Deprecated as of v1.2.0The SDPM (Semantic Double-Pass Merging) functionality has been integrated into the main SemanticChunker.Recommended Migration:
# Old way (deprecated)
from chonkie.legacy import SDPMChunker
chunker = SDPMChunker(skip_window=1)

# New way (recommended)
from chonkie import SemanticChunker
chunker = SemanticChunker(skip_window=1)
The new SemanticChunker provides all SDPM capabilities plus additional improvements like Savitzky-Golay filtering for better boundary detection.
The SDPMChunker extends semantic chunking by using a double-pass merging approach. It first groups content by semantic similarity, then merges similar groups within a skip window, allowing it to connect related content that may not be consecutive in the text.

​
Why Use the New SemanticChunker Instead?

The new SemanticChunker includes all SDPM functionality plus:
  • Better performance: Optimized C extensions for faster processing
  • Smoother boundaries: Savitzky-Golay filtering for noise reduction
  • Cleaner API: Simplified parameter names and improved defaults
  • Active development: Ongoing improvements and bug fixes

​
Legacy Installation

If you need to use the legacy version for compatibility: 
pip install "chonkie[semantic]"
Then import from the legacy module: 
from chonkie.legacy import SDPMChunker

​
Legacy Usage

This documentation is preserved for users who need to maintain existing code using SDPMChunker. For new projects, please use the main SemanticChunker.

​
Basic Initialization

from chonkie.legacy import SDPMChunker

# Legacy initialization
chunker = SDPMChunker(
    embedding_model="minishlab/potion-base-8M",
    threshold=0.5,                              
    chunk_size=2048,                             
    min_sentences=1,                            
    skip_window=1                               
)

​
Legacy Parameters

The legacy SDPMChunker uses these parameters (many now renamed in the new SemanticChunker):
  • embedding_model: Model identifier or embedding instance
  • mode: “cumulative” or “window” (removed in new version)
  • threshold: Similarity threshold (0-1) or “auto”
  • chunk_size: Maximum tokens per chunk
  • similarity_window: Sentences for threshold calculation
  • min_sentences: Minimum sentences per chunk (now min_sentences_per_chunk)
  • min_chunk_size: Minimum tokens per chunk (removed in new version)
  • min_characters_per_sentence: Minimum characters per sentence
  • threshold_step: Step size for threshold calculation (removed in new version)
  • skip_window: Number of chunks to skip when merging

​
Example Migration

​
Old Code (Legacy)

from chonkie.legacy import SDPMChunker

chunker = SDPMChunker(
    embedding_model="minishlab/potion-base-8M",
    mode="window",
    threshold="auto",
    chunk_size=512,
    min_sentences=1,
    min_chunk_size=2,
    skip_window=1
)

chunks = chunker.chunk(text)
for chunk in chunks:
    print(f"Sentences: {len(chunk.sentences)}")

from chonkie import SemanticChunker

chunker = SemanticChunker(
    embedding_model="minishlab/potion-base-8M",
    threshold=0.7,  # Explicit threshold instead of "auto"
    chunk_size=512,
    min_sentences_per_chunk=1,  # Renamed parameter
    skip_window=1  # Same functionality
)

chunks = chunker.chunk(text)
for chunk in chunks:
    print(f"Token count: {chunk.token_count}")

​
Return Type Changes

​
Legacy Return Type

The legacy SDPMChunker returns SemanticChunk objects with sentence details: 
@dataclass
class SemanticChunk:
    text: str
    start_index: int
    end_index: int
    token_count: int
    sentences: List[SemanticSentence]  # Detailed sentence information

​
New Return Type

The new SemanticChunker returns simpler Chunk objects: 
@dataclass
class Chunk:
    text: str
    start_index: int
    end_index: int
    token_count: int
    # No sentence details - cleaner and more efficient

​
Full Legacy Documentation

For users who must use the legacy version, the complete original functionality remains available: 
from chonkie.legacy import SDPMChunker

# All original parameters still work
chunker = SDPMChunker(
    embedding_model="minishlab/potion-base-8M",
    mode="window",
    threshold="auto",
    chunk_size=2048,
    similarity_window=1,
    min_sentences=1,
    min_chunk_size=2,
    min_characters_per_sentence=12,
    threshold_step=0.01,
    delim=[". ", "! ", "? ", "\n"],
    include_delim="prev",
    skip_window=1
)

# Original methods preserved
chunks = chunker.chunk(text)
batch_chunks = chunker.chunk_batch(texts)

​
Support

While the legacy SDPMChunker remains available for backward compatibility, it is no longer actively developed. Please consider migrating to the new SemanticChunker for:
  • Better performance
  • Active bug fixes
  • New features
  • Ongoing support
For migration assistance, see the SemanticChunker documentation or open an issue on our GitHub repository.