llama-cloud 0.1.41__py3-none-any.whl → 1.0.0b4__py3-none-any.whl

llama_cloud/types/llama_parse_parameters.py

@@ -1,140 +1,261 @@
-# This file was auto-generated by Fern from our API Definition.
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-import datetime as dt
-import typing
+from typing import List, Optional
+from typing_extensions import Literal
 
-from ..core.datetime_utils import serialize_datetime
-from .fail_page_mode import FailPageMode
-from .llama_parse_parameters_priority import LlamaParseParametersPriority
-from .parser_languages import ParserLanguages
+from pydantic import Field as FieldInfo
+
+from .._models import BaseModel
 from .parsing_mode import ParsingMode
-from .webhook_configuration import WebhookConfiguration
+from .fail_page_mode import FailPageMode
+from .parsing_languages import ParsingLanguages
+from .extraction.webhook_configuration import WebhookConfiguration
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+__all__ = ["LlamaParseParameters"]
 
 
-class LlamaParseParameters(pydantic.BaseModel):
+class LlamaParseParameters(BaseModel):
     """
     Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.
     """
 
-    webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]]
-    priority: typing.Optional[LlamaParseParametersPriority]
-    languages: typing.Optional[typing.List[ParserLanguages]]
-    parsing_instruction: typing.Optional[str]
-    disable_ocr: typing.Optional[bool]
-    annotate_links: typing.Optional[bool]
-    adaptive_long_table: typing.Optional[bool]
-    compact_markdown_table: typing.Optional[bool]
-    disable_reconstruction: typing.Optional[bool]
-    disable_image_extraction: typing.Optional[bool]
-    invalidate_cache: typing.Optional[bool]
-    outlined_table_extraction: typing.Optional[bool]
-    merge_tables_across_pages_in_markdown: typing.Optional[bool]
-    output_pdf_of_document: typing.Optional[bool]
-    do_not_cache: typing.Optional[bool]
-    fast_mode: typing.Optional[bool]
-    skip_diagonal_text: typing.Optional[bool]
-    preserve_layout_alignment_across_pages: typing.Optional[bool]
-    preserve_very_small_text: typing.Optional[bool]
-    gpt_4_o_mode: typing.Optional[bool] = pydantic.Field(alias="gpt4o_mode")
-    gpt_4_o_api_key: typing.Optional[str] = pydantic.Field(alias="gpt4o_api_key")
-    do_not_unroll_columns: typing.Optional[bool]
-    extract_layout: typing.Optional[bool]
-    high_res_ocr: typing.Optional[bool]
-    html_make_all_elements_visible: typing.Optional[bool]
-    layout_aware: typing.Optional[bool]
-    html_remove_navigation_elements: typing.Optional[bool]
-    html_remove_fixed_elements: typing.Optional[bool]
-    guess_xlsx_sheet_name: typing.Optional[bool]
-    page_separator: typing.Optional[str]
-    bounding_box: typing.Optional[str]
-    bbox_top: typing.Optional[float]
-    bbox_right: typing.Optional[float]
-    bbox_bottom: typing.Optional[float]
-    bbox_left: typing.Optional[float]
-    target_pages: typing.Optional[str]
-    use_vendor_multimodal_model: typing.Optional[bool]
-    vendor_multimodal_model_name: typing.Optional[str]
-    model: typing.Optional[str]
-    vendor_multimodal_api_key: typing.Optional[str]
-    page_prefix: typing.Optional[str]
-    page_suffix: typing.Optional[str]
-    webhook_url: typing.Optional[str]
-    preset: typing.Optional[str]
-    take_screenshot: typing.Optional[bool]
-    is_formatting_instruction: typing.Optional[bool]
-    premium_mode: typing.Optional[bool]
-    continuous_mode: typing.Optional[bool]
-    input_s_3_path: typing.Optional[str] = pydantic.Field(alias="input_s3_path")
-    input_s_3_region: typing.Optional[str] = pydantic.Field(alias="input_s3_region")
-    output_s_3_path_prefix: typing.Optional[str] = pydantic.Field(alias="output_s3_path_prefix")
-    output_s_3_region: typing.Optional[str] = pydantic.Field(alias="output_s3_region")
-    project_id: typing.Optional[str]
-    azure_openai_deployment_name: typing.Optional[str]
-    azure_openai_endpoint: typing.Optional[str]
-    azure_openai_api_version: typing.Optional[str]
-    azure_openai_key: typing.Optional[str]
-    input_url: typing.Optional[str]
-    http_proxy: typing.Optional[str]
-    auto_mode: typing.Optional[bool]
-    auto_mode_trigger_on_regexp_in_page: typing.Optional[str]
-    auto_mode_trigger_on_text_in_page: typing.Optional[str]
-    auto_mode_trigger_on_table_in_page: typing.Optional[bool]
-    auto_mode_trigger_on_image_in_page: typing.Optional[bool]
-    auto_mode_configuration_json: typing.Optional[str]
-    structured_output: typing.Optional[bool]
-    structured_output_json_schema: typing.Optional[str]
-    structured_output_json_schema_name: typing.Optional[str]
-    max_pages: typing.Optional[int]
-    max_pages_enforced: typing.Optional[int]
-    extract_charts: typing.Optional[bool]
-    formatting_instruction: typing.Optional[str]
-    complemental_formatting_instruction: typing.Optional[str]
-    content_guideline_instruction: typing.Optional[str]
-    spreadsheet_extract_sub_tables: typing.Optional[bool]
-    job_timeout_in_seconds: typing.Optional[float]
-    job_timeout_extra_time_per_page_in_seconds: typing.Optional[float]
-    strict_mode_image_extraction: typing.Optional[bool]
-    strict_mode_image_ocr: typing.Optional[bool]
-    strict_mode_reconstruction: typing.Optional[bool]
-    strict_mode_buggy_font: typing.Optional[bool]
-    save_images: typing.Optional[bool]
-    hide_headers: typing.Optional[bool]
-    hide_footers: typing.Optional[bool]
-    page_header_prefix: typing.Optional[str]
-    page_header_suffix: typing.Optional[str]
-    page_footer_prefix: typing.Optional[str]
-    page_footer_suffix: typing.Optional[str]
-    ignore_document_elements_for_layout_detection: typing.Optional[bool]
-    output_tables_as_html: typing.Optional[bool] = pydantic.Field(alias="output_tables_as_HTML")
-    internal_is_screenshot_job: typing.Optional[bool]
-    parse_mode: typing.Optional[ParsingMode]
-    system_prompt: typing.Optional[str]
-    system_prompt_append: typing.Optional[str]
-    user_prompt: typing.Optional[str]
-    page_error_tolerance: typing.Optional[float]
-    replace_failed_page_mode: typing.Optional[FailPageMode]
-    replace_failed_page_with_error_message_prefix: typing.Optional[str]
-    replace_failed_page_with_error_message_suffix: typing.Optional[str]
-    markdown_table_multiline_header_separator: typing.Optional[str]
-
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-        json_encoders = {dt.datetime: serialize_datetime}
+    adaptive_long_table: Optional[bool] = None
+
+    aggressive_table_extraction: Optional[bool] = None
+
+    annotate_links: Optional[bool] = None
+
+    auto_mode: Optional[bool] = None
+
+    auto_mode_configuration_json: Optional[str] = None
+
+    auto_mode_trigger_on_image_in_page: Optional[bool] = None
+
+    auto_mode_trigger_on_regexp_in_page: Optional[str] = None
+
+    auto_mode_trigger_on_table_in_page: Optional[bool] = None
+
+    auto_mode_trigger_on_text_in_page: Optional[str] = None
+
+    azure_openai_api_version: Optional[str] = None
+
+    azure_openai_deployment_name: Optional[str] = None
+
+    azure_openai_endpoint: Optional[str] = None
+
+    azure_openai_key: Optional[str] = None
+
+    bbox_bottom: Optional[float] = None
+
+    bbox_left: Optional[float] = None
+
+    bbox_right: Optional[float] = None
+
+    bbox_top: Optional[float] = None
+
+    bounding_box: Optional[str] = None
+
+    compact_markdown_table: Optional[bool] = None
+
+    complemental_formatting_instruction: Optional[str] = None
+
+    content_guideline_instruction: Optional[str] = None
+
+    continuous_mode: Optional[bool] = None
+
+    disable_image_extraction: Optional[bool] = None
+
+    disable_ocr: Optional[bool] = None
+
+    disable_reconstruction: Optional[bool] = None
+
+    do_not_cache: Optional[bool] = None
+
+    do_not_unroll_columns: Optional[bool] = None
+
+    extract_charts: Optional[bool] = None
+
+    extract_layout: Optional[bool] = None
+
+    extract_printed_page_number: Optional[bool] = None
+
+    fast_mode: Optional[bool] = None
+
+    formatting_instruction: Optional[str] = None
+
+    gpt4o_api_key: Optional[str] = None
+
+    gpt4o_mode: Optional[bool] = None
+
+    guess_xlsx_sheet_name: Optional[bool] = None
+
+    hide_footers: Optional[bool] = None
+
+    hide_headers: Optional[bool] = None
+
+    high_res_ocr: Optional[bool] = None
+
+    html_make_all_elements_visible: Optional[bool] = None
+
+    html_remove_fixed_elements: Optional[bool] = None
+
+    html_remove_navigation_elements: Optional[bool] = None
+
+    http_proxy: Optional[str] = None
+
+    ignore_document_elements_for_layout_detection: Optional[bool] = None
+
+    images_to_save: Optional[List[Literal["screenshot", "embedded", "layout"]]] = None
+
+    inline_images_in_markdown: Optional[bool] = None
+
+    input_s3_path: Optional[str] = None
+
+    input_s3_region: Optional[str] = None
+
+    input_url: Optional[str] = None
+
+    internal_is_screenshot_job: Optional[bool] = None
+
+    invalidate_cache: Optional[bool] = None
+
+    is_formatting_instruction: Optional[bool] = None
+
+    job_timeout_extra_time_per_page_in_seconds: Optional[float] = None
+
+    job_timeout_in_seconds: Optional[float] = None
+
+    keep_page_separator_when_merging_tables: Optional[bool] = None
+
+    languages: Optional[List[ParsingLanguages]] = None
+
+    layout_aware: Optional[bool] = None
+
+    line_level_bounding_box: Optional[bool] = None
+
+    markdown_table_multiline_header_separator: Optional[str] = None
+
+    max_pages: Optional[int] = None
+
+    max_pages_enforced: Optional[int] = None
+
+    merge_tables_across_pages_in_markdown: Optional[bool] = None
+
+    model: Optional[str] = None
+
+    outlined_table_extraction: Optional[bool] = None
+
+    output_pdf_of_document: Optional[bool] = None
+
+    output_s3_path_prefix: Optional[str] = None
+
+    output_s3_region: Optional[str] = None
+
+    output_tables_as_html: Optional[bool] = FieldInfo(alias="output_tables_as_HTML", default=None)
+
+    page_error_tolerance: Optional[float] = None
+
+    page_footer_prefix: Optional[str] = None
+
+    page_footer_suffix: Optional[str] = None
+
+    page_header_prefix: Optional[str] = None
+
+    page_header_suffix: Optional[str] = None
+
+    page_prefix: Optional[str] = None
+
+    page_separator: Optional[str] = None
+
+    page_suffix: Optional[str] = None
+
+    parse_mode: Optional[ParsingMode] = None
+    """Enum for representing the mode of parsing to be used."""
+
+    parsing_instruction: Optional[str] = None
+
+    precise_bounding_box: Optional[bool] = None
+
+    premium_mode: Optional[bool] = None
+
+    presentation_out_of_bounds_content: Optional[bool] = None
+
+    presentation_skip_embedded_data: Optional[bool] = None
+
+    preserve_layout_alignment_across_pages: Optional[bool] = None
+
+    preserve_very_small_text: Optional[bool] = None
+
+    preset: Optional[str] = None
+
+    priority: Optional[Literal["low", "medium", "high", "critical"]] = None
+    """The priority for the request.
+
+    This field may be ignored or overwritten depending on the organization tier.
+    """
+
+    project_id: Optional[str] = None
+
+    remove_hidden_text: Optional[bool] = None
+
+    replace_failed_page_mode: Optional[FailPageMode] = None
+    """Enum for representing the different available page error handling modes."""
+
+    replace_failed_page_with_error_message_prefix: Optional[str] = None
+
+    replace_failed_page_with_error_message_suffix: Optional[str] = None
+
+    save_images: Optional[bool] = None
+
+    skip_diagonal_text: Optional[bool] = None
+
+    specialized_chart_parsing_agentic: Optional[bool] = None
+
+    specialized_chart_parsing_efficient: Optional[bool] = None
+
+    specialized_chart_parsing_plus: Optional[bool] = None
+
+    specialized_image_parsing: Optional[bool] = None
+
+    spreadsheet_extract_sub_tables: Optional[bool] = None
+
+    spreadsheet_force_formula_computation: Optional[bool] = None
+
+    strict_mode_buggy_font: Optional[bool] = None
+
+    strict_mode_image_extraction: Optional[bool] = None
+
+    strict_mode_image_ocr: Optional[bool] = None
+
+    strict_mode_reconstruction: Optional[bool] = None
+
+    structured_output: Optional[bool] = None
+
+    structured_output_json_schema: Optional[str] = None
+
+    structured_output_json_schema_name: Optional[str] = None
+
+    system_prompt: Optional[str] = None
+
+    system_prompt_append: Optional[str] = None
+
+    take_screenshot: Optional[bool] = None
+
+    target_pages: Optional[str] = None
+
+    tier: Optional[str] = None
+
+    use_vendor_multimodal_model: Optional[bool] = None
+
+    user_prompt: Optional[str] = None
+
+    vendor_multimodal_api_key: Optional[str] = None
+
+    vendor_multimodal_model_name: Optional[str] = None
+
+    version: Optional[str] = None
+
+    webhook_configurations: Optional[List[WebhookConfiguration]] = None
+    """The outbound webhook configurations"""
+
+    webhook_url: Optional[str] = None

llama_cloud/types/llama_parse_parameters_param.py

@@ -0,0 +1,261 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import List, Iterable, Optional
+from typing_extensions import Literal, Annotated, TypedDict
+
+from .._utils import PropertyInfo
+from .parsing_mode import ParsingMode
+from .fail_page_mode import FailPageMode
+from .parsing_languages import ParsingLanguages
+from .extraction.webhook_configuration_param import WebhookConfigurationParam
+
+__all__ = ["LlamaParseParametersParam"]
+
+
+class LlamaParseParametersParam(TypedDict, total=False):
+    """
+    Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.
+    """
+
+    adaptive_long_table: Optional[bool]
+
+    aggressive_table_extraction: Optional[bool]
+
+    annotate_links: Optional[bool]
+
+    auto_mode: Optional[bool]
+
+    auto_mode_configuration_json: Optional[str]
+
+    auto_mode_trigger_on_image_in_page: Optional[bool]
+
+    auto_mode_trigger_on_regexp_in_page: Optional[str]
+
+    auto_mode_trigger_on_table_in_page: Optional[bool]
+
+    auto_mode_trigger_on_text_in_page: Optional[str]
+
+    azure_openai_api_version: Optional[str]
+
+    azure_openai_deployment_name: Optional[str]
+
+    azure_openai_endpoint: Optional[str]
+
+    azure_openai_key: Optional[str]
+
+    bbox_bottom: Optional[float]
+
+    bbox_left: Optional[float]
+
+    bbox_right: Optional[float]
+
+    bbox_top: Optional[float]
+
+    bounding_box: Optional[str]
+
+    compact_markdown_table: Optional[bool]
+
+    complemental_formatting_instruction: Optional[str]
+
+    content_guideline_instruction: Optional[str]
+
+    continuous_mode: Optional[bool]
+
+    disable_image_extraction: Optional[bool]
+
+    disable_ocr: Optional[bool]
+
+    disable_reconstruction: Optional[bool]
+
+    do_not_cache: Optional[bool]
+
+    do_not_unroll_columns: Optional[bool]
+
+    extract_charts: Optional[bool]
+
+    extract_layout: Optional[bool]
+
+    extract_printed_page_number: Optional[bool]
+
+    fast_mode: Optional[bool]
+
+    formatting_instruction: Optional[str]
+
+    gpt4o_api_key: Optional[str]
+
+    gpt4o_mode: Optional[bool]
+
+    guess_xlsx_sheet_name: Optional[bool]
+
+    hide_footers: Optional[bool]
+
+    hide_headers: Optional[bool]
+
+    high_res_ocr: Optional[bool]
+
+    html_make_all_elements_visible: Optional[bool]
+
+    html_remove_fixed_elements: Optional[bool]
+
+    html_remove_navigation_elements: Optional[bool]
+
+    http_proxy: Optional[str]
+
+    ignore_document_elements_for_layout_detection: Optional[bool]
+
+    images_to_save: Optional[List[Literal["screenshot", "embedded", "layout"]]]
+
+    inline_images_in_markdown: Optional[bool]
+
+    input_s3_path: Optional[str]
+
+    input_s3_region: Optional[str]
+
+    input_url: Optional[str]
+
+    internal_is_screenshot_job: Optional[bool]
+
+    invalidate_cache: Optional[bool]
+
+    is_formatting_instruction: Optional[bool]
+
+    job_timeout_extra_time_per_page_in_seconds: Optional[float]
+
+    job_timeout_in_seconds: Optional[float]
+
+    keep_page_separator_when_merging_tables: Optional[bool]
+
+    languages: List[ParsingLanguages]
+
+    layout_aware: Optional[bool]
+
+    line_level_bounding_box: Optional[bool]
+
+    markdown_table_multiline_header_separator: Optional[str]
+
+    max_pages: Optional[int]
+
+    max_pages_enforced: Optional[int]
+
+    merge_tables_across_pages_in_markdown: Optional[bool]
+
+    model: Optional[str]
+
+    outlined_table_extraction: Optional[bool]
+
+    output_pdf_of_document: Optional[bool]
+
+    output_s3_path_prefix: Optional[str]
+
+    output_s3_region: Optional[str]
+
+    output_tables_as_html: Annotated[Optional[bool], PropertyInfo(alias="output_tables_as_HTML")]
+
+    page_error_tolerance: Optional[float]
+
+    page_footer_prefix: Optional[str]
+
+    page_footer_suffix: Optional[str]
+
+    page_header_prefix: Optional[str]
+
+    page_header_suffix: Optional[str]
+
+    page_prefix: Optional[str]
+
+    page_separator: Optional[str]
+
+    page_suffix: Optional[str]
+
+    parse_mode: Optional[ParsingMode]
+    """Enum for representing the mode of parsing to be used."""
+
+    parsing_instruction: Optional[str]
+
+    precise_bounding_box: Optional[bool]
+
+    premium_mode: Optional[bool]
+
+    presentation_out_of_bounds_content: Optional[bool]
+
+    presentation_skip_embedded_data: Optional[bool]
+
+    preserve_layout_alignment_across_pages: Optional[bool]
+
+    preserve_very_small_text: Optional[bool]
+
+    preset: Optional[str]
+
+    priority: Optional[Literal["low", "medium", "high", "critical"]]
+    """The priority for the request.
+
+    This field may be ignored or overwritten depending on the organization tier.
+    """
+
+    project_id: Optional[str]
+
+    remove_hidden_text: Optional[bool]
+
+    replace_failed_page_mode: Optional[FailPageMode]
+    """Enum for representing the different available page error handling modes."""
+
+    replace_failed_page_with_error_message_prefix: Optional[str]
+
+    replace_failed_page_with_error_message_suffix: Optional[str]
+
+    save_images: Optional[bool]
+
+    skip_diagonal_text: Optional[bool]
+
+    specialized_chart_parsing_agentic: Optional[bool]
+
+    specialized_chart_parsing_efficient: Optional[bool]
+
+    specialized_chart_parsing_plus: Optional[bool]
+
+    specialized_image_parsing: Optional[bool]
+
+    spreadsheet_extract_sub_tables: Optional[bool]
+
+    spreadsheet_force_formula_computation: Optional[bool]
+
+    strict_mode_buggy_font: Optional[bool]
+
+    strict_mode_image_extraction: Optional[bool]
+
+    strict_mode_image_ocr: Optional[bool]
+
+    strict_mode_reconstruction: Optional[bool]
+
+    structured_output: Optional[bool]
+
+    structured_output_json_schema: Optional[str]
+
+    structured_output_json_schema_name: Optional[str]
+
+    system_prompt: Optional[str]
+
+    system_prompt_append: Optional[str]
+
+    take_screenshot: Optional[bool]
+
+    target_pages: Optional[str]
+
+    tier: Optional[str]
+
+    use_vendor_multimodal_model: Optional[bool]
+
+    user_prompt: Optional[str]
+
+    vendor_multimodal_api_key: Optional[str]
+
+    vendor_multimodal_model_name: Optional[str]
+
+    version: Optional[str]
+
+    webhook_configurations: Optional[Iterable[WebhookConfigurationParam]]
+    """The outbound webhook configurations"""
+
+    webhook_url: Optional[str]