trulens.core.utils.signature¶

trulens.core.utils.signature ¶

Utilities related to guessing inputs and outputs of functions.

Functions¶

_extract_content ¶

_extract_content(value, content_keys=['content'])

Extracts the 'content' from various data types commonly used by libraries like OpenAI, Canopy, LiteLLM, etc. This method navigates nested data structures (pydantic models, dictionaries, lists) to retrieve the 'content' field. If 'content' is not directly available, it attempts to extract from known structures like 'choices' in a ChatResponse. This standardizes extracting relevant text or data from complex API responses or internal data representations.

PARAMETER	DESCRIPTION
`value`	The input data to extract content from. Can be a pydantic model, dictionary, list, or basic data type.

RETURNS	DESCRIPTION
	The extracted content, which may be a single value, a list of values,
	or a nested structure with content extracted from all levels.

main_input ¶

main_input(
    func: Callable, sig: Signature, bindings: BoundArguments
) -> str

Determine (guess) the main input string for a main app call.

PARAMETER	DESCRIPTION
`func`	The main function we are targeting in this determination. TYPE: `Callable`
`sig`	The signature of the above. TYPE: `Signature`
`bindings`	The arguments to be passed to the function. TYPE: `BoundArguments`

RETURNS	DESCRIPTION
`str`	The main input string.

main_output ¶

main_output(func: Callable, ret: Any) -> str

Determine (guess) the "main output" string for a given main app call.

This is for functions whose output is not a string.

PARAMETER	DESCRIPTION
`func`	The main function whose main output we are guessing. TYPE: `Callable`
`ret`	The return value of the function. TYPE: `Any`