RAG Patterns

Chunking Strategies

from langchain.text_splitter import RecursiveCharacterTextSplitter

# Strategy 1: Recursive character splitting (general purpose)
splitter = RecursiveCharacterTextSplitter(
    chunk_size=512,
    chunk_overlap=64,
    separators=["\n\n", "\n", ". ", " ", ""],
    length_function=len,
)

# Strategy 2: Semantic chunking (better coherence)
from langchain_experimental.text_splitter import SemanticChunker
from langchain_openai import OpenAIEmbeddings