Types & classes — github.com/pymupdf/pymupdf4llm

CodeHub MCPcopy Create free account

hub / github.com/pymupdf/pymupdf4llm / types & classes

Types & classes10 in github.com/pymupdf/pymupdf4llm

⨍ Functions 159◇ Types & classes 10

↓ 5 callersClassPDFMarkdownReader

Read PDF files using PyMuPDF library.

pymupdf4llm/pymupdf4llm/llama/pdf_markdown_reader.py:17

↓ 2 callersClassIdentifyHeaders

Compute data for identifying header text. All non-white text from all selected pages is extracted and its font size noted as a rounded value.

pymupdf4llm/pymupdf4llm/helpers/pymupdf_rag.py:70

↓ 1 callersClassLayoutBox

pymupdf4llm/pymupdf4llm/helpers/document_layout.py:632

↓ 1 callersClassPageLayout

pymupdf4llm/pymupdf4llm/helpers/document_layout.py:650

↓ 1 callersClassParameters

pymupdf4llm/pymupdf4llm/helpers/pymupdf_rag.py:225

↓ 1 callersClassParsedDocument

pymupdf4llm/pymupdf4llm/helpers/document_layout.py:663

↓ 1 callersClass_ProgressBar

pymupdf4llm/pymupdf4llm/helpers/progress.py:19

↓ 1 callersClassmy_app

examples/GUI/browser-app.py:73

ClassLayoutEncoder

pymupdf4llm/pymupdf4llm/helpers/document_layout.py:786

ClassTocHeaders

Compute data for identifying header text. This is an alternative to IdentifyHeaders. Instead of running through the full document to identify

pymupdf4llm/pymupdf4llm/helpers/pymupdf_rag.py:174