CodeCodeToInstructionGenerator is an operator that uses an LLM to generate a human-readable instruction based on a given code snippet. This is often used as the first step in a 'self-instruct' style data synthesis pipeline for code.

__init__

def __init__(self, llm_serving: LLMServingABC, prompt_template=None)

Parameter	Type	Default	Description
llm_serving	LLMServingABC	Required	Large language model serving instance for executing inference.
prompt_template	PromptABC / str	CodeCodeToInstructionGeneratorPrompt()	The prompt template object used to construct the input. Supports custom templates via string or DiyCodePrompt.

Prompt Template Descriptions

Prompt Template Name	Primary Use	Applicable Scenarios	Feature Description

run

def run(self, storage: DataFlowStorage, input_key: str = "code", output_key: str = "generated_instruction")

Parameter	Type	Default	Description
storage	DataFlowStorage	Required	DataFlow storage instance for reading and writing data.
input_key	str	"code"	Input column name, corresponding to the code snippet field.
output_key	str	"generated_instruction"	Output column name, corresponding to the generated instruction field.

🧠 Example Usage

🧾 Default Output Format

Field	Type	Description
code	str	The input code snippet.
generated_instruction	str	The human-readable instruction generated by the model.

Example Input:

{
    "code": "def calculate_factorial(n):\n    if n == 0:\n        return 1\n    else:\n        return n * calculate_factorial(n-1)"
}

Example Output:

{
    "code": "def calculate_factorial(n):\n    if n == 0:\n        return 1\n    else:\n        return n * calculate_factorial(n-1)",
    "generated_instruction": "Write a Python function to calculate the factorial of a non-negative integer using recursion."
}