r"""Build the Docker container and start it. Args: time_out (int): The number of seconds to wait for the container to

r"""Chunks elements by titles. Args: elements (List[Element]): List of Element objects to be chunked. chunk_type (str

Splits the input text into chunks, each with a maximum number of characters. Args: text (str): The text to be split. max_cha

r"""Removes all records from the key-value storage system.

r"""Initialize :obj:`state` and :obj:`fuzz_state`.

Compute the standard deviation of the probability path N(t * x1 + (1 - t) * x0, sigma), see (Eq.14) [1]. Parameters --------

r"""Construct training examples from raw data. Args: raw_data (List[Dict[str, Any]]): List of raw data dictionaries

Create a stable page_hash of the path_or_stream of a file

r"""Manage and curate a dataset through multiple filtering stages. Args: examples (List[Dict[str, Any]]): List of examples to cur

r"""Deletes an entity (vertex) from the graph. Args: entity_id (str): The identifier of the entity to be deleted.

r"""Download the GAIA dataset.

r"""Download subdirectory of the Github repo of the benchmark. This function downloads all files and subdirectories from a specified subd

Draw clusters on an image

Draws a page image side by side with clusters filtered into two categories: - Left: Clusters excluding FORM, KEY_VALUE_REGION, and PI

r"""Generates embeddings for the given texts. Args: objs (list[T]): The objects for which to generate the embeddings.

Estimate the number of characters that can fit into a bounding box. :param width_in_inches: The width of the bounding box, in inches. :

r"""Recursively evaluate arguments, including nested calls.

r"""Execute the input python codes in a security environment. Args: code (str): Generated python code to be executed.

Extract equations from text content and images. Returns a dictionary of equations with their context and images.

Extract positions/sizes of text and image elements from an HTML file/URL. Returns a dict containing canvas size, meta, items, and relationshi

Extracts and preprocesses text content from a PDF. If raw_result is provided, reuse it to avoid re-conversion.

r"""Check if the given instruction passes all filter functions. Args: prompt (str): The prompt of generating the instruction.

Find generated TTS and face video files, prioritize audio/ and face/ subdirectories, fallback to old paths

Forward pass of ConditionalFlowMatchingTransformer. t: (B,) tensor of diffusion timesteps [0, 1] x: (B, L, 512) : tensor of sequence of motion

r"""Creates a File object from a BytesIO object. Args: file (BytesIO): A BytesIO object representing the contents of the

r"""Generates a list of system messages from a list of dictionaries. Args: meta_dicts (List[Dict[str, str]]): A list of dictionar

r"""Creates an AlpacaItem from a formatted string. Args: text: String in either of these formats: With input:

Generate TTS audio and face videos Args: script_json: Script JSON file path ref_face: Reference face image path

Build sinusoidal embeddings. This matches the implementation in tensor2tensor, but differs slightly from the description in Section 3

Build sinusoidal embeddings. This matches the implementation in tensor2tensor, but differs slightly from the description in Section 3

r"""Gets the prompt for generating tasks for a given task type. Args: task_type (TaskType): The type of the task. Return

r"""Returns a dictionary containing information about the chat session. Args: session_id (str, optional): The ID of the chat sess

Get the last text item at the current document level. Returns: The text item or None, if the current level parent has no children

r"""Get model encoding from tiktoken. Args: value_for_tiktoken: Model value for tiktoken. Returns: tiktoken.Encoding: Model

r"""Retrieve node properties from the graph. Returns: Tuple[List[str], List[Dict[str, Any]]]: A tuple where the first

r"""Extracts plain text from a list of rich text elements. Args: rich_text: A list of dictionaries representing rich text elements.

Get the project root directory

r"""Get the JSON schema of a Pydantic model. Args: pydantic_params (Type[BaseModel]): The Pydantic model class to retrieve th

r"""Retrieve relationship (edge) properties from the graph. Returns: Tuple[List[str], List[Dict[str, Any]]]: A tuple where the fi

r"""Retrieve relationship types from the graph. Returns: List[str]: A list of relationship (edge) type names.

r"""Parse the response of the Agent and return task list. Args: task_response (str): The string response of the Agent. Returns:

Loads an image, resizes it to a maximum width while preserving the aspect ratio, and encodes it as a Base64 data URI.

Transpose the features to interpolate linearly. Args: features (torch.Tensor): The extracted features to be interpolated. se

Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding symbols are ignored.

r"""

r"""Loads a file or a URL and parses its contents into elements. Args: input_path (str): Path to the file or URL to be parsed.

Print results summary for a specific task.

处理整个HTML文件夹

Processes chat history into a structured format for further use. Args: chat_history (List[Dict[str, Any]): A list of dic

r"""Remove a task from the channel.

r"""Saves or updates a Discord installation record.

r"""Set the channel for the node and all the child nodes under it.

r"""Recursively set the state of the task and its subtasks. Args: state (TaskState): The giving state.

Setup logging

r"""Split a string based on a list of characters. Args: s (str): The string to split. char_list (Optional[List[str]],

r"""Start itself and all the child nodes under it.

r"""stop the Docker container. Args: remove (Optional[bool]): Whether to remove the container after stopping it.

Store the key value within a document section in the docling document. Args: section: A patent section name. field: A

r"""Convert the :obj:`MemoryRecord` to a dict for serialization purposes.