Skip to content

base_extraction_engine

BaseExtractionEngine

Bases: ABC

Source code in griptape/engines/extraction/base_extraction_engine.py 
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
@define
class BaseExtractionEngine(ABC):
    max_token_multiplier: float = field(default=0.5, kw_only=True)
    chunk_joiner: str = field(default="\n\n", kw_only=True)
    prompt_driver: BasePromptDriver = field(
        default=Factory(lambda: Defaults.drivers_config.prompt_driver), kw_only=True
    )
    chunker: BaseChunker = field(
        default=Factory(
            lambda self: TextChunker(tokenizer=self.prompt_driver.tokenizer, max_tokens=self.max_chunker_tokens),
            takes_self=True,
        ),
        kw_only=True,
    )

    @max_token_multiplier.validator  # pyright: ignore[reportAttributeAccessIssue]
    def validate_max_token_multiplier(self, _: Attribute, max_token_multiplier: int) -> None:
        if max_token_multiplier > 1:
            raise ValueError("has to be less than or equal to 1")
        if max_token_multiplier <= 0:
            raise ValueError("has to be greater than 0")

    @property
    def max_chunker_tokens(self) -> int:
        return round(self.prompt_driver.tokenizer.max_input_tokens * self.max_token_multiplier)

    @property
    def min_response_tokens(self) -> int:
        return round(
            self.prompt_driver.tokenizer.max_input_tokens
            - self.prompt_driver.tokenizer.max_input_tokens * self.max_token_multiplier,
        )

    def extract_text(
        self,
        text: str,
        *,
        rulesets: Optional[list[Ruleset]] = None,
        **kwargs,
    ) -> ListArtifact:
        return self.extract_artifacts(ListArtifact([TextArtifact(text)]), rulesets=rulesets, **kwargs)

    @abstractmethod
    def extract_artifacts(
        self,
        artifacts: ListArtifact[TextArtifact],
        *,
        rulesets: Optional[list[Ruleset]] = None,
        **kwargs,
    ) -> ListArtifact: ...

chunk_joiner: str = field(default='\n\n', kw_only=True) class-attribute instance-attribute

chunker: BaseChunker = field(default=Factory(lambda self: TextChunker(tokenizer=self.prompt_driver.tokenizer, max_tokens=self.max_chunker_tokens), takes_self=True), kw_only=True) class-attribute instance-attribute

max_chunker_tokens: int property

max_token_multiplier: float = field(default=0.5, kw_only=True) class-attribute instance-attribute

min_response_tokens: int property

prompt_driver: BasePromptDriver = field(default=Factory(lambda: Defaults.drivers_config.prompt_driver), kw_only=True) class-attribute instance-attribute

extract_artifacts(artifacts, *, rulesets=None, **kwargs) abstractmethod

Source code in griptape/engines/extraction/base_extraction_engine.py 
59
60
61
62
63
64
65
66
@abstractmethod
def extract_artifacts(
    self,
    artifacts: ListArtifact[TextArtifact],
    *,
    rulesets: Optional[list[Ruleset]] = None,
    **kwargs,
) -> ListArtifact: ...

extract_text(text, *, rulesets=None, **kwargs)

Source code in griptape/engines/extraction/base_extraction_engine.py 
50
51
52
53
54
55
56
57
def extract_text(
    self,
    text: str,
    *,
    rulesets: Optional[list[Ruleset]] = None,
    **kwargs,
) -> ListArtifact:
    return self.extract_artifacts(ListArtifact([TextArtifact(text)]), rulesets=rulesets, **kwargs)

validate_max_token_multiplier(_, max_token_multiplier)

Source code in griptape/engines/extraction/base_extraction_engine.py 
32
33
34
35
36
37
@max_token_multiplier.validator  # pyright: ignore[reportAttributeAccessIssue]
def validate_max_token_multiplier(self, _: Attribute, max_token_multiplier: int) -> None:
    if max_token_multiplier > 1:
        raise ValueError("has to be less than or equal to 1")
    if max_token_multiplier <= 0:
        raise ValueError("has to be greater than 0")