​

Simple Parser

The Simple Parser provides basic text processing capabilities for straightforward document parsing needs.

​

Features

• Basic text chunking
• Minimal preprocessing
• Fast processing speed
• Low memory usage

​

Usage

from quivr_core.parsers import SimpleParser

parser = SimpleParser()
documents = parser.parse("path/to/document.txt")

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

​

Configuration

Configure the parser with these options:

parser = SimpleParser(
    chunk_size=500,  # Number of characters per chunk
    chunk_overlap=50,  # Number of overlapping characters between chunks
    strip_whitespace=True,  # Remove excess whitespace
    lowercase=False  # Convert text to lowercase
)

​

When to Use

Use the Simple Parser when:

• Processing plain text files
• Need fast processing
• Don’t require advanced features
• Working with simple document structures

For more advanced parsing needs, see the Megaparse documentation.