llama-cloud 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

llama_cloud/types/llama_parse_parameters.py

@@ -25,15 +25,24 @@ class LlamaParseParameters(pydantic.BaseModel):
     disable_ocr: typing.Optional[bool]
     annotate_links: 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]
     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]
+    html_make_all_elements_visible: 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]
@@ -47,10 +56,22 @@ class LlamaParseParameters(pydantic.BaseModel):
     continuous_mode: typing.Optional[bool]
     s_3_input_path: typing.Optional[str] = pydantic.Field(alias="s3_input_path")
     s_3_output_path_prefix: typing.Optional[str] = pydantic.Field(alias="s3_output_path_prefix")
+    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]
+    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]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/llm.py

@@ -34,7 +34,7 @@ class Llm(pydantic.BaseModel):
     """
 
     callback_manager: typing.Optional[typing.Any]
-    system_prompt: typing.Optional[str]
+    system_prompt: typing.Optional[str] = pydantic.Field(description="System prompt for LLM calls.")
     messages_to_prompt: typing.Optional[str] = pydantic.Field(
         description="Function to convert a list of messages to an LLM prompt."
     )
@@ -43,7 +43,9 @@ class Llm(pydantic.BaseModel):
     )
     output_parser: typing.Optional[typing.Any]
     pydantic_program_mode: typing.Optional[PydanticProgramMode]
-    query_wrapper_prompt: typing.Optional[BasePromptTemplate]
+    query_wrapper_prompt: typing.Optional[BasePromptTemplate] = pydantic.Field(
+        description="Query wrapper prompt for LLM calls."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/llm_parameters.py

@@ -19,8 +19,11 @@ class LlmParameters(pydantic.BaseModel):
     model_name: typing.Optional[SupportedLlmModelNames] = pydantic.Field(
         description="The name of the model to use for LLM completions."
     )
-    system_prompt: typing.Optional[str]
-    temperature: typing.Optional[float]
+    system_prompt: typing.Optional[str] = pydantic.Field(description="The system prompt to use for the completion.")
+    temperature: typing.Optional[float] = pydantic.Field(description="The temperature value for the model.")
+    use_chain_of_thought_reasoning: typing.Optional[bool] = pydantic.Field(
+        description="Whether to use chain of thought reasoning."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/local_eval.py

@@ -21,17 +21,19 @@ class LocalEval(pydantic.BaseModel):
     Output of an BaseEvaluator.
     """
 
-    query: typing.Optional[str]
-    contexts: typing.Optional[typing.List[str]]
-    response: typing.Optional[str]
-    passing: typing.Optional[bool]
-    feedback: typing.Optional[str]
-    score: typing.Optional[float]
-    pairwise_source: typing.Optional[str]
+    query: typing.Optional[str] = pydantic.Field(description="Query string")
+    contexts: typing.Optional[typing.List[str]] = pydantic.Field(description="Context strings")
+    response: typing.Optional[str] = pydantic.Field(description="Response string")
+    passing: typing.Optional[bool] = pydantic.Field(description="Binary evaluation result (passing or not)")
+    feedback: typing.Optional[str] = pydantic.Field(description="Feedback or reasoning for the response")
+    score: typing.Optional[float] = pydantic.Field(description="Score for the response")
+    pairwise_source: typing.Optional[str] = pydantic.Field(
+        description="Used only for pairwise and specifies whether it is from original order of presented answers or flipped order"
+    )
     invalid_result: typing.Optional[bool] = pydantic.Field(
         description="Whether the evaluation result is an invalid one."
     )
-    invalid_reason: typing.Optional[str]
+    invalid_reason: typing.Optional[str] = pydantic.Field(description="Reason for invalid evaluation.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/local_eval_results.py

@@ -21,7 +21,7 @@ class LocalEvalResults(pydantic.BaseModel):
     """
 
     project_id: str = pydantic.Field(description="The ID of the project.")
-    eval_set_id: typing.Optional[str]
+    eval_set_id: typing.Optional[str] = pydantic.Field(description="The ID of the local eval result set.")
     app_name: str = pydantic.Field(description="The name of the app.")
     eval_name: str = pydantic.Field(description="The name of the eval.")
     result: LocalEval = pydantic.Field(description="The eval results.")

llama_cloud/types/managed_ingestion_status_response.py

@@ -17,10 +17,12 @@ except ImportError:
 
 
 class ManagedIngestionStatusResponse(pydantic.BaseModel):
-    job_id: typing.Optional[str]
-    deployment_date: typing.Optional[dt.datetime]
+    job_id: typing.Optional[str] = pydantic.Field(description="ID of the latest job.")
+    deployment_date: typing.Optional[dt.datetime] = pydantic.Field(description="Date of the deployment.")
     status: ManagedIngestionStatus = pydantic.Field(description="Status of the ingestion.")
-    error: typing.Optional[typing.List[IngestionErrorResponse]]
+    error: typing.Optional[typing.List[IngestionErrorResponse]] = pydantic.Field(
+        description="List of errors that occurred during ingestion."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/markdown_element_node_parser.py

@@ -29,12 +29,14 @@ class MarkdownElementNodeParser(pydantic.BaseModel):
     )
     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]
-    llm: typing.Optional[Llm]
+    id_func: typing.Optional[str] = pydantic.Field(description="Function to generate node IDs.")
+    llm: typing.Optional[Llm] = pydantic.Field(description="LLM model to use for summarization.")
     summary_query_str: typing.Optional[str] = pydantic.Field(description="Query string to use for summarization.")
     num_workers: typing.Optional[int] = pydantic.Field(description="Num of workers for async jobs.")
     show_progress: typing.Optional[bool] = pydantic.Field(description="Whether to show progress.")
-    nested_node_parser: typing.Optional[NodeParser]
+    nested_node_parser: typing.Optional[NodeParser] = pydantic.Field(
+        description="Other types of node parsers to handle some types of nodes."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/markdown_node_parser.py

@@ -18,7 +18,8 @@ class MarkdownNodeParser(pydantic.BaseModel):
     """
     Markdown node parser.
 
-    Splits a document into Nodes using custom Markdown splitting logic.
+    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
@@ -30,7 +31,7 @@ class MarkdownNodeParser(pydantic.BaseModel):
     )
     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]
+    id_func: typing.Optional[str] = pydantic.Field(description="Function to generate node IDs.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/metadata_filter.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .filter_operator import FilterOperator
-from .metadata_filter_value import MetadataFilterValue
+from .value import Value
 
 try:
     import pydantic
@@ -27,7 +27,7 @@ class MetadataFilter(pydantic.BaseModel):
     """
 
     key: str
-    value: typing.Optional[MetadataFilterValue]
+    value: typing.Optional[Value]
     operator: typing.Optional[FilterOperator]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/metric_result.py

@@ -15,9 +15,9 @@ except ImportError:
 
 
 class MetricResult(pydantic.BaseModel):
-    passing: typing.Optional[bool]
-    score: typing.Optional[float]
-    feedback: typing.Optional[str]
+    passing: typing.Optional[bool] = pydantic.Field(description="Whether the metric passed or not.")
+    score: typing.Optional[float] = pydantic.Field(description="The score for the metric.")
+    feedback: typing.Optional[str] = pydantic.Field(description="The reasoning for the metric.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/node_parser.py

@@ -24,7 +24,7 @@ class NodeParser(pydantic.BaseModel):
     )
     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]
+    id_func: typing.Optional[str] = pydantic.Field(description="Function to generate node IDs.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/open_ai_embedding.py

@@ -17,20 +17,26 @@ except ImportError:
 class OpenAiEmbedding(pydantic.BaseModel):
     model_name: typing.Optional[str] = pydantic.Field(description="The name of the OpenAI embedding model.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    num_workers: typing.Optional[int]
+    num_workers: typing.Optional[int] = pydantic.Field(
+        description="The number of workers to use for async embedding calls."
+    )
     additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
         description="Additional kwargs for the OpenAI API."
     )
-    api_key: typing.Optional[str]
-    api_base: typing.Optional[str]
-    api_version: typing.Optional[str]
+    api_key: typing.Optional[str] = pydantic.Field(description="The OpenAI API key.")
+    api_base: typing.Optional[str] = pydantic.Field(description="The base URL for OpenAI API.")
+    api_version: typing.Optional[str] = pydantic.Field(description="The version for OpenAI API.")
     max_retries: typing.Optional[int] = pydantic.Field(description="Maximum number of retries.")
     timeout: typing.Optional[float] = pydantic.Field(description="Timeout for each request.")
-    default_headers: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    default_headers: typing.Optional[typing.Dict[str, typing.Optional[str]]] = pydantic.Field(
+        description="The default headers for API requests."
+    )
     reuse_client: typing.Optional[bool] = pydantic.Field(
         description="Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability."
     )
-    dimensions: typing.Optional[int]
+    dimensions: typing.Optional[int] = pydantic.Field(
+        description="The number of dimensions on the output embedding vectors. Works only with v3 embedding models."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/organization.py

@@ -20,8 +20,8 @@ class Organization(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: str = pydantic.Field(description="A name for the organization.")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/page_splitter_node_parser.py

@@ -24,8 +24,8 @@ class PageSplitterNodeParser(pydantic.BaseModel):
     )
     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]
-    page_separator: typing.Optional[str]
+    id_func: typing.Optional[str] = pydantic.Field(description="Function to generate node IDs.")
+    page_separator: typing.Optional[str] = pydantic.Field(description="Separator to split text into pages.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/paginated_list_pipeline_files_response.py

@@ -0,0 +1,35 @@
+# 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 .pipeline_file import PipelineFile
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PaginatedListPipelineFilesResponse(pydantic.BaseModel):
+    files: typing.List[PipelineFile] = pydantic.Field(description="The files to list")
+    limit: int = pydantic.Field(description="The limit of the files")
+    offset: int = pydantic.Field(description="The offset of the files")
+    total_count: int = pydantic.Field(description="The total number of files")
+
+    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/parsing_job_structured_result.py

@@ -0,0 +1,32 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ParsingJobStructuredResult(pydantic.BaseModel):
+    structured: typing.Any
+    job_metadata: typing.Any
+
+    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/permission.py

@@ -20,10 +20,10 @@ class Permission(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: str = pydantic.Field(description="A name for the permission.")
-    description: typing.Optional[str]
+    description: typing.Optional[str] = pydantic.Field(description="A description for the permission.")
     access: bool = pydantic.Field(description="Whether the permission is granted or not.")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/pipeline.py

@@ -29,19 +29,26 @@ class Pipeline(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: str
     project_id: str
+    embedding_model_config_id: typing.Optional[str] = pydantic.Field(
+        description="The ID of the EmbeddingModelConfig this pipeline is using."
+    )
     pipeline_type: typing.Optional[PipelineType] = pydantic.Field(
         description="Type of pipeline. Either PLAYGROUND or MANAGED."
     )
-    managed_pipeline_id: typing.Optional[str]
+    managed_pipeline_id: typing.Optional[str] = pydantic.Field(
+        description="The ID of the ManagedPipeline this playground pipeline is linked to."
+    )
     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]
+    config_hash: typing.Optional[PipelineConfigurationHashes] = pydantic.Field(
+        description="Hashes for the configuration of the pipeline."
+    )
     transform_config: typing.Optional[PipelineTransformConfig] = pydantic.Field(
         description="Configuration for the transformation."
     )
@@ -51,8 +58,12 @@ class Pipeline(pydantic.BaseModel):
     eval_parameters: typing.Optional[EvalExecutionParams] = pydantic.Field(
         description="Eval parameters for the pipeline."
     )
-    llama_parse_parameters: typing.Optional[LlamaParseParameters]
-    data_sink: typing.Optional[DataSink]
+    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."
+    )
+    data_sink: typing.Optional[DataSink] = pydantic.Field(
+        description="The data sink for the pipeline. If None, the pipeline will use the fully managed data sink."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_configuration_hashes.py

@@ -19,9 +19,9 @@ class PipelineConfigurationHashes(pydantic.BaseModel):
     Hashes for the configuration of a pipeline.
     """
 
-    embedding_config_hash: typing.Optional[str]
-    parsing_config_hash: typing.Optional[str]
-    transform_config_hash: typing.Optional[str]
+    embedding_config_hash: typing.Optional[str] = pydantic.Field(description="Hash of the embedding config.")
+    parsing_config_hash: typing.Optional[str] = pydantic.Field(description="Hash of the llama parse parameters.")
+    transform_config_hash: typing.Optional[str] = pydantic.Field(description="Hash of the transform config.")
 
     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

@@ -31,9 +31,18 @@ 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]
-    data_sink: typing.Optional[DataSinkCreate]
+    configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = pydantic.Field(
+        description="Deprecated, use embedding_config or transform_config instead. configured transformations for the pipeline."
+    )
+    data_sink_id: typing.Optional[str] = pydantic.Field(
+        description="Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID."
+    )
+    embedding_model_config_id: typing.Optional[str] = pydantic.Field(
+        description="Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID."
+    )
+    data_sink: typing.Optional[DataSinkCreate] = pydantic.Field(
+        description="Data sink. When provided instead of data_sink_id, the data sink will be created."
+    )
     preset_retrieval_parameters: typing.Optional[PresetRetrievalParams] = pydantic.Field(
         description="Preset retrieval parameters for the pipeline."
     )
@@ -45,7 +54,9 @@ class PipelineCreate(pydantic.BaseModel):
     pipeline_type: typing.Optional[PipelineType] = pydantic.Field(
         description="Type of pipeline. Either PLAYGROUND or MANAGED."
     )
-    managed_pipeline_id: typing.Optional[str]
+    managed_pipeline_id: typing.Optional[str] = pydantic.Field(
+        description="The ID of the ManagedPipeline this playground pipeline is linked to."
+    )
 
     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.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .configurable_data_source_names import ConfigurableDataSourceNames
-from .pipeline_data_source_component import PipelineDataSourceComponent
+from .data_source_create_component import DataSourceCreateComponent
 from .pipeline_data_source_custom_metadata_value import PipelineDataSourceCustomMetadataValue
 
 try:
@@ -23,18 +23,24 @@ class PipelineDataSource(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: str = pydantic.Field(description="The name of the data source.")
     source_type: ConfigurableDataSourceNames
-    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[PipelineDataSourceCustomMetadataValue]]]
-    component: PipelineDataSourceComponent
+    custom_metadata: typing.Optional[
+        typing.Dict[str, typing.Optional[PipelineDataSourceCustomMetadataValue]]
+    ] = pydantic.Field(description="Custom metadata that will be present on all data loaded from the data source")
+    component: DataSourceCreateComponent = pydantic.Field(description="Component that implements the data source")
     project_id: str
     data_source_id: str = pydantic.Field(description="The ID of the data source.")
     pipeline_id: str = pydantic.Field(description="The ID of the pipeline.")
     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]
+    sync_interval: typing.Optional[float] = pydantic.Field(
+        description="The interval at which the data source should be synced."
+    )
+    sync_schedule_set_by: typing.Optional[str] = pydantic.Field(
+        description="The id of the user who set the sync schedule."
+    )
 
     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_create.py

@@ -20,7 +20,9 @@ class PipelineDataSourceCreate(pydantic.BaseModel):
     """
 
     data_source_id: str = pydantic.Field(description="The ID of the data source.")
-    sync_interval: typing.Optional[float]
+    sync_interval: typing.Optional[float] = pydantic.Field(
+        description="The interval at which the data source should be synced."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_deployment.py

@@ -17,11 +17,11 @@ except ImportError:
 
 class PipelineDeployment(pydantic.BaseModel):
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     status: ManagedIngestionStatus = pydantic.Field(description="Status of the pipeline deployment.")
-    started_at: typing.Optional[dt.datetime]
-    ended_at: typing.Optional[dt.datetime]
+    started_at: typing.Optional[dt.datetime] = pydantic.Field(description="Time the pipeline deployment started.")
+    ended_at: typing.Optional[dt.datetime] = pydantic.Field(description="Time the pipeline deployment finished.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_file.py

@@ -6,6 +6,7 @@ import typing
 from ..core.datetime_utils import serialize_datetime
 from .pipeline_file_config_hash_value import PipelineFileConfigHashValue
 from .pipeline_file_custom_metadata_value import PipelineFileCustomMetadataValue
+from .pipeline_file_permission_info_value import PipelineFilePermissionInfoValue
 from .pipeline_file_resource_info_value import PipelineFileResourceInfoValue
 
 try:
@@ -23,19 +24,33 @@ class PipelineFile(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: typing.Optional[str]
-    file_size: typing.Optional[int]
-    file_type: typing.Optional[str]
+    file_size: typing.Optional[int] = pydantic.Field(description="Size of the file in bytes")
+    file_type: typing.Optional[str] = pydantic.Field(description="File type (e.g. pdf, docx, etc.)")
     project_id: str = pydantic.Field(description="The ID of the project that the file belongs to")
-    last_modified_at: typing.Optional[dt.datetime]
-    resource_info: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileResourceInfoValue]]]
-    data_source_id: typing.Optional[str]
-    file_id: typing.Optional[str]
+    last_modified_at: typing.Optional[dt.datetime] = pydantic.Field(description="The last modified time of the file")
+    resource_info: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileResourceInfoValue]]] = pydantic.Field(
+        description="Resource information for the file"
+    )
+    permission_info: typing.Optional[
+        typing.Dict[str, typing.Optional[PipelineFilePermissionInfoValue]]
+    ] = pydantic.Field(description="Permission information for the file")
+    data_source_id: typing.Optional[str] = pydantic.Field(
+        description="The ID of the data source that the file belongs to"
+    )
+    file_id: typing.Optional[str] = pydantic.Field(description="The ID of the file")
     pipeline_id: str = pydantic.Field(description="The ID of the pipeline that the file is associated with")
-    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileCustomMetadataValue]]]
-    config_hash: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileConfigHashValue]]]
+    custom_metadata: typing.Optional[
+        typing.Dict[str, typing.Optional[PipelineFileCustomMetadataValue]]
+    ] = pydantic.Field(description="Custom metadata for the file")
+    config_hash: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileConfigHashValue]]] = pydantic.Field(
+        description="Hashes for the configuration of the pipeline."
+    )
+    indexed_page_count: typing.Optional[int] = pydantic.Field(
+        description="The number of pages that have been indexed for this file"
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_file_create.py

@@ -21,7 +21,9 @@ class PipelineFileCreate(pydantic.BaseModel):
     """
 
     file_id: str = pydantic.Field(description="The ID of the file")
-    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[PipelineFileCreateCustomMetadataValue]]]
+    custom_metadata: typing.Optional[
+        typing.Dict[str, typing.Optional[PipelineFileCreateCustomMetadataValue]]
+    ] = pydantic.Field(description="Custom metadata for the file")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/pipeline_file_permission_info_value.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+PipelineFilePermissionInfoValue = typing.Union[
+    typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
+]