Splitting_configuration

This module contains functionality related to the the splitting_configuration module for embedding.bootstrap.configuration.

Splitting_configuration

SplitterConfiguration

Bases: BaseConfiguration

Base configuration class for text splitters.

This class provides the foundation for defining specific configurations required by different text splitting algorithms.

Source code in src/embedding/bootstrap/configuration/splitting_configuration.py
19
20
21
22
23
24
25
26
27
class SplitterConfiguration(BaseConfiguration):
    """
    Base configuration class for text splitters.

    This class provides the foundation for defining specific configurations
    required by different text splitting algorithms.
    """

    pass

SplitterConfigurationRegistry

Bases: ConfigurationRegistry

Registry for managing different splitter configurations.

This registry maps SplitterName enum values to their corresponding configuration classes, allowing for dynamic configuration selection based on the chosen splitter type.

Attributes:
  • _key_class (Type) –

    The type used as keys in the registry (SplitterName).

Source code in src/embedding/bootstrap/configuration/splitting_configuration.py
31
32
33
34
35
36
37
38
39
40
41
42
43
class SplitterConfigurationRegistry(ConfigurationRegistry):
    """
    Registry for managing different splitter configurations.

    This registry maps SplitterName enum values to their corresponding
    configuration classes, allowing for dynamic configuration selection
    based on the chosen splitter type.

    Attributes:
        _key_class: The type used as keys in the registry (SplitterName).
    """

    _key_class: Type = SplitterName

SplitterName

Bases: str, Enum

Enumeration of available text splitter types.

Attributes:
  • BASIC_MARKDOWN

    A basic splitter for markdown documents.

Source code in src/embedding/bootstrap/configuration/splitting_configuration.py
 8
 9
10
11
12
13
14
15
16
class SplitterName(str, Enum):
    """
    Enumeration of available text splitter types.

    Attributes:
        BASIC_MARKDOWN: A basic splitter for markdown documents.
    """

    BASIC_MARKDOWN = "basic-markdown"