Skip to content

SemanticChunkingConfiguration

Source code in docs_src/capo_qconnect/types/semantic_chunking_configuration.py 
 8
 9
10
11
12
13
14
class SemanticChunkingConfiguration(TypedDict, closed=True):
    max_tokens: "int"
    """<p>The maximum number of tokens that a chunk can contain.</p>"""
    buffer_size: "int"
    """<p>The buffer size.</p>"""
    breakpoint_percentile_threshold: "int"
    """<p>The dissimilarity threshold for splitting chunks.</p>"""

breakpoint_percentile_threshold instance-attribute 

breakpoint_percentile_threshold: int

The dissimilarity threshold for splitting chunks.

buffer_size instance-attribute 

buffer_size: int

The buffer size.

max_tokens instance-attribute 

max_tokens: int

The maximum number of tokens that a chunk can contain.