Encodes an image to a base64 string.

Extract and parse the floorplan room data. Args: text (str): The input text containing floorplan data Returns:

n is num_of_classes

Merge walls that are extremely close and should be combined (within the same room).

fill in the hole

Query recent info (skill/image/reasoning) from memory.

Handle file uploads and store them in the upload directory

Performs a left-click at the current mouse location.

Load the memory from the local file.

Load all existing files from the uploads folder

Load data from a file in the storage directory.

Load data from a file in the storage directory.

Render loop for Gradio

Render loop for Gradio

Moves the mouse pointer to the specified (x, y) location.

Sends an image to the Vision-LLM endpoint, saves the returned annotation, and returns a double-spaced string representation of the detected b

Use huggingface model to replace the original model

Simulates pressing the 'Esc' key.

Simulates pressing the 'Esc' key.

Press and hold the left mouse button at the current location.

Replace placeholders in each paragraph and join them.

Refresh the list of files from the current session and detect new files

Releases the left mouse button.

Reset the view to the VNC viewer

Save the memory to the local file.

Save data to a file in the storage directory.

Save data to a file in the storage directory.

Set the environment name.

Retrieve the keys from the store. Args: data: the query data. top_k: the number of results to return. **k

For each line, check for intersections with all other lines and split the line at each intersection.

Toggle between OmniTool Computer view and file viewer