ml_research_tools.doc

Document processing tools for ML Research.

class ml_research_tools.doc.AskDocumentTool(services)

Bases: BaseTool

Tool for interactive chat with document content.

Initialize the tool with default values.

Parameters:

services (ServiceProvider)

classmethod add_arguments(parser)

Add tool-specific arguments to the argument parser.

Return type:

None

Parameters:

parser (ArgumentParser)

description: str = 'Interactive chat with document content using LLMs'

execute(config, args)

Execute the tool with the provided arguments.

Return type:

int

Parameters:

• config (Config)

• args (Namespace)

name: str = 'ask-document'

Submodules

• has_requests()
• has_bs4()
• has_pypdf2()
• has_tiktoken()
• DocumentParser
• TextDocumentParser
• CodeDocumentParser
• LatexDocumentParser
• PDFDocumentParser
• URLParser
• get_parser_for_document()
• generate_document_cache_key()
• load_document_with_cache()
• estimate_token_count_with_cache()
• DocumentChat
• AskDocumentTool
• get_venue_pdfs_with_metadata()
• OpenreviewLoadTool
• PDFDocument
• SearchResult
• PDFIndexDB
• PDFIndexTool