llama-cloud 0.0.1__py3-none-any.whl

llama_cloud/types/cloud_document_create.py

@@ -0,0 +1,36 @@
+# 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.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudDocumentCreate(pydantic.BaseModel):
+    """
+    Create a new cloud document.
+    """
+
+    text: str
+    metadata: typing.Dict[str, typing.Any]
+    excluded_embed_metadata_keys: typing.Optional[typing.List[str]]
+    excluded_llm_metadata_keys: typing.Optional[typing.List[str]]
+    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
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/cloud_gcs_data_source.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
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudGcsDataSource(pydantic.BaseModel):
+    """
+    Base component object to capture class names.
+    """
+
+    bucket: str = pydantic.Field(description="The name of the GCS bucket to read from.")
+    prefix: typing.Optional[str] = pydantic.Field(description="The prefix of the GCS objects to read from.")
+    service_account_key: typing.Dict[str, typing.Any] = pydantic.Field(
+        description="The service account key JSON to use for authentication."
+    )
+    class_name: 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/cloud_google_drive_data_source.py

@@ -0,0 +1,36 @@
+# 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.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudGoogleDriveDataSource(pydantic.BaseModel):
+    """
+    Base component object to capture class names.
+    """
+
+    folder_id: str = pydantic.Field(description="The ID of the Google Drive folder to read from.")
+    service_account_key: typing.Dict[str, typing.Any] = pydantic.Field(
+        description="The service account key JSON to use for authentication."
+    )
+    class_name: 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/cloud_one_drive_data_source.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
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudOneDriveDataSource(pydantic.BaseModel):
+    """
+    Base component object to capture class names.
+    """
+
+    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.")
+    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.")
+    class_name: 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/cloud_pinecone_vector_store.py

@@ -0,0 +1,46 @@
+# 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.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudPineconeVectorStore(pydantic.BaseModel):
+    """
+    Cloud Pinecone Vector Store.
+
+    This class is used to store the configuration for a Pinecone vector store, so that it can be
+    created and used in LlamaCloud.
+
+    Args:
+    api_key (str): API key for authenticating with Pinecone
+    index_name (str): name of the Pinecone index
+    namespace (optional[str]): namespace to use in the Pinecone index
+    insert_kwargs (optional[dict]): additional kwargs to pass during insertion
+    """
+
+    supports_nested_metadata_filters: typing.Optional[bool]
+    api_key: str
+    index_name: str
+    namespace: typing.Optional[str]
+    insert_kwargs: typing.Optional[typing.Dict[str, typing.Any]]
+    class_name: 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/cloud_postgres_vector_store.py

@@ -0,0 +1,44 @@
+# 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.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudPostgresVectorStore(pydantic.BaseModel):
+    """
+    Base class for cloud vector stores.
+    """
+
+    supports_nested_metadata_filters: typing.Optional[bool]
+    connection_string: str
+    async_connection_string: str
+    table_name: str
+    schema_name: str
+    embed_dim: int
+    hybrid_search: bool
+    text_search_config: str
+    cache_ok: bool
+    perform_setup: bool
+    debug: bool
+    use_jsonb: bool
+    class_name: 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/cloud_qdrant_vector_store.py

@@ -0,0 +1,48 @@
+# 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.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudQdrantVectorStore(pydantic.BaseModel):
+    """
+    Cloud Qdrant Vector Store.
+
+    This class is used to store the configuration for a Qdrant vector store, so that it can be
+    created and used in LlamaCloud.
+
+    Args:
+    collection_name (str): name of the Qdrant collection
+    url (str): url of the Qdrant instance
+    api_key (str): API key for authenticating with Qdrant
+    max_retries (int): maximum number of retries in case of a failure. Defaults to 3
+    client_kwargs (dict): additional kwargs to pass to the Qdrant client
+    """
+
+    supports_nested_metadata_filters: typing.Optional[bool]
+    collection_name: str
+    url: str
+    api_key: str
+    max_retries: typing.Optional[int]
+    client_kwargs: typing.Optional[typing.Dict[str, typing.Any]]
+    class_name: 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/cloud_s_3_data_source.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.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+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."
+    )
+    class_name: 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/cloud_sharepoint_data_source.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
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudSharepointDataSource(pydantic.BaseModel):
+    """
+    Base component object to capture class names.
+    """
+
+    site_name: str = pydantic.Field(description="The name 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.")
+    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.")
+    class_name: 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/cloud_weaviate_vector_store.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
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudWeaviateVectorStore(pydantic.BaseModel):
+    """
+    Base class for cloud vector stores.
+    """
+
+    supports_nested_metadata_filters: typing.Optional[bool]
+    index_name: str
+    url: typing.Optional[str]
+    text_key: str
+    auth_config: typing.Optional[typing.Dict[str, typing.Any]]
+    client_kwargs: typing.Optional[typing.Dict[str, typing.Any]]
+    class_name: 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/code_splitter.py

@@ -0,0 +1,46 @@
+# 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.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CodeSplitter(pydantic.BaseModel):
+    """
+    Split code using a AST parser.
+
+    Thank you to Kevin Lu / SweepAI for suggesting this elegant code splitting solution.
+    https://docs.sweep.dev/blogs/chunking-2m-files
+    """
+
+    include_metadata: typing.Optional[bool] = pydantic.Field(
+        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]]
+    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(
+        description="How many lines of code each chunk overlaps with."
+    )
+    max_chars: typing.Optional[int] = pydantic.Field(description="Maximum number of characters per chunk.")
+    class_name: 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/cohere_embedding.py

@@ -0,0 +1,46 @@
+# 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.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CohereEmbedding(pydantic.BaseModel):
+    """
+    CohereEmbedding uses the Cohere API to generate embeddings for text.
+    """
+
+    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."
+    )
+    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."
+    )
+    embedding_type: str = pydantic.Field(
+        description="Embedding type. If not provided float embedding_type is used when needed."
+    )
+    class_name: 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/configurable_data_sink_names.py

@@ -0,0 +1,37 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class ConfigurableDataSinkNames(str, enum.Enum):
+    """
+    An enumeration.
+    """
+
+    CHROMA = "CHROMA"
+    PINECONE = "PINECONE"
+    POSTGRES = "POSTGRES"
+    QDRANT = "QDRANT"
+    WEAVIATE = "WEAVIATE"
+
+    def visit(
+        self,
+        chroma: typing.Callable[[], T_Result],
+        pinecone: typing.Callable[[], T_Result],
+        postgres: typing.Callable[[], T_Result],
+        qdrant: typing.Callable[[], T_Result],
+        weaviate: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is ConfigurableDataSinkNames.CHROMA:
+            return chroma()
+        if self is ConfigurableDataSinkNames.PINECONE:
+            return pinecone()
+        if self is ConfigurableDataSinkNames.POSTGRES:
+            return postgres()
+        if self is ConfigurableDataSinkNames.QDRANT:
+            return qdrant()
+        if self is ConfigurableDataSinkNames.WEAVIATE:
+            return weaviate()

llama_cloud/types/configurable_data_source_names.py

@@ -0,0 +1,41 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class ConfigurableDataSourceNames(str, enum.Enum):
+    """
+    An enumeration.
+    """
+
+    S_3 = "S3"
+    AZURE_STORAGE_BLOB = "AZURE_STORAGE_BLOB"
+    GCS = "GCS"
+    GOOGLE_DRIVE = "GOOGLE_DRIVE"
+    MICROSOFT_ONEDRIVE = "MICROSOFT_ONEDRIVE"
+    MICROSOFT_SHAREPOINT = "MICROSOFT_SHAREPOINT"
+
+    def visit(
+        self,
+        s_3: typing.Callable[[], T_Result],
+        azure_storage_blob: typing.Callable[[], T_Result],
+        gcs: typing.Callable[[], T_Result],
+        google_drive: typing.Callable[[], T_Result],
+        microsoft_onedrive: typing.Callable[[], T_Result],
+        microsoft_sharepoint: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is ConfigurableDataSourceNames.S_3:
+            return s_3()
+        if self is ConfigurableDataSourceNames.AZURE_STORAGE_BLOB:
+            return azure_storage_blob()
+        if self is ConfigurableDataSourceNames.GCS:
+            return gcs()
+        if self is ConfigurableDataSourceNames.GOOGLE_DRIVE:
+            return google_drive()
+        if self is ConfigurableDataSourceNames.MICROSOFT_ONEDRIVE:
+            return microsoft_onedrive()
+        if self is ConfigurableDataSourceNames.MICROSOFT_SHAREPOINT:
+            return microsoft_sharepoint()

llama_cloud/types/configurable_transformation_definition.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 .configurable_transformation_names import ConfigurableTransformationNames
+from .transformation_category_names import TransformationCategoryNames
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ConfigurableTransformationDefinition(pydantic.BaseModel):
+    """
+    Schema for a transformation definition.
+    """
+
+    label: str = pydantic.Field(
+        description="The label field will be used to display the name of the component in the UI"
+    )
+    json_schema: typing.Dict[str, typing.Any] = pydantic.Field(
+        description="The json_schema field can be used by clients to determine how to construct the component"
+    )
+    configurable_transformation_type: ConfigurableTransformationNames = pydantic.Field(
+        description="The name field will act as the unique identifier of TransformationDefinition objects"
+    )
+    transformation_category: TransformationCategoryNames = pydantic.Field(
+        description="The transformation_category field will be used to group transformations in the UI"
+    )
+
+    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}