function_app/bp_doc_intel_extract_city_names.py [69:111]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
)


# Setup Pydantic models for validation of LLM calls, and the Function response itself
class LLMCityNamesModel(LLMResponseBaseModel):
    """
    Defines the required JSON schema for the LLM to adhere to. This can be used
    to validate that the LLM's raw text response can be parsed into the format
    that is expected by downstream processes (e.g. when we need to save the data
    into a database).

    This class inherits from LLMResponseBaseModel and sets a description and
    example for each field, allowing us to run `model.get_prompt_json_example()`
    to generate a prompt-friendly string representation of the expected JSON
    that we can provide to the LLM.
    """

    city_names: list[str] = Field(
        description="A list of city names, that were extracted from the text.",
        examples=[["London", "Paris", "New York"]],
    )


class FunctionReponseModel(BaseModel):
    """
    Defines the schema that will be returned by the function. We'll use this to
    ensure that the response contains the correct values and structure, and
    to allow a partially filled response to be returned in case of an error.
    """

    success: bool = Field(
        False, description="Indicates whether the pipeline was successful."
    )
    result: Optional[LLMCityNamesModel] = Field(
        None, description="The final result of the pipeline."
    )
    func_time_taken_secs: Optional[float] = Field(
        None, description="The total time taken to process the request."
    )
    error_text: Optional[str] = Field(
        None,
        description="If an error occurred, this field will contain the error message.",
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



function_app/bp_pymupdf_extract_city_names.py [55:97]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
)


# Setup Pydantic models for validation of LLM calls, and the Function response itself
class LLMCityNamesModel(LLMResponseBaseModel):
    """
    Defines the required JSON schema for the LLM to adhere to. This can be used
    to validate that the LLM's raw text response can be parsed into the format
    that is expected by downstream processes (e.g. when we need to save the data
    into a database).

    This class inherits from LLMResponseBaseModel and sets a description and
    example for each field, allowing us to run `model.get_prompt_json_example()`
    to generate a prompt-friendly string representation of the expected JSON
    that we can provide to the LLM.
    """

    city_names: list[str] = Field(
        description="A list of city names, that were extracted from the text.",
        examples=[["London", "Paris", "New York"]],
    )


class FunctionReponseModel(BaseModel):
    """
    Defines the schema that will be returned by the function. We'll use this to
    ensure that the response contains the correct values and structure, and
    to allow a partially filled response to be returned in case of an error.
    """

    success: bool = Field(
        False, description="Indicates whether the pipeline was successful."
    )
    result: Optional[LLMCityNamesModel] = Field(
        None, description="The final result of the pipeline."
    )
    func_time_taken_secs: Optional[float] = Field(
        None, description="The total time taken to process the request."
    )
    error_text: Optional[str] = Field(
        None,
        description="If an error occurred, this field will contain the error message.",
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -