How-To Guides Overview¶

This section provides focused, task-based guides for working with rs_document. Each guide covers a specific workflow or use case with practical examples.

Getting Started¶

• Loading Documents - Create documents from files and manage metadata
• Cleaning Tasks - Remove bullets, ligatures, and special characters
• Splitting Tasks - Split documents with different strategies

Advanced Workflows¶

• Batch Operations - Process multiple documents efficiently
• Vector DB Preparation - Prepare documents for embedding and retrieval
• LangChain Integration - Use rs_document with LangChain

Quick Examples¶

Basic Document Processing¶

from rs_document import Document

# Create, clean, and split a document
doc = Document(
    page_content="Your text here...",
    metadata={"source": "example.txt"}
)

doc.clean()
chunks = doc.recursive_character_splitter(1000)

Batch Processing¶

from rs_document import clean_and_split_docs, Document

# Process multiple documents at once
documents = [...]  # Your documents
chunks = clean_and_split_docs(documents, chunk_size=1000)

Common Use Cases¶

RAG Applications¶

1. Load your documents
2. Clean the text
3. Split into chunks
4. Prepare for vector DB

Text Processing Pipeline¶

1. Create documents with metadata
2. Apply specific cleaners
3. Split with context overlap
4. Filter and organize chunks

Need More Help?¶

• See the API Reference for detailed method documentation
• Check the Tutorial to learn the basics first