nodes"][__ivy_node_id__]["input"]
creator = inp["creator"]
max_tokens = inp["max_tokens"]
context = inp["context"]
question = inp["question"]

# Compute
from typing import Callable, Dict, Any

class PromptGenerator:
    """
    A class to generate prompts using different prompt creation strategies.
    """

    def __init__(self, creator: Callable[[str, str, Dict[str, Any]], str], max_tokens: int):
        """
        Initialize the PromptGenerator with a prompt creation function.

        :param creator: A function that generates prompts based on context and question.
        :param max_tokens: The maximum number of tokens allowed in the prompt.
        """
        self.creator: Callable[[str, str, Dict[str, Any]], str] = creator
        self.max_tokens: int = max_tokens

    def generate_prompt(self, context: str, question: str, **kwargs: Dict[str, Any]) -> str:
        """
        Generate a prompt using the assigned prompt creation function.

        :param context: The context or background information.
        :param question: The question to be answered.
        :param kwargs: Additional parameters for prompt formatting.
        :return: The generated prompt.
        """
        prompt: str = self.creator(context, question, **kwargs)

        # Ensure prompt does not exceed max token limit (if specified)
        if prompt and self.max_tokens is not None and len(prompt.split()) > self.max_tokens:
            raise ValueError(f"Prompt exceeds the maximum token limit of {self.max_tokens} tokens.")

        return prompt

prompt_generator = PromptGenerator(creator=creator, max_tokens=max_tokens)
prompt = prompt_generator.generate_prompt(context, question)

# Output collection (runner reads __ivy_ctx__)
out = __ivy_ctx__["nodes"][__ivy_node_id__]["output"]
out["prompt"] = prompt

Tests

Requires: python:3.11

basic-prompt-generation
Generate prompt with valid inputs (should succeed).
promptgenerationbasic
error-exceeds-token-limit
Prompt exceeding max_tokens should raise an error.
error-handlingvalidation