​
Megaparse

Megaparse is an advanced document parsing system that can handle complex document structures and multiple file formats.

​
Features

  • Multi-format support (PDF, DOCX, TXT, etc.)
  • Intelligent chunk splitting
  • Metadata extraction
  • Table and image handling
  • Structure preservation

​
Usage

from quivr_core.parsers import MegaparseParser

parser = MegaparseParser()
documents = parser.parse("path/to/document.pdf")

for doc in documents:
    print(f"Content: {doc.page_content}")
    print(f"Metadata: {doc.metadata}")

​
Configuration

You can customize the parser behavior: 
parser = MegaparseParser(
    chunk_size=1000,
    chunk_overlap=200,
    include_metadata=True,
    extract_tables=True
)

​
Supported File Types

  • PDF (.pdf)
  • Word Documents (.docx, .doc)
  • Text Files (.txt)
  • Markdown (.md)
  • HTML (.html)
  • And more…
For simpler parsing needs, see the Simple Parser documentation.