Skip to content

opto.optimizers.optoprime

FunctionFeedback dataclass 

FunctionFeedback(
    graph: List[Tuple[int, str]],
    documentation: Dict[str, str],
    others: Dict[str, Any],
    roots: Dict[str, Any],
    output: Dict[str, Any],
    user_feedback: str,
)

Feedback container used by FunctionPropagator.

graph instance-attribute 

graph: List[Tuple[int, str]]

documentation instance-attribute 

documentation: Dict[str, str]

others instance-attribute 

others: Dict[str, Any]

roots instance-attribute 

roots: Dict[str, Any]

output instance-attribute 

output: Dict[str, Any]

user_feedback instance-attribute 

user_feedback: str

ProblemInstance dataclass 

ProblemInstance(
    instruction: str,
    code: str,
    documentation: str,
    variables: str,
    inputs: str,
    others: str,
    outputs: str,
    feedback: str,
    constraints: str,
)

instruction instance-attribute 

instruction: str

code instance-attribute 

code: str

documentation instance-attribute 

documentation: str

variables instance-attribute 

variables: str

inputs instance-attribute 

inputs: str

others instance-attribute 

others: str

outputs instance-attribute 

outputs: str

feedback instance-attribute 

feedback: str

constraints instance-attribute 

constraints: str

problem_template class-attribute instance-attribute 

problem_template = dedent(
    "\n        #Instruction\n        {instruction}\n\n        #Code\n        {code}\n\n        #Documentation\n        {documentation}\n\n        #Variables\n        {variables}\n\n        #Constraints\n        {constraints}\n\n        #Inputs\n        {inputs}\n\n        #Others\n        {others}\n\n        #Outputs\n        {outputs}\n\n        #Feedback\n        {feedback}\n        "
)

OptoPrime 

OptoPrime(
    parameters: List[ParameterNode],
    llm: AbstractModel = None,
    *args,
    propagator: Propagator = None,
    objective: Union[None, str] = None,
    ignore_extraction_error: bool = True,
    include_example=False,
    memory_size=0,
    max_tokens=4096,
    log=True,
    prompt_symbols=None,
    json_keys=None,
    use_json_object_format=True,
    highlight_variables=False,
    **kwargs
)

Bases: Optimizer

representation_prompt class-attribute instance-attribute 

representation_prompt = dedent(
    "\n        You're tasked to solve a coding/algorithm problem. You will see the instruction, the code, the documentation of each function used in the code, and the feedback about the execution result.\n\n        Specifically, a problem will be composed of the following parts:\n        - #Instruction: the instruction which describes the things you need to do or the question you should answer.\n        - #Code: the code defined in the problem.\n        - #Documentation: the documentation of each function used in #Code. The explanation might be incomplete and just contain high-level description. You can use the values in #Others to help infer how those functions work.\n        - #Variables: the input variables that you can change.\n        - #Constraints: the constraints or descriptions of the variables in #Variables.\n        - #Inputs: the values of other inputs to the code, which are not changeable.\n        - #Others: the intermediate values created through the code execution.\n        - #Outputs: the result of the code output.\n        - #Feedback: the feedback about the code's execution result.\n\n        In #Variables, #Inputs, #Outputs, and #Others, the format is:\n\n        <data_type> <variable_name> = <value>\n\n        If <type> is (code), it means <value> is the source code of a python code, which may include docstring and definitions.\n        "
)

default_objective class-attribute instance-attribute 

default_objective = "You need to change the <value> of the variables in #Variables to improve the output in accordance to #Feedback."

output_format_prompt_original class-attribute instance-attribute 

output_format_prompt_original = dedent(
    '\n        Output_format: Your output should be in the following json format, satisfying the json syntax:\n\n        {{\n        "{reasoning}": <Your reasoning>,\n        "{answer}": <Your answer>,\n        "{suggestion}": {{\n            <variable_1>: <suggested_value_1>,\n            <variable_2>: <suggested_value_2>,\n        }}\n        }}\n\n        In "{reasoning}", explain the problem: 1. what the #Instruction means 2. what the #Feedback on #Output means to #Variables considering how #Variables are used in #Code and other values in #Documentation, #Inputs, #Others. 3. Reasoning about the suggested changes in #Variables (if needed) and the expected result.\n\n        If #Instruction asks for an answer, write it down in "{answer}".\n\n        If you need to suggest a change in the values of #Variables, write down the suggested values in "{suggestion}". Remember you can change only the values in #Variables, not others. When <type> of a variable is (code), you should write the new definition in the format of python code without syntax errors, and you should not change the function name or the function signature.\n\n        If no changes or answer are needed, just output TERMINATE.\n        '
)

output_format_prompt_no_answer class-attribute instance-attribute 

output_format_prompt_no_answer = dedent(
    '\n        Output_format: Your output should be in the following json format, satisfying the json syntax:\n\n        {{\n        "{reasoning}": <Your reasoning>,\n        "{suggestion}": {{\n            <variable_1>: <suggested_value_1>,\n            <variable_2>: <suggested_value_2>,\n        }}\n        }}\n\n        In "{reasoning}", explain the problem: 1. what the #Instruction means 2. what the #Feedback on #Output means to #Variables considering how #Variables are used in #Code and other values in #Documentation, #Inputs, #Others. 3. Reasoning about the suggested changes in #Variables (if needed) and the expected result.\n\n        If you need to suggest a change in the values of #Variables, write down the suggested values in "{suggestion}". Remember you can change only the values in #Variables, not others. When <type> of a variable is (code), you should write the new definition in the format of python code without syntax errors, and you should not change the function name or the function signature.\n\n        If no changes are needed, just output TERMINATE.\n        '
)

example_problem_template class-attribute instance-attribute 

example_problem_template = dedent(
    "\n        Here is an example of problem instance and response:\n\n        ================================\n        {example_problem}\n        ================================\n\n        Your response:\n        {example_response}\n        "
)

user_prompt_template class-attribute instance-attribute 

user_prompt_template = dedent(
    "\n        Now you see problem instance:\n\n        ================================\n        {problem_instance}\n        ================================\n\n        "
)

example_prompt class-attribute instance-attribute 

example_prompt = dedent(
    "\n\n        Here are some feasible but not optimal solutions for the current problem instance. Consider this as a hint to help you understand the problem better.\n\n        ================================\n\n        {examples}\n\n        ================================\n        "
)

final_prompt class-attribute instance-attribute 

final_prompt = dedent('\n        Your response:\n        ')

final_prompt_with_variables class-attribute instance-attribute 

final_prompt_with_variables = dedent(
    "\n        What are your suggestions on variables {names}?\n\n        Your response:\n        "
)

default_prompt_symbols class-attribute instance-attribute 

default_prompt_symbols = {
    "variables": "#Variables",
    "constraints": "#Constraints",
    "inputs": "#Inputs",
    "outputs": "#Outputs",
    "others": "#Others",
    "feedback": "#Feedback",
    "instruction": "#Instruction",
    "code": "#Code",
    "documentation": "#Documentation",
}

default_json_keys class-attribute instance-attribute 

default_json_keys = {
    "reasoning": "reasoning",
    "answer": "answer",
    "suggestion": "suggestion",
}

ignore_extraction_error instance-attribute 

ignore_extraction_error = ignore_extraction_error

llm instance-attribute 

llm = llm or LLM()

objective instance-attribute 

objective = objective or default_objective

example_problem instance-attribute 

example_problem = format(
    instruction=default_objective,
    code="y = add(x=a,y=b)\nz = subtract(x=y, y=c)",
    documentation="add: add x and y \nsubtract: subtract y from x",
    variables="(int) a = 5",
    constraints="a: a > 0",
    outputs="(int) z = 1",
    others="(int) y = 6",
    inputs="(int) b = 1\n(int) c = 5",
    feedback="The result of the code is not as expected. The result should be 10, but the code returns 1",
    stepsize=1,
)

example_response instance-attribute 

example_response = dedent(
    '\n            {"reasoning": \'In this case, the desired response would be to change the value of input a to 14, as that would make the code return 10.\',\n             "answer", {},\n             "suggestion": {"a": 10}\n            }\n            '
)

include_example instance-attribute 

include_example = include_example

max_tokens instance-attribute 

max_tokens = max_tokens

log instance-attribute 

log = [] if log else None

summary_log instance-attribute 

summary_log = [] if log else None

memory instance-attribute 

memory = FIFOBuffer(memory_size)

prompt_symbols instance-attribute 

prompt_symbols = deepcopy(default_prompt_symbols)

output_format_prompt instance-attribute 

output_format_prompt = format(**(default_json_keys))

use_json_object_format instance-attribute 

use_json_object_format = use_json_object_format

highlight_variables instance-attribute 

highlight_variables = highlight_variables

default_propagator 

default_propagator()

Return the default Propagator object of the optimizer.

summarize 

summarize()

repr_node_value staticmethod 

repr_node_value(node_dict)

repr_node_constraint staticmethod 

repr_node_constraint(node_dict)

problem_instance 

problem_instance(summary, mask=None)

construct_prompt 

construct_prompt(summary, mask=None, *args, **kwargs)

Construct the system and user prompt.

replace_symbols 

replace_symbols(text: str, symbols: Dict[str, str]) -> str

construct_update_dict 

construct_update_dict(
    suggestion: Dict[str, Any],
) -> Dict[ParameterNode, Any]

Convert the suggestion in text into the right data type.

extract_llm_suggestion 

extract_llm_suggestion(response: str)

Extract the suggestion from the response.

call_llm 

call_llm(
    system_prompt: str,
    user_prompt: str,
    verbose: Union[bool, str] = False,
    max_tokens: int = 4096,
)

Call the LLM with a prompt and return the response.

save 

save(path: str)

Save the optimizer state to a file.

load 

load(path: str)

Load the optimizer state from a file.

get_fun_name 

get_fun_name(node: MessageNode)

repr_function_call 

repr_function_call(child: MessageNode)

node_to_function_feedback 

node_to_function_feedback(node_feedback: TraceGraph)

Convert a TraceGraph to a FunctionFeedback. roots, others, outputs are dict of variable name and its data and constraints.