TextTensor is a specialized subclass of torch.Tensor designed for handling and manipulating textual data within the LangTorch framework. Each ent

The Text class represents structured textual data within LangTorch, allowing for complex manipulations and operations on text similar to work

A context manager for saving and loading session data: tensors, api calls, configuration and caching

A `TextModule` is an abstraction designed to facilitate operations on `TextTensor` objects using a chain of texts transformations and l

Abstract API request class.

Based on: Large Language Models as Optimizers (Yang et al., 2023)

Based on: zero-shot CoT (Kojima et al., 2022)

Stores metadata about the script's progress. Only one instance is created.

Stores metadata about the script's progress. Only one instance is created.

Represents an OpenAI API request.

TextTensor + TextTensor

r"""Returns cosine similarity between :math:`x_1` and :math:`x_2`, computed along `dim`. .. math :: \text{similarity} = \dfrac{x_1 \cdot

TextModule.format

r"""Applies a matmul to the incoming TextTensor: :math:`y = A @ x.T + b` Args: in_features: size of each input sample out_featur

TextModule.format

r""" Args: embed_dim: Total dimension of the model. num_heads: Number of parallel attention heads. Note that ``embed_dim`` will b

Wrapper that converts a TextTensor input to a torch.Tensor output using a specified model or function. Parameters: - model (callable): T

Wrapper that converts a TextTensor input to a TextTensor output using a specified model or function. Parameters: - model (callable): The