Parse an audio file, transcribing speech to text. This method converts spoken words in the audio file to text, providing a textual

Parse a Word document file and convert it to structured markdown. Args: file_path (str): Path to the DOC or DOCS file.

Parse a document file (PDF, PPT, or DOCX) and convert it to structured markdown. This method extracts text, tables, and images from

Parse an image file, extracting visual information and generating captions. This method can be used for tasks such as object detecti

Parse a PDF file and convert it to structured markdown. Args: file_path (str): Path to the PDF file. output_

Parse a PowerPoint file and convert it to structured markdown. Args: file_path (str): Path to the PPT or PPTX file.

Parse a video file, extracting key frames, generating captions, and transcribing audio. This method provides a structured representa

Parse a website, extracting structured content from web pages. This method crawls the specified URL, extracting text, images, and ot

Process an image with a specific task such as OCR, captioning, or object detection. This method allows for more specific image proce