llama-cloud 0.1.6__py3-none-any.whl → 0.1.7a1__py3-none-any.whl

llama_cloud/types/cloud_jira_data_source.py

@@ -20,12 +20,10 @@ class CloudJiraDataSource(pydantic.BaseModel):
     """
 
     supports_access_control: typing.Optional[bool]
-    email: typing.Optional[str] = pydantic.Field(description="The email address to use for authentication.")
-    api_token: typing.Optional[str] = pydantic.Field(
-        description="The API/ Access Token used for Basic, PAT and OAuth2 authentication."
-    )
-    server_url: typing.Optional[str] = pydantic.Field(description="The server url for Jira Cloud.")
-    cloud_id: typing.Optional[str] = pydantic.Field(description="The cloud ID, used in case of OAuth2.")
+    email: typing.Optional[str]
+    api_token: typing.Optional[str]
+    server_url: typing.Optional[str]
+    cloud_id: typing.Optional[str]
     authentication_mechanism: str = pydantic.Field(description="Type of Authentication for connecting to Jira APIs.")
     query: str = pydantic.Field(description="JQL (Jira Query Language) query to search.")
     class_name: typing.Optional[str]

llama_cloud/types/cloud_notion_page_data_source.py

@@ -17,8 +17,8 @@ except ImportError:
 class CloudNotionPageDataSource(pydantic.BaseModel):
     supports_access_control: typing.Optional[bool]
     integration_token: str = pydantic.Field(description="The integration token to use for authentication.")
-    database_ids: typing.Optional[str] = pydantic.Field(description="The Notion Database Id to read content from.")
-    page_ids: typing.Optional[str] = pydantic.Field(description="The Page ID's of the Notion to read from.")
+    database_ids: typing.Optional[str]
+    page_ids: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_one_drive_data_source.py

@@ -17,14 +17,12 @@ except ImportError:
 class CloudOneDriveDataSource(pydantic.BaseModel):
     supports_access_control: typing.Optional[bool]
     user_principal_name: str = pydantic.Field(description="The user principal name to use for authentication.")
-    folder_path: typing.Optional[str] = pydantic.Field(description="The path of the OneDrive folder to read from.")
-    folder_id: typing.Optional[str] = pydantic.Field(description="The ID of the OneDrive folder to read from.")
+    folder_path: typing.Optional[str]
+    folder_id: typing.Optional[str]
     client_id: str = pydantic.Field(description="The client ID to use for authentication.")
     client_secret: str = pydantic.Field(description="The client secret to use for authentication.")
     tenant_id: str = pydantic.Field(description="The tenant ID to use for authentication.")
-    required_exts: typing.Optional[typing.List[str]] = pydantic.Field(
-        description="The list of required file extensions."
-    )
+    required_exts: typing.Optional[typing.List[str]]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_postgres_vector_store.py

@@ -25,6 +25,7 @@ class CloudPostgresVectorStore(pydantic.BaseModel):
     schema_name: str
     embed_dim: int
     hybrid_search: typing.Optional[bool]
+    perform_setup: typing.Optional[bool]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_s_3_data_source.py

@@ -17,14 +17,10 @@ except ImportError:
 class CloudS3DataSource(pydantic.BaseModel):
     supports_access_control: typing.Optional[bool]
     bucket: str = pydantic.Field(description="The name of the S3 bucket to read from.")
-    prefix: typing.Optional[str] = pydantic.Field(description="The prefix of the S3 objects to read from.")
-    aws_access_id: typing.Optional[str] = pydantic.Field(description="The AWS access ID to use for authentication.")
-    aws_access_secret: typing.Optional[str] = pydantic.Field(
-        description="The AWS access secret to use for authentication."
-    )
-    s_3_endpoint_url: typing.Optional[str] = pydantic.Field(
-        alias="s3_endpoint_url", description="The S3 endpoint URL to use for authentication."
-    )
+    prefix: typing.Optional[str]
+    aws_access_id: typing.Optional[str]
+    aws_access_secret: typing.Optional[str]
+    s_3_endpoint_url: typing.Optional[str] = pydantic.Field(alias="s3_endpoint_url")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_sharepoint_data_source.py

@@ -16,17 +16,15 @@ except ImportError:
 
 class CloudSharepointDataSource(pydantic.BaseModel):
     supports_access_control: typing.Optional[bool]
-    site_name: typing.Optional[str] = pydantic.Field(description="The name of the SharePoint site to download from.")
-    site_id: typing.Optional[str] = pydantic.Field(description="The ID of the SharePoint site to download from.")
-    folder_path: typing.Optional[str] = pydantic.Field(description="The path of the Sharepoint folder to read from.")
-    folder_id: typing.Optional[str] = pydantic.Field(description="The ID of the Sharepoint folder to read from.")
-    drive_name: typing.Optional[str] = pydantic.Field(description="The name of the Sharepoint drive to read from.")
+    site_name: typing.Optional[str]
+    site_id: typing.Optional[str]
+    folder_path: typing.Optional[str]
+    folder_id: typing.Optional[str]
+    drive_name: typing.Optional[str]
     client_id: str = pydantic.Field(description="The client ID to use for authentication.")
     client_secret: str = pydantic.Field(description="The client secret to use for authentication.")
     tenant_id: str = pydantic.Field(description="The tenant ID to use for authentication.")
-    required_exts: typing.Optional[typing.List[str]] = pydantic.Field(
-        description="The list of required file extensions."
-    )
+    required_exts: typing.Optional[typing.List[str]]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_slack_data_source.py

@@ -17,12 +17,12 @@ except ImportError:
 class CloudSlackDataSource(pydantic.BaseModel):
     supports_access_control: typing.Optional[bool]
     slack_token: str = pydantic.Field(description="Slack Bot Token.")
-    channel_ids: typing.Optional[str] = pydantic.Field(description="Slack Channel.")
-    latest_date: typing.Optional[str] = pydantic.Field(description="Latest date.")
-    earliest_date: typing.Optional[str] = pydantic.Field(description="Earliest date.")
-    earliest_date_timestamp: typing.Optional[float] = pydantic.Field(description="Earliest date timestamp.")
-    latest_date_timestamp: typing.Optional[float] = pydantic.Field(description="Latest date timestamp.")
-    channel_patterns: typing.Optional[str] = pydantic.Field(description="Slack Channel name pattern.")
+    channel_ids: typing.Optional[str]
+    latest_date: typing.Optional[str]
+    earliest_date: typing.Optional[str]
+    earliest_date_timestamp: typing.Optional[float]
+    latest_date_timestamp: typing.Optional[float]
+    channel_patterns: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/code_splitter.py

@@ -27,7 +27,7 @@ class CodeSplitter(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] = pydantic.Field(description="Function to generate node IDs.")
+    id_func: typing.Optional[str]
     language: str = pydantic.Field(description="The programming language of the code being split.")
     chunk_lines: typing.Optional[int] = pydantic.Field(description="The number of lines to include in each chunk.")
     chunk_lines_overlap: typing.Optional[int] = pydantic.Field(

llama_cloud/types/cohere_embedding.py

@@ -17,14 +17,10 @@ except ImportError:
 class CohereEmbedding(pydantic.BaseModel):
     model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the Cohere model to use.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    num_workers: typing.Optional[int] = pydantic.Field(
-        description="The number of workers to use for async embedding calls."
-    )
-    api_key: typing.Optional[str] = pydantic.Field(description="The Cohere API key.")
+    num_workers: typing.Optional[int]
+    api_key: typing.Optional[str]
     truncate: typing.Optional[str] = pydantic.Field(description="Truncation type - START/ END/ NONE")
-    input_type: typing.Optional[str] = pydantic.Field(
-        description="Model Input type. If not provided, search_document and search_query are used when needed."
-    )
+    input_type: typing.Optional[str]
     embedding_type: typing.Optional[str] = pydantic.Field(
         description="Embedding type. If not provided float embedding_type is used when needed."
     )

llama_cloud/types/composite_retrieval_mode.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class CompositeRetrievalMode(str, enum.Enum):
+    """
+    Enum for the mode of composite retrieval.
+    """
+
+    ROUTING = "routing"
+    FULL = "full"
+
+    def visit(self, routing: typing.Callable[[], T_Result], full: typing.Callable[[], T_Result]) -> T_Result:
+        if self is CompositeRetrievalMode.ROUTING:
+            return routing()
+        if self is CompositeRetrievalMode.FULL:
+            return full()

llama_cloud/types/composite_retrieval_result.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 .composite_retrieved_text_node import CompositeRetrievedTextNode
+from .page_screenshot_node_with_score import PageScreenshotNodeWithScore
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CompositeRetrievalResult(pydantic.BaseModel):
+    nodes: typing.Optional[typing.List[CompositeRetrievedTextNode]] = pydantic.Field(
+        description="The retrieved nodes from the composite retrieval."
+    )
+    image_nodes: typing.Optional[typing.List[PageScreenshotNodeWithScore]] = pydantic.Field(
+        description="The image nodes retrieved by the pipeline for the given query."
+    )
+
+    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/composite_retrieved_text_node.py

@@ -0,0 +1,42 @@
+# 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 CompositeRetrievedTextNode(pydantic.BaseModel):
+    id: str = pydantic.Field(description="The ID of the retrieved node.")
+    retriever_id: str = pydantic.Field(description="The ID of the retriever this node was retrieved from.")
+    retriever_pipeline_name: str = pydantic.Field(
+        description="The name of the retrieval pipeline this node was retrieved from."
+    )
+    pipeline_id: str = pydantic.Field(description="The ID of the pipeline this node was retrieved from.")
+    metadata: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
+        description="Metadata associated with the retrieved node."
+    )
+    text: str = pydantic.Field(description="The text of the retrieved node.")
+    start_char_idx: typing.Optional[int]
+    end_char_idx: typing.Optional[int]
+
+    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/data_sink.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .configurable_data_sink_names import ConfigurableDataSinkNames
-from .data_sink_create_component import DataSinkCreateComponent
+from .data_sink_component import DataSinkComponent
 
 try:
     import pydantic
@@ -22,11 +22,11 @@ class DataSink(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
-    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
     name: str = pydantic.Field(description="The name of the data sink.")
     sink_type: ConfigurableDataSinkNames
-    component: DataSinkCreateComponent = pydantic.Field(description="Component that implements the data sink")
+    component: DataSinkComponent = pydantic.Field(description="Component that implements the data sink")
     project_id: str
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/data_sink_component.py

@@ -0,0 +1,20 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
+from .cloud_milvus_vector_store import CloudMilvusVectorStore
+from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
+from .cloud_pinecone_vector_store import CloudPineconeVectorStore
+from .cloud_postgres_vector_store import CloudPostgresVectorStore
+from .cloud_qdrant_vector_store import CloudQdrantVectorStore
+
+DataSinkComponent = typing.Union[
+    typing.Dict[str, typing.Any],
+    CloudPineconeVectorStore,
+    CloudPostgresVectorStore,
+    CloudQdrantVectorStore,
+    CloudAzureAiSearchVectorStore,
+    CloudMongoDbAtlasVectorSearch,
+    CloudMilvusVectorStore,
+]

llama_cloud/types/data_source.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .configurable_data_source_names import ConfigurableDataSourceNames
-from .data_source_create_component import DataSourceCreateComponent
+from .data_source_component import DataSourceComponent
 from .data_source_custom_metadata_value import DataSourceCustomMetadataValue
 
 try:
@@ -23,14 +23,12 @@ class DataSource(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
-    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
     name: str = pydantic.Field(description="The name of the data source.")
     source_type: ConfigurableDataSourceNames
-    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[DataSourceCustomMetadataValue]]] = 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")
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[DataSourceCustomMetadataValue]]]
+    component: DataSourceComponent = pydantic.Field(description="Component that implements the data source")
     project_id: str
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/data_source_component.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+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
+
+DataSourceComponent = typing.Union[
+    typing.Dict[str, typing.Any],
+    CloudS3DataSource,
+    CloudAzStorageBlobDataSource,
+    CloudGoogleDriveDataSource,
+    CloudOneDriveDataSource,
+    CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
+    CloudConfluenceDataSource,
+    CloudJiraDataSource,
+    CloudBoxDataSource,
+]

llama_cloud/types/data_source_create.py

@@ -24,9 +24,7 @@ class DataSourceCreate(pydantic.BaseModel):
 
     name: str = pydantic.Field(description="The name of the data source.")
     source_type: ConfigurableDataSourceNames
-    custom_metadata: typing.Optional[
-        typing.Dict[str, typing.Optional[DataSourceCreateCustomMetadataValue]]
-    ] = pydantic.Field(description="Custom metadata that will be present on all data loaded from the data source")
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[DataSourceCreateCustomMetadataValue]]]
     component: DataSourceCreateComponent = pydantic.Field(description="Component that implements the data source")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/edit_suggestion.py

@@ -0,0 +1,39 @@
+# 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 .report_block import ReportBlock
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class EditSuggestion(pydantic.BaseModel):
+    """
+    A suggestion for an edit to a report.
+    """
+
+    justification: str
+    start_line: int
+    end_line: int
+    blocks: typing.List[ReportBlock]
+
+    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/embedding_model_config.py

@@ -21,8 +21,8 @@ class EmbeddingModelConfig(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
-    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
     name: str = pydantic.Field(description="The name of the embedding model config.")
     embedding_config: EmbeddingModelConfigEmbeddingConfig = pydantic.Field(
         description="The embedding configuration for the embedding model config."

llama_cloud/types/embedding_model_config_update.py

@@ -16,10 +16,8 @@ except ImportError:
 
 
 class EmbeddingModelConfigUpdate(pydantic.BaseModel):
-    name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model config.")
-    embedding_config: typing.Optional[EmbeddingModelConfigUpdateEmbeddingConfig] = pydantic.Field(
-        description="The embedding configuration for the embedding model config."
-    )
+    name: typing.Optional[str]
+    embedding_config: typing.Optional[EmbeddingModelConfigUpdateEmbeddingConfig]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/eval_dataset.py

@@ -21,8 +21,8 @@ class EvalDataset(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
-    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
     name: str = pydantic.Field(description="The name of the EvalDataset.")
     project_id: str
 

llama_cloud/types/eval_dataset_job_record.py

@@ -28,27 +28,22 @@ class EvalDatasetJobRecord(pydantic.BaseModel):
     partitions: typing.Dict[str, str] = pydantic.Field(
         description="The partitions for this execution. Used for determining where to save job output."
     )
-    parameters: typing.Optional[EvalDatasetJobParams] = pydantic.Field(
-        description="Additional input parameters for the eval execution."
-    )
-    session_id: typing.Optional[str] = pydantic.Field(
-        description="The upstream request ID that created this job. Used for tracking the job across services."
-    )
-    correlation_id: typing.Optional[str] = pydantic.Field(
-        description="The correlation ID for this job. Used for tracking the job across services."
-    )
-    parent_job_execution_id: typing.Optional[str] = pydantic.Field(description="The ID of the parent job execution.")
-    user_id: typing.Optional[str] = pydantic.Field(description="The ID of the user that created this job")
+    parameters: typing.Optional[EvalDatasetJobParams]
+    session_id: typing.Optional[str]
+    correlation_id: typing.Optional[str]
+    parent_job_execution_id: typing.Optional[str]
+    user_id: typing.Optional[str]
     created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    project_id: typing.Optional[str]
     id: typing.Optional[str] = pydantic.Field(description="Unique identifier")
     status: StatusEnum
     error_code: typing.Optional[str]
     error_message: typing.Optional[str]
-    attempts: typing.Optional[int] = pydantic.Field(description="The number of times this job has been attempted")
+    attempts: typing.Optional[int]
     started_at: typing.Optional[dt.datetime]
     ended_at: typing.Optional[dt.datetime]
     updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
-    data: typing.Optional[Base] = pydantic.Field(description="Additional metadata for the job execution.")
+    data: typing.Optional[Base]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/eval_execution_params_override.py

@@ -20,12 +20,8 @@ class EvalExecutionParamsOverride(pydantic.BaseModel):
     Schema for the params override for an eval execution.
     """
 
-    llm_model: typing.Optional[SupportedLlmModelNames] = pydantic.Field(
-        description="The LLM model to use within eval execution."
-    )
-    qa_prompt_tmpl: typing.Optional[str] = pydantic.Field(
-        description="The template to use for the question answering prompt."
-    )
+    llm_model: typing.Optional[SupportedLlmModelNames]
+    qa_prompt_tmpl: 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/eval_question.py

@@ -16,8 +16,8 @@ except ImportError:
 
 class EvalQuestion(pydantic.BaseModel):
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
-    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
     content: str = pydantic.Field(description="The content of the question.")
     eval_dataset_id: str
     eval_dataset_index: int = pydantic.Field(

llama_cloud/types/extract_agent.py

@@ -0,0 +1,45 @@
+# 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 .extract_agent_data_schema_value import ExtractAgentDataSchemaValue
+from .extract_config import ExtractConfig
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtractAgent(pydantic.BaseModel):
+    """
+    Schema and configuration for creating an extraction agent.
+    """
+
+    id: str = pydantic.Field(description="The id of the extraction agent.")
+    name: str = pydantic.Field(description="The name of the extraction agent.")
+    project_id: str = pydantic.Field(description="The ID of the project that the extraction agent belongs to.")
+    data_schema: typing.Dict[str, typing.Optional[ExtractAgentDataSchemaValue]] = pydantic.Field(
+        description="The schema of the data."
+    )
+    config: ExtractConfig = pydantic.Field(description="The configuration parameters for the extraction agent.")
+    created_at: typing.Optional[dt.datetime]
+    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}
+        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/extract_agent_data_schema_value.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractAgentDataSchemaValue = typing.Union[typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool]

llama_cloud/types/extract_config.py

@@ -0,0 +1,40 @@
+# 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 .extract_mode import ExtractMode
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtractConfig(pydantic.BaseModel):
+    """
+    Additional parameters for the extraction agent.
+    """
+
+    extraction_mode: typing.Optional[ExtractMode] = pydantic.Field(description="The extraction mode specified.")
+    handle_missing: typing.Optional[bool] = pydantic.Field(
+        description="Whether to handle missing fields in the schema."
+    )
+    system_prompt: 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
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/extract_job.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 .file import File
+from .status_enum import StatusEnum
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtractJob(pydantic.BaseModel):
+    id: str = pydantic.Field(description="The id of the extraction job")
+    status: StatusEnum = pydantic.Field(description="The status of the extraction job")
+    file: File = pydantic.Field(description="The file that the extract was extracted from")
+
+    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}