Generate image description and entity info only, without entity relation extraction. Used for batch processing stage 1. Args

Generate table description and entity info only, without entity relation extraction. Used for batch processing stage 1. Args

Generate equation description and entity info only, without entity relation extraction. Used for batch processing stage 1. A

Generate generic modal description and entity info only, without entity relation extraction. Used for batch processing stage 1.

Run the actual Paper2Slides pipeline Args: session_id: Unique session ID for this upload message: User message f

Get information about available backends

Get current configuration information

Generate config directory name: {output}_{style}_{param}.

Get all figures as markdown, sorted by original position.

Get output directory with timestamp to preserve history.

Get processor supported features

Get path to summary markdown file.

Get list of supported file extensions for batch processing

Index multiple documents by file paths. Args: file_paths: List of file paths to process. output_dir:

Insert pure text content into LightRAG Args: lightrag: LightRAG instance input: Single document string or list of document s

List all projects and their output configurations.

Command-line interface for enhanced markdown conversion

Main function to run the document parser from command line

Command-line interface for batch parsing

Merge all RAG answers from a list of query results. Args: rag_results: List of query results [{"query": ..., "answer": ..., "suc

Normalize and validate input path.

Parse HTML document using Docling Supported formats: .html, .htm, .xhtml Args: html_path: Path to the HTML file

Abstract method to parse image document. Must be implemented by subclasses. Note: Different parsers may support different im

Parse image document using MinerU 2.0 Note: MinerU 2.0 natively supports .png, .jpeg, .jpg formats. Other formats (.bmp, .ti

Parse office document by first converting to PDF, then parsing with MinerU 2.0 Note: This method requires LibreOffice to be installe

Parse office document directly using Docling Supported formats: .doc, .docx, .ppt, .pptx, .xls, .xlsx Args: doc

Parse PDF document using Docling Args: pdf_path: Path to the PDF file output_dir: Output directory path

Parse style string into style type and custom style.

Parse text file by first converting to PDF, then parsing with MinerU 2.0 Supported formats: .txt, .md Args: tex

Create a content plan from generation input.

Async version of batch processing Args: file_paths: List of file paths or directories to process output_dir:

Process user's custom style request with LLM.

Process multiple documents in batch using the new BatchParser Args: file_paths: List of file paths or directories to pro

Process documents in batch and then add them to RAG This method combines document parsing and RAG insertion: 1. First, parse

Process all supported files in a folder Args: folder_path: Path to the folder containing files to process ou

Process image content with context support

Remove all tables from summary content. Supports both formats: 1. Markdown tables: | col1 | col2 | with |---|---| separator 2. H

Stage 4: Generate images.

Stage 3: Plan content sections.

Stage 1: Index document and run RAG queries. Args: base_dir: Base directory for this document/project config: Pipeline config

Stage 2: Extract content from RAG results.

Save generated images as a single PDF file. Args: images: List of GeneratedImage from ImageGenerator.generate() output_p

Save text to file.

Set content source for context extraction Args: content_source: Source content for context extraction content_format:

Try to start a new session. Returns False if another session is already running

Convert to RAGAnythingConfig for internal use.

Validate if a file is a valid image file Args: image_path: Path to the image file max_size_mb: Maximum file size in MB

Initialize the converter Args: config: Configuration for conversion

Initialize MineruParser

Initialize DoclingParser

Initialize batch parser Args: parser_type: Type of parser to use ("mineru" or "docling") max_workers: Maximu

Initialize base processor Args: lightrag: LightRAG instance modal_caption_func: Function for generating descriptions

Initialize image processor Args: lightrag: LightRAG instance modal_caption_func: Function for generating descriptions

Args: config: RAG configuration. Uses defaults if None. lightrag_instance: Existing LightRAG instance to reuse.

Post-initialization setup for backward compatibility

Post-initialization setup following LightRAG pattern