from helix import Chunk

# Simple token-based chunking
text = "Your long document text here..."
chunks = Chunk.token_chunk(text)

# Process multiple texts at once (batch processing)
texts = ["Document 1...", "Document 2...", "Document 3..."]
batch_chunks = Chunk.sentence_chunk(texts)

Chunk.token_chunk(
    text,                      # Single string or list of strings
    chunk_size=2048,           # Maximum tokens per chunk
    chunk_overlap=12,          # Overlapping tokens between chunks
    tokenizer=None             # Optional custom tokenizer
)

Chunk.sentence_chunk(
    text,                      # Single string or list of strings
    tokenizer="character",     # Tokenizer type
    chunk_size=2048,           # Maximum tokens per chunk
    chunk_overlap=12,          # Overlapping tokens between chunks
    min_sentences_per_chunk=1  # Minimum sentences in each chunk
)

Chunk.recursive_chunk(
    text,                       # Single string or list of strings
    tokenizer="character",      # Tokenizer type
    chunk_size=2048,            # Maximum tokens per chunk
    rules=None,                 # Custom recursive splitting rules
    min_characters_per_chunk=24,# Minimum characters per chunk
    recipe=None,                # Predefined chunking recipe
    lang="en"                   # Language code for rules
)

Chunk.code_chunk(
    text,                      # Code text (single string or list)
    language,                  # Programming language (required)
    tokenizer="character",     # Tokenizer type
    chunk_size=2048,           # Maximum tokens per chunk
    include_nodes=False        # Whether to include AST nodes
)

Chunk.semantic_chunk(
    text,                           # Single string or list of strings
    embedding_model="minishlab/potion-base-8M",  # Embedding model
    threshold=0.8,                  # Similarity threshold (0-1)
    chunk_size=2048,                # Maximum tokens per chunk
    similarity_window=3,            # Window size for similarity calculation
    min_sentences_per_chunk=1,      # Minimum sentences per chunk
    min_characters_per_sentence=24, # Minimum characters per sentence
    skip_window=0,                  # Number of groups to skip when merging
    filter_window=5,                # Window length for Savitzky-Golay filter
    filter_polyorder=3,             # Polynomial order for filter
    filter_tolerance=0.2,           # Tolerance for filter boundary detection
    delim=['.', '!', '?', '\n'],    # Sentence delimiters
    include_delim="prev",           # How to include delimiters ("prev", "next", None)
    **embedding_kwargs              # Additional embedding model arguments
)

Chunk.late_chunk(
    text,                       # Single string or list of strings
    embedding_model="all-MiniLM-L6-v2",  # Embedding model
    chunk_size=2048,            # Maximum tokens per chunk
    rules=None,                 # Custom recursive splitting rules
    min_characters_per_chunk=24,# Minimum characters per chunk
    recipe=None,                # Predefined chunking recipe
    lang="en"                   # Language code for rules
)

Chunk.neural_chunk(
    text,                       # Single string or list of strings
    model="mirth/chonky_modernbert_base_1",  # Neural chunking model
    device_map="cpu",           # Device to run the model on
    min_characters_per_chunk=10 # Minimum characters per chunk
)

Chunk.slumber_chunk(
    text,                       # Single string or list of strings
    genie=None,                 # LLM interface (defaults to Gemini)
    tokenizer="character",      # Tokenizer type
    chunk_size=1024,            # Maximum tokens per chunk
    rules=None,                 # Custom recursive splitting rules
    candidate_size=128,         # Size of candidate chunks to evaluate
    min_characters_per_chunk=24,# Minimum characters per chunk
    verbose=True                # Whether to print progress information
)

from helix import Chunk

text = """
This is a massive text blob that we want to chunk into smaller pieces for processing. It contains multiple sentences and paragraphs that need to be divided appropriately to maintain context while fitting within token limits. When working with large documents, it is important to ensure that each chunk maintains enough context for downstream tasks, such as retrieval or summarization. Chunking strategies can vary depending on the use case, but the goal is always to balance context preservation with processing efficiency.

The chunker should handle overlaps properly to ensure no important information is lost at chunk boundaries. For example, if a sentence is split between two chunks, the overlap ensures that both chunks retain the full meaning of the text. This is especially important in applications like document question answering, where missing a single sentence could lead to incorrect answers. Additionally, chunkers may need to account for different languages, code blocks, or special formatting, which can add complexity to the chunking process.

This example demonstrates how the token chunker works with a realistic text sample that would be common in document processing and RAG (Retrieval-Augmented Generation) applications. The chunks will be created with specified token limits and overlap settings to optimize for both comprehension and processing efficiency. Each chunk will contain metadata about its position in the original text and token count for further processing. By using a robust chunking strategy, we can ensure that downstream models receive high-quality, context-rich input, improving the overall performance of NLP pipelines and applications.
"""

chunks = Chunk.token_chunk(text, chunk_size=100, chunk_overlap=20)
print(chunks)

['\nThis is a massive text blob that we want to chunk into smaller pieces for processing. It contains m',
 't contains multiple sentences and paragraphs that need to be divided appropriately to maintain conte',
 'intain context while fitting within token limits. When working with large documents, it is important',
 'is important to ensure that each chunk maintains enough context for downstream tasks, such as retrie',
 'ch as retrieval or summarization. Chunking strategies can vary depending on the use case, but the go',
 ', but the goal is always to balance context preservation with processing efficiency.']