textgrad.autograd.algebra

Classes

Aggregate()	This function is WIP
Sum()	Represents a sum operation on a list of variables.

class textgrad.autograd.algebra.Aggregate

Bases: Function

This function is WIP

backward(aggregated_variable, backward_engine)

Parameters:

• aggregated_variable (Variable)

• backward_engine (EngineLM)

forward(variables)

Aggregates a list of variables. In TextGrad, forward pass of aggregation is simply concatenation of the values of the variables. The backward pass performs a reduction operation on the gradients of the variables. This reduction is currently an LLM call to summarize the gradients.

Parameters:

variables (List[Variable]) – The list of variables to be aggregated.

Returns:

The aggregated variable.

Return type:

Variable

class textgrad.autograd.algebra.Sum

Bases: Function

Represents a sum operation on a list of variables. In TextGrad, sum is simply concatenation of the values of the variables.

Parameters:

variables (List[Variable]) – The list of variables to be summed (concatenated).

Returns:

A new variable representing the sum of the input variables.

Return type:

Variable

backward(summation, backward_engine)

Performs the backward pass of the sum operation. This is simply an idempotent operation, where we pass the feedback to the predecessors variables.

Parameters:

• summation (Variable) – The variable representing the sum.

• backward_engine (EngineLM) – The backward engine used for backpropagation.

forward(variables)

Performs the forward pass of the sum (concatenation) operation.

Parameters:

variables (List[Variable]) – The list of variables to be summed.

Returns:

A new variable representing the sum of the input variables.

Return type:

Variable