llama-cloud 0.0.17__py3-none-any.whl → 0.1.0__py3-none-any.whl

llama_cloud/types/cloud_s_3_data_source.py

@@ -15,19 +15,11 @@ except ImportError:
 
 
 class CloudS3DataSource(pydantic.BaseModel):
-    """
-    Base component object to capture class names.
-    """
-
     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

@@ -15,15 +15,11 @@ except ImportError:
 
 
 class CloudSharepointDataSource(pydantic.BaseModel):
-    """
-    Base component object to capture class names.
-    """
-
-    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.")

llama_cloud/types/cloud_slack_data_source.py

@@ -15,17 +15,13 @@ except ImportError:
 
 
 class CloudSlackDataSource(pydantic.BaseModel):
-    """
-    Base component object to capture class names.
-    """
-
     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/cloud_weaviate_vector_store.py

@@ -15,10 +15,6 @@ except ImportError:
 
 
 class CloudWeaviateVectorStore(pydantic.BaseModel):
-    """
-    Base class for cloud vector stores.
-    """
-
     supports_nested_metadata_filters: typing.Optional[bool]
     index_name: str
     url: typing.Optional[str]

llama_cloud/types/code_splitter.py

@@ -26,7 +26,8 @@ class CodeSplitter(pydantic.BaseModel):
         description="Whether or not to consider metadata when splitting."
     )
     include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
+    callback_manager: typing.Optional[typing.Any]
+    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

@@ -21,15 +21,11 @@ class CohereEmbedding(pydantic.BaseModel):
 
     model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
-    num_workers: typing.Optional[int] = pydantic.Field(
-        description="The number of workers to use for async embedding calls."
-    )
+    callback_manager: typing.Optional[typing.Any]
+    num_workers: typing.Optional[int]
     api_key: str = pydantic.Field(description="The Cohere API key.")
     truncate: 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: str = pydantic.Field(
         description="Embedding type. If not provided float embedding_type is used when needed."
     )

llama_cloud/types/configurable_data_sink_names.py

@@ -7,10 +7,6 @@ T_Result = typing.TypeVar("T_Result")
 
 
 class ConfigurableDataSinkNames(str, enum.Enum):
-    """
-    An enumeration.
-    """
-
     CHROMA = "CHROMA"
     PINECONE = "PINECONE"
     POSTGRES = "POSTGRES"

llama_cloud/types/configurable_data_source_names.py

@@ -7,10 +7,6 @@ T_Result = typing.TypeVar("T_Result")
 
 
 class ConfigurableDataSourceNames(str, enum.Enum):
-    """
-    An enumeration.
-    """
-
     S_3 = "S3"
     AZURE_STORAGE_BLOB = "AZURE_STORAGE_BLOB"
     GOOGLE_DRIVE = "GOOGLE_DRIVE"

llama_cloud/types/configurable_transformation_names.py

@@ -7,10 +7,6 @@ T_Result = typing.TypeVar("T_Result")
 
 
 class ConfigurableTransformationNames(str, enum.Enum):
-    """
-    An enumeration.
-    """
-
     CHARACTER_SPLITTER = "CHARACTER_SPLITTER"
     PAGE_SPLITTER_NODE_PARSER = "PAGE_SPLITTER_NODE_PARSER"
     CODE_NODE_PARSER = "CODE_NODE_PARSER"

llama_cloud/types/configured_transformation_item_component.py

@@ -2,8 +2,35 @@
 
 import typing
 
-from .configured_transformation_item_component_one import ConfiguredTransformationItemComponentOne
+from .azure_open_ai_embedding import AzureOpenAiEmbedding
+from .bedrock_embedding import BedrockEmbedding
+from .character_splitter import CharacterSplitter
+from .code_splitter import CodeSplitter
+from .cohere_embedding import CohereEmbedding
+from .extend_vertex_text_embedding import ExtendVertexTextEmbedding
+from .gemini_embedding import GeminiEmbedding
+from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
+from .markdown_element_node_parser import MarkdownElementNodeParser
+from .markdown_node_parser import MarkdownNodeParser
+from .open_ai_embedding import OpenAiEmbedding
+from .page_splitter_node_parser import PageSplitterNodeParser
+from .sentence_splitter import SentenceSplitter
+from .token_text_splitter import TokenTextSplitter
 
 ConfiguredTransformationItemComponent = typing.Union[
-    typing.Dict[str, typing.Any], ConfiguredTransformationItemComponentOne
+    typing.Dict[str, typing.Any],
+    CharacterSplitter,
+    PageSplitterNodeParser,
+    CodeSplitter,
+    SentenceSplitter,
+    TokenTextSplitter,
+    MarkdownNodeParser,
+    MarkdownElementNodeParser,
+    OpenAiEmbedding,
+    AzureOpenAiEmbedding,
+    CohereEmbedding,
+    BedrockEmbedding,
+    HuggingFaceInferenceApiEmbedding,
+    GeminiEmbedding,
+    ExtendVertexTextEmbedding,
 ]

llama_cloud/types/data_sink.py

@@ -22,8 +22,8 @@ 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: DataSinkComponent

llama_cloud/types/data_sink_component.py

@@ -2,6 +2,23 @@
 
 import typing
 
-from .data_sink_component_one import DataSinkComponentOne
+from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
+from .cloud_chroma_vector_store import CloudChromaVectorStore
+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
+from .cloud_weaviate_vector_store import CloudWeaviateVectorStore
 
-DataSinkComponent = typing.Union[typing.Dict[str, typing.Any], DataSinkComponentOne]
+DataSinkComponent = typing.Union[
+    typing.Dict[str, typing.Any],
+    CloudChromaVectorStore,
+    CloudPineconeVectorStore,
+    CloudPostgresVectorStore,
+    CloudQdrantVectorStore,
+    CloudWeaviateVectorStore,
+    CloudAzureAiSearchVectorStore,
+    CloudMongoDbAtlasVectorSearch,
+    CloudMilvusVectorStore,
+]

llama_cloud/types/data_sink_create_component.py

@@ -2,6 +2,23 @@
 
 import typing
 
-from .data_sink_create_component_one import DataSinkCreateComponentOne
+from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
+from .cloud_chroma_vector_store import CloudChromaVectorStore
+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
+from .cloud_weaviate_vector_store import CloudWeaviateVectorStore
 
-DataSinkCreateComponent = typing.Union[typing.Dict[str, typing.Any], DataSinkCreateComponentOne]
+DataSinkCreateComponent = typing.Union[
+    typing.Dict[str, typing.Any],
+    CloudChromaVectorStore,
+    CloudPineconeVectorStore,
+    CloudPostgresVectorStore,
+    CloudQdrantVectorStore,
+    CloudWeaviateVectorStore,
+    CloudAzureAiSearchVectorStore,
+    CloudMongoDbAtlasVectorSearch,
+    CloudMilvusVectorStore,
+]

llama_cloud/types/data_source.py

@@ -23,13 +23,11 @@ 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, DataSourceCustomMetadataValue]] = 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[DataSourceCustomMetadataValue]]]
     component: DataSourceComponent
     project_id: str
 

llama_cloud/types/data_source_component.py

@@ -2,6 +2,27 @@
 
 import typing
 
-from .data_source_component_one import DataSourceComponentOne
+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], DataSourceComponentOne]
+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, 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
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/data_source_create_component.py

@@ -2,6 +2,27 @@
 
 import typing
 
-from .data_source_create_component_one import DataSourceCreateComponentOne
+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
 
-DataSourceCreateComponent = typing.Union[typing.Dict[str, typing.Any], DataSourceCreateComponentOne]
+DataSourceCreateComponent = typing.Union[
+    typing.Dict[str, typing.Any],
+    CloudS3DataSource,
+    CloudAzStorageBlobDataSource,
+    CloudGoogleDriveDataSource,
+    CloudOneDriveDataSource,
+    CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
+    CloudConfluenceDataSource,
+    CloudJiraDataSource,
+    CloudBoxDataSource,
+]

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 +28,21 @@ 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")
     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_metric.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class EvalMetric(str, enum.Enum):
+    RELEVANCY = "RELEVANCY"
+    FAITHFULNESS = "FAITHFULNESS"
+
+    def visit(self, relevancy: typing.Callable[[], T_Result], faithfulness: typing.Callable[[], T_Result]) -> T_Result:
+        if self is EvalMetric.RELEVANCY:
+            return relevancy()
+        if self is EvalMetric.FAITHFULNESS:
+            return faithfulness()

llama_cloud/types/eval_question.py

@@ -15,13 +15,9 @@ except ImportError:
 
 
 class EvalQuestion(pydantic.BaseModel):
-    """
-    Base schema model containing common database fields.
-    """
-
     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/extend_vertex_text_embedding.py

@@ -16,30 +16,18 @@ except ImportError:
 
 
 class ExtendVertexTextEmbedding(pydantic.BaseModel):
-    """
-    Base class for embeddings.
-    """
-
     model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
-    num_workers: typing.Optional[int] = pydantic.Field(
-        description="The number of workers to use for async embedding calls."
-    )
+    callback_manager: typing.Optional[typing.Any]
+    num_workers: typing.Optional[int]
     embed_mode: VertexEmbeddingMode = pydantic.Field(description="The embedding mode to use.")
     additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
         description="Additional kwargs for the Vertex."
     )
-    client_email: typing.Optional[str] = pydantic.Field(
-        description="The client email to use when making Vertex API calls."
-    )
-    token_uri: typing.Optional[str] = pydantic.Field(description="The token uri to use when making Vertex API calls.")
-    private_key_id: typing.Optional[str] = pydantic.Field(
-        description="The private key id to use when making Vertex API calls."
-    )
-    private_key: typing.Optional[str] = pydantic.Field(
-        description="The private key to use when making Vertex API calls."
-    )
+    client_email: typing.Optional[str]
+    token_uri: typing.Optional[str]
+    private_key_id: typing.Optional[str]
+    private_key: typing.Optional[str]
     project: str = pydantic.Field(description="The default GCP project to use when making Vertex API calls.")
     location: str = pydantic.Field(description="The default location to use when making API calls.")
     class_name: typing.Optional[str]

llama_cloud/types/extraction_result.py

@@ -22,10 +22,12 @@ class ExtractionResult(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]
     schema_id: str = pydantic.Field(description="The id of the schema")
-    data: typing.Dict[str, ExtractionResultDataValue] = pydantic.Field(description="The data extracted from the file")
+    data: typing.Dict[str, typing.Optional[ExtractionResultDataValue]] = pydantic.Field(
+        description="The data extracted from the file"
+    )
     file: File = pydantic.Field(description="The file that the extract was extracted from")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/extraction_schema.py

@@ -21,13 +21,11 @@ class ExtractionSchema(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 extraction schema")
     project_id: str = pydantic.Field(description="The ID of the project that the extraction schema belongs to")
-    data_schema: typing.Optional[typing.Dict[str, ExtractionSchemaDataSchemaValue]] = pydantic.Field(
-        description="The schema of the data"
-    )
+    data_schema: typing.Optional[typing.Dict[str, typing.Optional[ExtractionSchemaDataSchemaValue]]]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/file.py

@@ -21,19 +21,15 @@ class File(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
-    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.)")
+    file_size: typing.Optional[int]
+    file_type: typing.Optional[str]
     project_id: str = pydantic.Field(description="The ID of the project that the file belongs to")
-    last_modified_at: typing.Optional[dt.datetime] = pydantic.Field(description="The last modified time of the file")
-    resource_info: typing.Optional[typing.Dict[str, FileResourceInfoValue]] = pydantic.Field(
-        description="Resource information for the file"
-    )
-    data_source_id: typing.Optional[str] = pydantic.Field(
-        description="The ID of the data source that the file belongs to"
-    )
+    last_modified_at: typing.Optional[dt.datetime]
+    resource_info: typing.Optional[typing.Dict[str, typing.Optional[FileResourceInfoValue]]]
+    data_source_id: 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/gemini_embedding.py

@@ -29,15 +29,11 @@ class GeminiEmbedding(pydantic.BaseModel):
 
     model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
-    num_workers: typing.Optional[int] = pydantic.Field(
-        description="The number of workers to use for async embedding calls."
-    )
-    title: typing.Optional[str] = pydantic.Field(
-        description="Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid."
-    )
-    task_type: typing.Optional[str] = pydantic.Field(description="The task for embedding model.")
-    api_key: typing.Optional[str] = pydantic.Field(description="API key to access the model. Defaults to None.")
+    callback_manager: typing.Optional[typing.Any]
+    num_workers: typing.Optional[int]
+    title: typing.Optional[str]
+    task_type: typing.Optional[str]
+    api_key: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/hugging_face_inference_api_embedding.py

@@ -25,36 +25,20 @@ class HuggingFaceInferenceApiEmbedding(pydantic.BaseModel):
     - Uses the feature extraction task: https://huggingface.co/tasks/feature-extraction
     """
 
-    model_name: typing.Optional[str] = pydantic.Field(
-        description="Hugging Face model name. If None, the task will be used."
-    )
+    model_name: typing.Optional[str]
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
-    num_workers: typing.Optional[int] = pydantic.Field(
-        description="The number of workers to use for async embedding calls."
-    )
-    pooling: typing.Optional[Pooling] = pydantic.Field(
-        description="Pooling strategy. If None, the model's default pooling is used."
-    )
-    query_instruction: typing.Optional[str] = pydantic.Field(
-        description="Instruction to prepend during query embedding."
-    )
-    text_instruction: typing.Optional[str] = pydantic.Field(description="Instruction to prepend during text embedding.")
+    callback_manager: typing.Optional[typing.Any]
+    num_workers: typing.Optional[int]
+    pooling: typing.Optional[Pooling]
+    query_instruction: typing.Optional[str]
+    text_instruction: typing.Optional[str]
     token: typing.Optional[HuggingFaceInferenceApiEmbeddingToken] = pydantic.Field(
         description="Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server."
     )
-    timeout: typing.Optional[float] = pydantic.Field(
-        description="The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available."
-    )
-    headers: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
-        description="Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values."
-    )
-    cookies: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
-        description="Additional cookies to send to the server."
-    )
-    task: typing.Optional[str] = pydantic.Field(
-        description="Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None."
-    )
+    timeout: typing.Optional[float]
+    headers: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    cookies: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    task: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/input_message.py

@@ -20,12 +20,10 @@ class InputMessage(pydantic.BaseModel):
     This is distinct from a ChatMessage because this schema is enforced by the AI Chat library used in the frontend
     """
 
-    id: typing.Optional[str] = pydantic.Field(description="ID of the message, if any. Not necessarily a UUID.")
+    id: typing.Optional[str]
     role: MessageRole
     content: str
-    data: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
-        description="Additional data to be stored with the message."
-    )
+    data: typing.Optional[typing.Dict[str, typing.Any]]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str: