llama-cloud 0.0.1__py3-none-any.whl

llama_cloud/types/eval_dataset_job_record.py

@@ -0,0 +1,59 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+import typing_extensions
+
+from ..core.datetime_utils import serialize_datetime
+from .base import Base
+from .eval_dataset_job_params import EvalDatasetJobParams
+from .status_enum import StatusEnum
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class EvalDatasetJobRecord(pydantic.BaseModel):
+    """
+    Schema for job that evaluates an EvalDataset against a pipeline.
+    """
+
+    job_name: typing_extensions.Literal["eval_dataset_job"]
+    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.")
+    id: typing.Optional[str] = pydantic.Field(description="Unique identifier")
+    status: StatusEnum
+    error_message: typing.Optional[str]
+    attempts: typing.Optional[int] = pydantic.Field(description="The number of times this job has been attempted")
+    started_at: typing.Optional[dt.datetime]
+    ended_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")
+    data: typing.Optional[Base] = pydantic.Field(description="Additional metadata for the job execution.")
+
+    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/eval_execution_params.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 .supported_eval_llm_model_names import SupportedEvalLlmModelNames
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class EvalExecutionParams(pydantic.BaseModel):
+    """
+    Schema for the params for an eval execution.
+    """
+
+    llm_model: typing.Optional[SupportedEvalLlmModelNames] = 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."
+    )
+
+    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/eval_execution_params_override.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 .supported_eval_llm_model_names import SupportedEvalLlmModelNames
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class EvalExecutionParamsOverride(pydantic.BaseModel):
+    """
+    Schema for the params override for an eval execution.
+    """
+
+    llm_model: typing.Optional[SupportedEvalLlmModelNames] = 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."
+    )
+
+    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/eval_llm_model_data.py

@@ -0,0 +1,33 @@
+# 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 EvalLlmModelData(pydantic.BaseModel):
+    """
+    Schema for an eval LLM model.
+    """
+
+    name: str = pydantic.Field(description="The name of the LLM model.")
+    description: str = pydantic.Field(description="The description of the LLM model.")
+
+    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/eval_question.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
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+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")
+    content: str = pydantic.Field(description="The content of the question.")
+    eval_dataset_id: str
+    eval_dataset_index: int = pydantic.Field(
+        description="The index at which this question is positioned relative to the other questions in the linked EvalDataset. Client is responsible for setting this correctly."
+    )
+
+    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/eval_question_create.py

@@ -0,0 +1,28 @@
+# 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 EvalQuestionCreate(pydantic.BaseModel):
+    content: str = pydantic.Field(description="The content of the question.")
+
+    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/eval_question_result.py

@@ -0,0 +1,49 @@
+# 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 .eval_execution_params import EvalExecutionParams
+from .metric_result import MetricResult
+from .text_node import TextNode
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class EvalQuestionResult(pydantic.BaseModel):
+    """
+    Schema for the result of an eval question job.
+    """
+
+    eval_question_id: str = pydantic.Field(description="The ID of the question that was executed.")
+    pipeline_id: str = pydantic.Field(description="The ID of the pipeline that the question was executed against.")
+    source_nodes: typing.List[TextNode] = pydantic.Field(
+        description="The nodes retrieved by the pipeline for the given question."
+    )
+    answer: str = pydantic.Field(description="The answer to the question.")
+    eval_metrics: typing.Dict[str, MetricResult] = pydantic.Field(description="The eval metrics for the question.")
+    eval_dataset_execution_id: str = pydantic.Field(
+        description="The ID of the EvalDatasetJobRecord that this result was generated from."
+    )
+    eval_dataset_execution_params: EvalExecutionParams = pydantic.Field(
+        description="The EvalExecutionParams that were used when this result was generated."
+    )
+    eval_finished_at: dt.datetime = pydantic.Field(description="The timestamp when the eval finished.")
+    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/file.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
+from .file_resource_info_value import FileResourceInfoValue
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class File(pydantic.BaseModel):
+    """
+    Schema for a file.
+    """
+
+    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")
+    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.)")
+    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"
+    )
+
+    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/file_resource_info_value.py

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

llama_cloud/types/filter_condition.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 FilterCondition(str, enum.Enum):
+    """
+    Vector store filter conditions to combine different filters.
+    """
+
+    AND = "and"
+    OR = "or"
+
+    def visit(self, and_: typing.Callable[[], T_Result], or_: typing.Callable[[], T_Result]) -> T_Result:
+        if self is FilterCondition.AND:
+            return and_()
+        if self is FilterCondition.OR:
+            return or_()

llama_cloud/types/filter_operator.py

@@ -0,0 +1,65 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class FilterOperator(str, enum.Enum):
+    """
+    Vector store filter operator.
+    """
+
+    EQUAL_TO = "=="
+    GREATER_THAN = ">"
+    LESS_THAN = "<"
+    NOT_EQUALS = "!="
+    GREATER_THAN_OR_EQUAL_TO = ">="
+    LESS_THAN_OR_EQUAL_TO = "<="
+    IN = "in"
+    NIN = "nin"
+    ANY = "any"
+    ALL = "all"
+    TEXT_MATCH = "text_match"
+    CONTAINS = "contains"
+
+    def visit(
+        self,
+        equal_to: typing.Callable[[], T_Result],
+        greater_than: typing.Callable[[], T_Result],
+        less_than: typing.Callable[[], T_Result],
+        not_equals: typing.Callable[[], T_Result],
+        greater_than_or_equal_to: typing.Callable[[], T_Result],
+        less_than_or_equal_to: typing.Callable[[], T_Result],
+        in_: typing.Callable[[], T_Result],
+        nin: typing.Callable[[], T_Result],
+        any: typing.Callable[[], T_Result],
+        all: typing.Callable[[], T_Result],
+        text_match: typing.Callable[[], T_Result],
+        contains: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is FilterOperator.EQUAL_TO:
+            return equal_to()
+        if self is FilterOperator.GREATER_THAN:
+            return greater_than()
+        if self is FilterOperator.LESS_THAN:
+            return less_than()
+        if self is FilterOperator.NOT_EQUALS:
+            return not_equals()
+        if self is FilterOperator.GREATER_THAN_OR_EQUAL_TO:
+            return greater_than_or_equal_to()
+        if self is FilterOperator.LESS_THAN_OR_EQUAL_TO:
+            return less_than_or_equal_to()
+        if self is FilterOperator.IN:
+            return in_()
+        if self is FilterOperator.NIN:
+            return nin()
+        if self is FilterOperator.ANY:
+            return any()
+        if self is FilterOperator.ALL:
+            return all()
+        if self is FilterOperator.TEXT_MATCH:
+            return text_match()
+        if self is FilterOperator.CONTAINS:
+            return contains()

llama_cloud/types/gemini_embedding.py

@@ -0,0 +1,51 @@
+# 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 GeminiEmbedding(pydantic.BaseModel):
+    """
+    Google Gemini embeddings.
+
+    Args:
+    model_name (str): Model for embedding.
+    Defaults to "models/embedding-001".
+
+        api_key (Optional[str]): API key to access the model. Defaults to None.
+        api_base (Optional[str]): API base to access the model. Defaults to Official Base.
+        transport (Optional[str]): Transport to access the model.
+    """
+
+    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.")
+    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/html_node_parser.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 HtmlNodeParser(pydantic.BaseModel):
+    """
+    HTML node parser.
+
+    Splits a document into Nodes using custom HTML splitting logic.
+
+    Args:
+    include_metadata (bool): whether to include metadata in nodes
+    include_prev_next_rel (bool): whether to include prev/next relationships
+    """
+
+    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]]
+    tags: typing.Optional[typing.List[str]] = pydantic.Field(description="HTML tags to extract text from.")
+    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/http_validation_error.py

@@ -0,0 +1,29 @@
+# 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 .validation_error import ValidationError
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class HttpValidationError(pydantic.BaseModel):
+    detail: typing.Optional[typing.List[ValidationError]]
+
+    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/hugging_face_inference_api_embedding.py

@@ -0,0 +1,68 @@
+# 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 .hugging_face_inference_api_embedding_token import HuggingFaceInferenceApiEmbeddingToken
+from .pooling import Pooling
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class HuggingFaceInferenceApiEmbedding(pydantic.BaseModel):
+    """
+    Wrapper on the Hugging Face's Inference API for embeddings.
+
+    Overview of the design:
+
+    - 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."
+    )
+    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.")
+    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."
+    )
+    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/hugging_face_inference_api_embedding_token.py

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