r"""Build the API server. Returns: RemoteHttpRuntime: The current runtime.

Build a slide in the presentation.

Calculate overall metrics for comparison task.

Calculate per-category metrics for deficiency tasks only.

r"""Calculate rouge l score between hypothesis and reference.

Calculate score prediction metrics.

Calculate detailed metrics for each task type (F1, accuracy, etc.) Note: This function assumes answer_content is already extracted from <answ

r"""Runs the agent in a chat conversation mode. Args: *args (Any): Positional arguments to pass to the agent. remote

r"""Check whether the input model configuration contains unexpected arguments Raises: ValueError: If the model configurat

Check if two bboxes overlap sufficiently.

Split Chinese text into chunks, prioritizing chunks ending with period, exclamation or question marks, then considering commas and other punc

Uses OpenAI API to classify whether each main category has deficiencies (booleans). Returns a list of category names predicted as True.

Delete all slides from the presentation.

Merge multiple video chunks into one complete video using ffmpeg concat mode

r"""Compare the function name and arguments of agent_call and ground_truth_call. Args: agent_call (str): Function call by agent.

For comparison tasks only: - Extract text from the <answer> tag. - If it exactly matches the solution (e.g., "Slide A" or "Slide B"),

r"""compose task result by the sub-tasks. Args: agent (ChatAgent): An agent that used to compose the task result. tem

Composite PNG background with TTS audio into a video (no face overlay).

Composite PNG background with face video into a single encoded output video (audio from face video).

Compute the conditional vector field ut(x1|x0) = x1 - x0, see Eq.(15) [1]. Parameters ---------- x0 : Tensor, shape

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

r"""Save the machine-generated tasks to the specified output path in JSON format.

r"Construct prompt from tools and input.

r"""Construct tool descriptions from function definitions and descriptions.

r"""Convert the collected data into a dictionary.

r"""Convert the collected data into a dictionary.

r"""Convert the content to the specified choice. Args: content (str): The content to be converted. choices (List[str]

r"""Convert the content to the specified grammar. Args: content (str): The content to be converted. grammar (str): Th

r"""Convert the content to the specified JSON schema given by output_schema. Args: content (str): The content to be conve

r"""Convert the content to the specified Pydantic schema. Args: content (str): The content to be converted. output_sc

r"""Convert the content to the specified regex pattern. Args: content (str): The content to be converted. regex_patte

r"""Convert the content to the specified type. The following types are currently available: 1. int 2. float

r"""Count the number of tokens in the messages using the specific tokenizer. Args: messages (List[Dict]): message list wi

r"""Returns successive n-sized chunks from provided text. Split a text into smaller chunks of size n". Args: text (str): The text to

r"""An abstract method to create conversational context from the chat history. Constructs the context from provided records. The spec

Create necessary directories if they don't exist

r"""Creates a Text element from a given text input, with optional metadata and embeddings. Args: text (str): The text con

r"""Reads an uploaded file and returns a File object. Args: file (BytesIO): A BytesIO object representing the contents of the

Apply enrichment based on scholar_request in the slide JSON. Args: paper_markdown: The paper content in markdown format

Transform a sequence of int ids into a their string versions. This method supports transforming individual input/output ids to their

Default audio loader

Default image loader

r"""Deletes an installation record by guild ID.

r"""Deletes the entire collection in the Qdrant storage.

r"""Displays the options to the user. Args: messages (Sequence[BaseMessage]): A list of `BaseMessage` objects. Returns:

r"""Download APIBank dataset and code from Github.

r"""Download the benchmark data. Returns: BaseBenchmark: The benchmark instance.

r"""Download the Nexus Functional Calling Benchmark dataset.

r"""Download the RAGBench dataset.

r"""Download the APIBench dataset.

r"""Encode multiple prompt instructions into a single string.

r"""Ensures that a specified edge type exists in the NebulaGraph database. If the edge type already exists, this method does nothing.

Returns the "width-equivalent length" of the text when forced newlines are respected. Each physical line (including partial) is counted as if

r"""Evaluate the messages using the reward model. Args: messages (List[Dict[str, str]]): A list of messages where each

r"""Check if a task with the given id exists.

Synchronous wrapper for extract_layout_async.

Extract text from a table cell, including lists with indents.