Loads an agent defined on the Hub. <Tip warning={true}> Loading a tool from the Hub means that you'll download the tool and

Loads a tool collection from the Hub. it adds a collection of tools from all Spaces in the collection to the agent's toolbox > [!NOT

Creates a [`Tool`] from a langchain tool.

Automatically load a tool collection from an MCP server. This method supports both SSE and Stdio MCP servers. Look at the `sever_parameters`

Goes back to previous page.

Compare two class items (methods or attributes) for equality.

Launches a gradio demo for a tool. The corresponding tool class needs to properly implement the class attributes `inputs` and `output_type`.

Main function to quickly load a tool from the Hub. <Tip warning={true}> Loading a tool means that you'll download the tool and execute

Exact match of math if and only if: 1. numerical equal: both can convert to float and are equal 2. symbolic equal: both can convert to sy

Exact match of math if and only if: 1. numerical equal: both can convert to float and are equal 2. symbolic equal: both can convert to sy

Process an agent experiment entry Args: entry: Dictionary containing a question model: Model instance

Process a reasoning experiment entry Args: entry: Dictionary containing a question model: Model instance

Top-level function to process a single entry in a separate process Args: entry: The entry to process worker_id: ID of th

Upload the agent to the Hub. Parameters: repo_id (`str`): The name of the repository you want to push to

Upload the tool to the Hub. Parameters: repo_id (`str`): The name of the repository you want to push you

Prints a pretty replay of the agent's steps. Args: detailed (bool, optional): If True, also displays the memory at each step. Def

Prints a pretty replay of the agent's steps. Args: logger (AgentLogger): The logger to print replay logs to. detailed

Endpoint that accepts queries and performs retrieval. Input format: { "queries": ["What is Python?", "Tell me about neural networks

Execute code and return result based on whether it's a final answer.

Decorator to make the evaluation of a function safer by checking its return value. Args: func: Function to make safer. Returns:

Searches for text on the current page via Ctrl + F and jumps to the nth occurrence. Args: text: The text to search for nth_re

Perform one step in the ReAct framework: the agent thinks, acts, and observes the result. Returns None if the step is not final.

Check if execution should stop due to cost threshold Returns: True if cost threshold has been reached, False oth

Converts the model into a JSON-compatible dictionary.

Returns the "raw" version of that object. It is a `torch.Tensor` object.

Update the metrics of the monitor. Args: step_log ([`MemoryStep`]): Step log to update the monitor with.

Handle file uploads, default allowed types are .pdf, .docx, and .txt

Track annotated assignments.

Track variables in dictionary comprehensions

Track exception aliases (the 'e' in 'except Exception as e')

Track variables in list comprehensions

Track variables in set comprehensions

Track aliases in 'with' statements (the 'y' in 'with X as y')

Collect function arguments

Creates a rich tree visualization of the agent's structure.