YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Table of Contents
InteractiveCodeGenFlow
InteractiveCodeGenFlow Objects
class InteractiveCodeGenFlow(SequentialFlow)
This flow writes code in an interactive manner. It is a sequential flow composed of:
- MemoryReading: reads in the code library.
- CodeGenerator: generates code based on the goal and functions in the code library.
- CodeFileEditor: writes the generated code to a temp file for the user to see, edit and provide feedback.
- ParseFeedback: opens up the temp file with vscode and parses the feedback from the user.
Input Interface:
goal
Output Interface:
code
feedback
temp_code_file_location
Configuration Parameters:
input_interface
: the input interface of the flow.output_interface
: the output interface of the flow.subflows_config
: the configuration of the subflows.early_exit_key
: the key in the state dict that indicates whether the flow should exit early.topology
: the topology of the subflows.
__init__
def __init__(memory_files: Dict[str, Any], **kwargs)
This function initializes the flow.
Arguments:
memory_files
(Dict[str, Any]
): the memory files that are used in the flow.kwargs
(Any
): the keyword arguments.
instantiate_from_config
@classmethod
def instantiate_from_config(cls, config)
This function instantiates the flow from a configuration.
Arguments:
config
(Dict[str, Any]
): the configuration of the flow.
Returns:
Flow
: the instantiated flow.
run
def run(input_data: Dict[str, Any]) -> Dict[str, Any]
This function runs the flow.
Arguments:
input_data
(Dict[str, Any]
): the input data to the flow.
Returns:
Dict[str, Any]
: the output data from the flow.
run
__init__
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support