chunking-strategies

Chunking Strategies for RAG

Optimize document splitting for retrieval accuracy and context preservation.

When to Use

• Designing a new RAG pipeline
• Retrieval quality is poor due to chunk boundaries
• Documents have mixed content types (code, tables, prose)
• Need to balance context window limits with retrieval precision

Chunking Methods

1. Fixed-Size Chunking

from langchain.text_splitter import CharacterTextSplitter

splitter = CharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    separator="\n"
)
chunks = splitter.split_text(document)

Best for: Homogeneous content, quick prototyping Avoid when: Documents have natural boundaries (sections, paragraphs)

2. Recursive Character Splitting

from langchain.text_splitter import RecursiveCharacterTextSplitter

splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    separators=["\n\n", "\n", ".", " ", ""]
)
chunks = splitter.split_documents(docs)

Best for: General-purpose text, maintains paragraph integrity Hierarchy: Tries larger separators first, falls back to smaller

3. Semantic Chunking

from langchain_experimental.text_splitter import SemanticChunker
from langchain_openai import OpenAIEmbeddings

splitter = SemanticChunker(
    embeddings=OpenAIEmbeddings(),
    breakpoint_threshold_type="percentile",
    breakpoint_threshold_amount=95
)
chunks = splitter.split_text(document)

Best for: When meaning matters more than size Trade-off: Slower, requires embedding calls

4. Document-Specific Chunking

Markdown

from langchain.text_splitter import MarkdownHeaderTextSplitter

headers = [
    ("#", "h1"),
    ("##", "h2"),
    ("###", "h3"),
]
splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers)
chunks = splitter.split_text(markdown_doc)

Code

from langchain.text_splitter import Language, RecursiveCharacterTextSplitter

splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.PYTHON,
    chunk_size=2000,
    chunk_overlap=200
)
chunks = splitter.split_documents(code_docs)