llama-cloud 0.1.18__py3-none-any.whl → 0.1.20__py3-none-any.whl

llama_cloud/types/parse_job_config.py

@@ -0,0 +1,134 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .fail_page_mode import FailPageMode
+from .parser_languages import ParserLanguages
+from .parsing_mode import ParsingMode
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ParseJobConfig(pydantic.BaseModel):
+    """
+    Configuration for llamaparse job
+    """
+
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Any]]
+    resource_info: typing.Optional[typing.Dict[str, typing.Any]]
+    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]
+    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]
+    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]
+    html_make_all_elements_visible: 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]
+    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]
+    file_name: str = pydantic.Field(description="The file name.")
+    original_file_name: str = pydantic.Field(description="The original file name.")
+    file_key: str = pydantic.Field(description="The file key.")
+    lang: str = pydantic.Field(description="The language.")
+    output_bucket: typing.Optional[str] = pydantic.Field(alias="outputBucket")
+    file_id: typing.Optional[str]
+    pipeline_id: 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}

llama_cloud/types/pg_vector_distance_method.py

@@ -0,0 +1,43 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class PgVectorDistanceMethod(str, enum.Enum):
+    """
+    Distance methods for PGVector.
+    Docs:
+    https://github.com/pgvector/pgvector?tab=readme-ov-file#query-options
+    """
+
+    L_2 = "l2"
+    IP = "ip"
+    COSINE = "cosine"
+    L_1 = "l1"
+    HAMMING = "hamming"
+    JACCARD = "jaccard"
+
+    def visit(
+        self,
+        l_2: typing.Callable[[], T_Result],
+        ip: typing.Callable[[], T_Result],
+        cosine: typing.Callable[[], T_Result],
+        l_1: typing.Callable[[], T_Result],
+        hamming: typing.Callable[[], T_Result],
+        jaccard: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is PgVectorDistanceMethod.L_2:
+            return l_2()
+        if self is PgVectorDistanceMethod.IP:
+            return ip()
+        if self is PgVectorDistanceMethod.COSINE:
+            return cosine()
+        if self is PgVectorDistanceMethod.L_1:
+            return l_1()
+        if self is PgVectorDistanceMethod.HAMMING:
+            return hamming()
+        if self is PgVectorDistanceMethod.JACCARD:
+            return jaccard()

llama_cloud/types/{extract_job_create_batch.py → pg_vector_hnsw_settings.py}

@@ -4,8 +4,8 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_config import ExtractConfig
-from .extract_job_create_batch_data_schema_override import ExtractJobCreateBatchDataSchemaOverride
+from .pg_vector_distance_method import PgVectorDistanceMethod
+from .pg_vector_vector_type import PgVectorVectorType
 
 try:
     import pydantic
@@ -16,17 +16,20 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ExtractJobCreateBatch(pydantic.BaseModel):
+class PgVectorHnswSettings(pydantic.BaseModel):
     """
-    Schema for creating extraction jobs in batch.
+    HNSW settings for PGVector.
     """
 
-    extraction_agent_id: str = pydantic.Field(description="The id of the extraction agent")
-    file_ids: typing.List[str] = pydantic.Field(description="The ids of the files")
-    data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride] = pydantic.Field(
-        description="The data schema to override the extraction agent's data schema with"
+    ef_construction: typing.Optional[int] = pydantic.Field(
+        description="The number of edges to use during the construction phase."
     )
-    config_override: typing.Optional[ExtractConfig]
+    ef_search: typing.Optional[int] = pydantic.Field(description="The number of edges to use during the search phase.")
+    m: typing.Optional[int] = pydantic.Field(
+        description="The number of bi-directional links created for each new element."
+    )
+    vector_type: typing.Optional[PgVectorVectorType] = pydantic.Field(description="The type of vector to use.")
+    distance_method: typing.Optional[PgVectorDistanceMethod] = pydantic.Field(description="The distance method to use.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pg_vector_vector_type.py

@@ -0,0 +1,35 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class PgVectorVectorType(str, enum.Enum):
+    """
+    Vector storage formats for PGVector.
+    Docs:
+    https://github.com/pgvector/pgvector?tab=readme-ov-file#query-options
+    """
+
+    VECTOR = "vector"
+    HALF_VEC = "half_vec"
+    BIT = "bit"
+    SPARSE_VEC = "sparse_vec"
+
+    def visit(
+        self,
+        vector: typing.Callable[[], T_Result],
+        half_vec: typing.Callable[[], T_Result],
+        bit: typing.Callable[[], T_Result],
+        sparse_vec: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is PgVectorVectorType.VECTOR:
+            return vector()
+        if self is PgVectorVectorType.HALF_VEC:
+            return half_vec()
+        if self is PgVectorVectorType.BIT:
+            return bit()
+        if self is PgVectorVectorType.SPARSE_VEC:
+            return sparse_vec()

llama_cloud/types/pipeline.py

@@ -4,12 +4,12 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .configured_transformation_item import ConfiguredTransformationItem
 from .data_sink import DataSink
 from .eval_execution_params import EvalExecutionParams
 from .llama_parse_parameters import LlamaParseParameters
 from .pipeline_configuration_hashes import PipelineConfigurationHashes
 from .pipeline_embedding_config import PipelineEmbeddingConfig
+from .pipeline_metadata_config import PipelineMetadataConfig
 from .pipeline_transform_config import PipelineTransformConfig
 from .pipeline_type import PipelineType
 from .preset_retrieval_params import PresetRetrievalParams
@@ -39,9 +39,6 @@ class Pipeline(pydantic.BaseModel):
     )
     managed_pipeline_id: typing.Optional[str]
     embedding_config: PipelineEmbeddingConfig
-    configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = pydantic.Field(
-        description="Deprecated don't use it, List of configured transformations."
-    )
     config_hash: typing.Optional[PipelineConfigurationHashes]
     transform_config: typing.Optional[PipelineTransformConfig] = pydantic.Field(
         description="Configuration for the transformation."
@@ -54,6 +51,7 @@ class Pipeline(pydantic.BaseModel):
     )
     llama_parse_parameters: typing.Optional[LlamaParseParameters]
     data_sink: typing.Optional[DataSink]
+    metadata_config: typing.Optional[PipelineMetadataConfig]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_create.py

@@ -4,12 +4,12 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .configured_transformation_item import ConfiguredTransformationItem
 from .data_sink_create import DataSinkCreate
 from .eval_execution_params import EvalExecutionParams
 from .llama_parse_parameters import LlamaParseParameters
 from .pipeline_create_embedding_config import PipelineCreateEmbeddingConfig
 from .pipeline_create_transform_config import PipelineCreateTransformConfig
+from .pipeline_metadata_config import PipelineMetadataConfig
 from .pipeline_type import PipelineType
 from .preset_retrieval_params import PresetRetrievalParams
 
@@ -31,7 +31,6 @@ class PipelineCreate(pydantic.BaseModel):
     transform_config: typing.Optional[PipelineCreateTransformConfig] = pydantic.Field(
         description="Configuration for the transformation."
     )
-    configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]]
     data_sink_id: typing.Optional[str]
     embedding_model_config_id: typing.Optional[str]
     data_sink: typing.Optional[DataSinkCreate]
@@ -44,6 +43,8 @@ class PipelineCreate(pydantic.BaseModel):
     llama_parse_parameters: typing.Optional[LlamaParseParameters] = pydantic.Field(
         description="Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline."
     )
+    status: typing.Optional[str]
+    metadata_config: typing.Optional[PipelineMetadataConfig]
     name: str
     pipeline_type: typing.Optional[PipelineType] = pydantic.Field(
         description="Type of pipeline. Either PLAYGROUND or MANAGED."

llama_cloud/types/pipeline_data_source.py

@@ -7,6 +7,7 @@ from ..core.datetime_utils import serialize_datetime
 from .configurable_data_source_names import ConfigurableDataSourceNames
 from .pipeline_data_source_component import PipelineDataSourceComponent
 from .pipeline_data_source_custom_metadata_value import PipelineDataSourceCustomMetadataValue
+from .pipeline_data_source_status import PipelineDataSourceStatus
 
 try:
     import pydantic
@@ -36,6 +37,8 @@ class PipelineDataSource(pydantic.BaseModel):
     last_synced_at: dt.datetime = pydantic.Field(description="The last time the data source was automatically synced.")
     sync_interval: typing.Optional[float]
     sync_schedule_set_by: typing.Optional[str]
+    status: typing.Optional[PipelineDataSourceStatus]
+    status_updated_at: typing.Optional[dt.datetime]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_data_source_component.py

@@ -2,27 +2,6 @@
 
 import typing
 
-from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_box_data_source import CloudBoxDataSource
-from .cloud_confluence_data_source import CloudConfluenceDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
-from .cloud_jira_data_source import CloudJiraDataSource
-from .cloud_notion_page_data_source import CloudNotionPageDataSource
-from .cloud_one_drive_data_source import CloudOneDriveDataSource
-from .cloud_s_3_data_source import CloudS3DataSource
-from .cloud_sharepoint_data_source import CloudSharepointDataSource
-from .cloud_slack_data_source import CloudSlackDataSource
+from .pipeline_data_source_component_one import PipelineDataSourceComponentOne
 
-PipelineDataSourceComponent = typing.Union[
-    typing.Dict[str, typing.Any],
-    CloudS3DataSource,
-    CloudAzStorageBlobDataSource,
-    CloudGoogleDriveDataSource,
-    CloudOneDriveDataSource,
-    CloudSharepointDataSource,
-    CloudSlackDataSource,
-    CloudNotionPageDataSource,
-    CloudConfluenceDataSource,
-    CloudJiraDataSource,
-    CloudBoxDataSource,
-]
+PipelineDataSourceComponent = typing.Union[typing.Dict[str, typing.Any], PipelineDataSourceComponentOne]

llama_cloud/types/pipeline_data_source_component_one.py

@@ -0,0 +1,122 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+from .cloud_box_data_source import CloudBoxDataSource
+from .cloud_confluence_data_source import CloudConfluenceDataSource
+from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_jira_data_source import CloudJiraDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
+from .cloud_one_drive_data_source import CloudOneDriveDataSource
+from .cloud_s_3_data_source import CloudS3DataSource
+from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
+
+
+class PipelineDataSourceComponentOne_AzureStorageBlob(CloudAzStorageBlobDataSource):
+    type: typing_extensions.Literal["AZURE_STORAGE_BLOB"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_Box(CloudBoxDataSource):
+    type: typing_extensions.Literal["BOX"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_Confluence(CloudConfluenceDataSource):
+    type: typing_extensions.Literal["CONFLUENCE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_GoogleDrive(CloudGoogleDriveDataSource):
+    type: typing_extensions.Literal["GOOGLE_DRIVE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_Jira(CloudJiraDataSource):
+    type: typing_extensions.Literal["JIRA"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_MicrosoftOnedrive(CloudOneDriveDataSource):
+    type: typing_extensions.Literal["MICROSOFT_ONEDRIVE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_MicrosoftSharepoint(CloudSharepointDataSource):
+    type: typing_extensions.Literal["MICROSOFT_SHAREPOINT"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_NotionPage(CloudNotionPageDataSource):
+    type: typing_extensions.Literal["NOTION_PAGE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_S3(CloudS3DataSource):
+    type: typing_extensions.Literal["S3"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class PipelineDataSourceComponentOne_Slack(CloudSlackDataSource):
+    type: typing_extensions.Literal["SLACK"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+PipelineDataSourceComponentOne = typing.Union[
+    PipelineDataSourceComponentOne_AzureStorageBlob,
+    PipelineDataSourceComponentOne_Box,
+    PipelineDataSourceComponentOne_Confluence,
+    PipelineDataSourceComponentOne_GoogleDrive,
+    PipelineDataSourceComponentOne_Jira,
+    PipelineDataSourceComponentOne_MicrosoftOnedrive,
+    PipelineDataSourceComponentOne_MicrosoftSharepoint,
+    PipelineDataSourceComponentOne_NotionPage,
+    PipelineDataSourceComponentOne_S3,
+    PipelineDataSourceComponentOne_Slack,
+]

llama_cloud/types/pipeline_data_source_status.py

@@ -0,0 +1,33 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class PipelineDataSourceStatus(str, enum.Enum):
+    NOT_STARTED = "NOT_STARTED"
+    IN_PROGRESS = "IN_PROGRESS"
+    SUCCESS = "SUCCESS"
+    ERROR = "ERROR"
+    CANCELLED = "CANCELLED"
+
+    def visit(
+        self,
+        not_started: typing.Callable[[], T_Result],
+        in_progress: typing.Callable[[], T_Result],
+        success: typing.Callable[[], T_Result],
+        error: typing.Callable[[], T_Result],
+        cancelled: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is PipelineDataSourceStatus.NOT_STARTED:
+            return not_started()
+        if self is PipelineDataSourceStatus.IN_PROGRESS:
+            return in_progress()
+        if self is PipelineDataSourceStatus.SUCCESS:
+            return success()
+        if self is PipelineDataSourceStatus.ERROR:
+            return error()
+        if self is PipelineDataSourceStatus.CANCELLED:
+            return cancelled()

llama_cloud/types/pipeline_file.py

@@ -42,6 +42,7 @@ class PipelineFile(pydantic.BaseModel):
     config_hash: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileConfigHashValue]]]
     indexed_page_count: typing.Optional[int]
     status: typing.Optional[PipelineFileStatus]
+    status_updated_at: typing.Optional[dt.datetime]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_file_update_dispatcher_config.py

@@ -0,0 +1,38 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .delete_params import DeleteParams
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PipelineFileUpdateDispatcherConfig(pydantic.BaseModel):
+    """
+    Schema for the parameters of a load files job.
+    """
+
+    pipeline_file_ids: typing.Optional[typing.List[str]]
+    should_delete: typing.Optional[bool]
+    delete_info: typing.Optional[DeleteParams]
+
+    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
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/{markdown_node_parser.py → pipeline_file_updater_config.py}

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .delete_params import DeleteParams
 
 try:
     import pydantic
@@ -14,25 +15,23 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class MarkdownNodeParser(pydantic.BaseModel):
+class PipelineFileUpdaterConfig(pydantic.BaseModel):
     """
-    Markdown node parser.
-
-    Splits a document into Nodes using Markdown header-based splitting logic.
-    Each node contains its text content and the path of headers leading to it.
-
-    Args:
-    include_metadata (bool): whether to include metadata in nodes
-    include_prev_next_rel (bool): whether to include prev/next relationships
+    Schema for the parameters of a load files job.
     """
 
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Any]]
+    resource_info: typing.Optional[typing.Dict[str, typing.Any]]
+    should_delete: typing.Optional[bool]
+    should_parse: typing.Optional[bool]
+    delete_info: typing.Optional[DeleteParams]
+    is_new_file: typing.Optional[bool] = pydantic.Field(description="Whether the file is new")
+    data_source_project_file_changed: typing.Optional[bool] = pydantic.Field(
+        description="Whether the data source project file has changed"
+    )
+    should_migrate_pipeline_file_to_external_file_id: typing.Optional[bool] = pydantic.Field(
+        description="Whether to migrate the pipeline file to the external file id"
     )
-    include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
-    class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_managed_ingestion_job_params.py

@@ -0,0 +1,37 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .delete_params import DeleteParams
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PipelineManagedIngestionJobParams(pydantic.BaseModel):
+    """
+    Schema for the parameters of a managed pipeline ingestion job.
+    """
+
+    should_delete: typing.Optional[bool]
+    delete_info: typing.Optional[DeleteParams]
+
+    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
+        json_encoders = {dt.datetime: serialize_datetime}