llama-cloud 0.1.41__py3-none-any.whl → 1.0.0b4__py3-none-any.whl

llama_cloud/types/project_create.py

@@ -1,35 +0,0 @@
-# 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 ProjectCreate(pydantic.BaseModel):
-    """
-    Schema for creating a project.
-    """
-
-    name: 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/prompt_conf.py

@@ -1,38 +0,0 @@
-# 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 PromptConf(pydantic.BaseModel):
-    system_prompt: typing.Optional[str] = pydantic.Field(description="The system prompt to use for the extraction.")
-    extraction_prompt: typing.Optional[str] = pydantic.Field(description="The prompt to use for the extraction.")
-    error_handling_prompt: typing.Optional[str] = pydantic.Field(description="The prompt to use for error handling.")
-    reasoning_prompt: typing.Optional[str] = pydantic.Field(description="The prompt to use for reasoning.")
-    cite_sources_prompt: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
-        description="The prompt to use for citing sources."
-    )
-    scratchpad_prompt: typing.Optional[str] = pydantic.Field(description="The prompt to use for scratchpad.")
-
-    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/public_model_name.py

@@ -1,97 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import enum
-import typing
-
-T_Result = typing.TypeVar("T_Result")
-
-
-class PublicModelName(str, enum.Enum):
-    OPENAI_GPT_4_O = "openai-gpt-4o"
-    OPENAI_GPT_4_O_MINI = "openai-gpt-4o-mini"
-    OPENAI_GPT_41 = "openai-gpt-4-1"
-    OPENAI_GPT_41_MINI = "openai-gpt-4-1-mini"
-    OPENAI_GPT_41_NANO = "openai-gpt-4-1-nano"
-    OPENAI_GPT_5 = "openai-gpt-5"
-    OPENAI_GPT_5_MINI = "openai-gpt-5-mini"
-    OPENAI_GPT_5_NANO = "openai-gpt-5-nano"
-    OPENAI_TEXT_EMBEDDING_3_SMALL = "openai-text-embedding-3-small"
-    OPENAI_TEXT_EMBEDDING_3_LARGE = "openai-text-embedding-3-large"
-    OPENAI_WHISPER_1 = "openai-whisper-1"
-    ANTHROPIC_SONNET_35 = "anthropic-sonnet-3.5"
-    ANTHROPIC_SONNET_35_V_2 = "anthropic-sonnet-3.5-v2"
-    ANTHROPIC_SONNET_37 = "anthropic-sonnet-3.7"
-    ANTHROPIC_SONNET_40 = "anthropic-sonnet-4.0"
-    GEMINI_25_FLASH = "gemini-2.5-flash"
-    GEMINI_25_PRO = "gemini-2.5-pro"
-    GEMINI_20_FLASH = "gemini-2.0-flash"
-    GEMINI_20_FLASH_LITE = "gemini-2.0-flash-lite"
-    GEMINI_15_FLASH = "gemini-1.5-flash"
-    GEMINI_15_PRO = "gemini-1.5-pro"
-
-    def visit(
-        self,
-        openai_gpt_4_o: typing.Callable[[], T_Result],
-        openai_gpt_4_o_mini: typing.Callable[[], T_Result],
-        openai_gpt_41: typing.Callable[[], T_Result],
-        openai_gpt_41_mini: typing.Callable[[], T_Result],
-        openai_gpt_41_nano: typing.Callable[[], T_Result],
-        openai_gpt_5: typing.Callable[[], T_Result],
-        openai_gpt_5_mini: typing.Callable[[], T_Result],
-        openai_gpt_5_nano: typing.Callable[[], T_Result],
-        openai_text_embedding_3_small: typing.Callable[[], T_Result],
-        openai_text_embedding_3_large: typing.Callable[[], T_Result],
-        openai_whisper_1: typing.Callable[[], T_Result],
-        anthropic_sonnet_35: typing.Callable[[], T_Result],
-        anthropic_sonnet_35_v_2: typing.Callable[[], T_Result],
-        anthropic_sonnet_37: typing.Callable[[], T_Result],
-        anthropic_sonnet_40: typing.Callable[[], T_Result],
-        gemini_25_flash: typing.Callable[[], T_Result],
-        gemini_25_pro: typing.Callable[[], T_Result],
-        gemini_20_flash: typing.Callable[[], T_Result],
-        gemini_20_flash_lite: typing.Callable[[], T_Result],
-        gemini_15_flash: typing.Callable[[], T_Result],
-        gemini_15_pro: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is PublicModelName.OPENAI_GPT_4_O:
-            return openai_gpt_4_o()
-        if self is PublicModelName.OPENAI_GPT_4_O_MINI:
-            return openai_gpt_4_o_mini()
-        if self is PublicModelName.OPENAI_GPT_41:
-            return openai_gpt_41()
-        if self is PublicModelName.OPENAI_GPT_41_MINI:
-            return openai_gpt_41_mini()
-        if self is PublicModelName.OPENAI_GPT_41_NANO:
-            return openai_gpt_41_nano()
-        if self is PublicModelName.OPENAI_GPT_5:
-            return openai_gpt_5()
-        if self is PublicModelName.OPENAI_GPT_5_MINI:
-            return openai_gpt_5_mini()
-        if self is PublicModelName.OPENAI_GPT_5_NANO:
-            return openai_gpt_5_nano()
-        if self is PublicModelName.OPENAI_TEXT_EMBEDDING_3_SMALL:
-            return openai_text_embedding_3_small()
-        if self is PublicModelName.OPENAI_TEXT_EMBEDDING_3_LARGE:
-            return openai_text_embedding_3_large()
-        if self is PublicModelName.OPENAI_WHISPER_1:
-            return openai_whisper_1()
-        if self is PublicModelName.ANTHROPIC_SONNET_35:
-            return anthropic_sonnet_35()
-        if self is PublicModelName.ANTHROPIC_SONNET_35_V_2:
-            return anthropic_sonnet_35_v_2()
-        if self is PublicModelName.ANTHROPIC_SONNET_37:
-            return anthropic_sonnet_37()
-        if self is PublicModelName.ANTHROPIC_SONNET_40:
-            return anthropic_sonnet_40()
-        if self is PublicModelName.GEMINI_25_FLASH:
-            return gemini_25_flash()
-        if self is PublicModelName.GEMINI_25_PRO:
-            return gemini_25_pro()
-        if self is PublicModelName.GEMINI_20_FLASH:
-            return gemini_20_flash()
-        if self is PublicModelName.GEMINI_20_FLASH_LITE:
-            return gemini_20_flash_lite()
-        if self is PublicModelName.GEMINI_15_FLASH:
-            return gemini_15_flash()
-        if self is PublicModelName.GEMINI_15_PRO:
-            return gemini_15_pro()

llama_cloud/types/quota_configuration.py

@@ -1,53 +0,0 @@
-# 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 .quota_configuration_configuration_type import QuotaConfigurationConfigurationType
-from .quota_configuration_status import QuotaConfigurationStatus
-from .quota_rate_limit_configuration_value import QuotaRateLimitConfigurationValue
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class QuotaConfiguration(pydantic.BaseModel):
-    """
-    Full quota configuration model.
-    """
-
-    source_type: typing_extensions.Literal["organization"]
-    source_id: str = pydantic.Field(description="The source ID, e.g. the organization ID")
-    configuration_type: QuotaConfigurationConfigurationType = pydantic.Field(description="The quota configuration type")
-    configuration_value: QuotaRateLimitConfigurationValue = pydantic.Field(description="The quota configuration value")
-    configuration_metadata: typing.Optional[typing.Dict[str, typing.Any]]
-    started_at: typing.Optional[dt.datetime] = pydantic.Field(description="The start date of the quota")
-    ended_at: typing.Optional[dt.datetime]
-    idempotency_key: typing.Optional[str]
-    status: QuotaConfigurationStatus = pydantic.Field(
-        description="The status of the quota, i.e. 'ACTIVE' or 'INACTIVE'"
-    )
-    id: typing.Optional[str]
-    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/quota_configuration_configuration_type.py

@@ -1,33 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import enum
-import typing
-
-T_Result = typing.TypeVar("T_Result")
-
-
-class QuotaConfigurationConfigurationType(str, enum.Enum):
-    """
-    The quota configuration type
-    """
-
-    RATE_LIMIT_PARSE_CONCURRENT_PREMIUM = "rate_limit_parse_concurrent_premium"
-    RATE_LIMIT_PARSE_CONCURRENT_DEFAULT = "rate_limit_parse_concurrent_default"
-    RATE_LIMIT_CONCURRENT_JOBS_IN_EXECUTION_DEFAULT = "rate_limit_concurrent_jobs_in_execution_default"
-    RATE_LIMIT_CONCURRENT_JOBS_IN_EXECUTION_DOC_INGEST = "rate_limit_concurrent_jobs_in_execution_doc_ingest"
-
-    def visit(
-        self,
-        rate_limit_parse_concurrent_premium: typing.Callable[[], T_Result],
-        rate_limit_parse_concurrent_default: typing.Callable[[], T_Result],
-        rate_limit_concurrent_jobs_in_execution_default: typing.Callable[[], T_Result],
-        rate_limit_concurrent_jobs_in_execution_doc_ingest: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is QuotaConfigurationConfigurationType.RATE_LIMIT_PARSE_CONCURRENT_PREMIUM:
-            return rate_limit_parse_concurrent_premium()
-        if self is QuotaConfigurationConfigurationType.RATE_LIMIT_PARSE_CONCURRENT_DEFAULT:
-            return rate_limit_parse_concurrent_default()
-        if self is QuotaConfigurationConfigurationType.RATE_LIMIT_CONCURRENT_JOBS_IN_EXECUTION_DEFAULT:
-            return rate_limit_concurrent_jobs_in_execution_default()
-        if self is QuotaConfigurationConfigurationType.RATE_LIMIT_CONCURRENT_JOBS_IN_EXECUTION_DOC_INGEST:
-            return rate_limit_concurrent_jobs_in_execution_doc_ingest()

llama_cloud/types/quota_configuration_status.py

@@ -1,21 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import enum
-import typing
-
-T_Result = typing.TypeVar("T_Result")
-
-
-class QuotaConfigurationStatus(str, enum.Enum):
-    """
-    The status of the quota, i.e. 'ACTIVE' or 'INACTIVE'
-    """
-
-    ACTIVE = "ACTIVE"
-    INACTIVE = "INACTIVE"
-
-    def visit(self, active: typing.Callable[[], T_Result], inactive: typing.Callable[[], T_Result]) -> T_Result:
-        if self is QuotaConfigurationStatus.ACTIVE:
-            return active()
-        if self is QuotaConfigurationStatus.INACTIVE:
-            return inactive()

llama_cloud/types/quota_rate_limit_configuration_value.py

@@ -1,38 +0,0 @@
-# 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 .quota_rate_limit_configuration_value_denominator_units import QuotaRateLimitConfigurationValueDenominatorUnits
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class QuotaRateLimitConfigurationValue(pydantic.BaseModel):
-    """
-    Quota-specific wrapper for default rate limit configuration.
-    """
-
-    numerator: int = pydantic.Field(description="The rate numerator")
-    denominator: typing.Optional[int]
-    denominator_units: typing.Optional[QuotaRateLimitConfigurationValueDenominatorUnits]
-
-    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/quota_rate_limit_configuration_value_denominator_units.py

@@ -1,29 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import enum
-import typing
-
-T_Result = typing.TypeVar("T_Result")
-
-
-class QuotaRateLimitConfigurationValueDenominatorUnits(str, enum.Enum):
-    SECOND = "second"
-    MINUTE = "minute"
-    HOUR = "hour"
-    DAY = "day"
-
-    def visit(
-        self,
-        second: typing.Callable[[], T_Result],
-        minute: typing.Callable[[], T_Result],
-        hour: typing.Callable[[], T_Result],
-        day: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is QuotaRateLimitConfigurationValueDenominatorUnits.SECOND:
-            return second()
-        if self is QuotaRateLimitConfigurationValueDenominatorUnits.MINUTE:
-            return minute()
-        if self is QuotaRateLimitConfigurationValueDenominatorUnits.HOUR:
-            return hour()
-        if self is QuotaRateLimitConfigurationValueDenominatorUnits.DAY:
-            return day()

llama_cloud/types/re_rank_config.py

@@ -1,35 +0,0 @@
-# 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 .re_ranker_type import ReRankerType
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class ReRankConfig(pydantic.BaseModel):
-    top_n: typing.Optional[int] = pydantic.Field(
-        description="The number of nodes to retrieve after reranking over retrieved nodes from all retrieval tools."
-    )
-    type: typing.Optional[ReRankerType] = pydantic.Field(description="The type of reranker to use.")
-
-    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/re_ranker_type.py

@@ -1,41 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import enum
-import typing
-
-T_Result = typing.TypeVar("T_Result")
-
-
-class ReRankerType(str, enum.Enum):
-    """
-    Enum for the reranker type.
-    """
-
-    SYSTEM_DEFAULT = "system_default"
-    LLM = "llm"
-    COHERE = "cohere"
-    BEDROCK = "bedrock"
-    SCORE = "score"
-    DISABLED = "disabled"
-
-    def visit(
-        self,
-        system_default: typing.Callable[[], T_Result],
-        llm: typing.Callable[[], T_Result],
-        cohere: typing.Callable[[], T_Result],
-        bedrock: typing.Callable[[], T_Result],
-        score: typing.Callable[[], T_Result],
-        disabled: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is ReRankerType.SYSTEM_DEFAULT:
-            return system_default()
-        if self is ReRankerType.LLM:
-            return llm()
-        if self is ReRankerType.COHERE:
-            return cohere()
-        if self is ReRankerType.BEDROCK:
-            return bedrock()
-        if self is ReRankerType.SCORE:
-            return score()
-        if self is ReRankerType.DISABLED:
-            return disabled()

llama_cloud/types/recurring_credit_grant.py

@@ -1,44 +0,0 @@
-# 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 .credit_type import CreditType
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class RecurringCreditGrant(pydantic.BaseModel):
-    name: str
-    credit_amount: int
-    credit_type: CreditType
-    product_id: str = pydantic.Field(
-        description="The ID of the product in Metronome used to represent the credit grant"
-    )
-    priority: float
-    rollover_fraction: float = pydantic.Field(
-        description="The fraction of the credit that will roll over to the next period, between 0 and 1"
-    )
-    periods_duration: typing.Optional[float] = pydantic.Field(
-        description="How many billing periods the credit grant will last for"
-    )
-
-    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/related_node_info.py

@@ -1,36 +0,0 @@
-# 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 .related_node_info_node_type import RelatedNodeInfoNodeType
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class RelatedNodeInfo(pydantic.BaseModel):
-    node_id: str
-    node_type: typing.Optional[RelatedNodeInfoNodeType]
-    metadata: typing.Optional[typing.Dict[str, typing.Any]]
-    hash: typing.Optional[str]
-    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/related_node_info_node_type.py

@@ -1,7 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-from .object_type import ObjectType
-
-RelatedNodeInfoNodeType = typing.Union[ObjectType, str]

llama_cloud/types/retrieve_results.py

@@ -1,56 +0,0 @@
-# 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 .metadata_filters import MetadataFilters
-from .page_figure_node_with_score import PageFigureNodeWithScore
-from .page_screenshot_node_with_score import PageScreenshotNodeWithScore
-from .text_node_with_score import TextNodeWithScore
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class RetrieveResults(pydantic.BaseModel):
-    """
-    Schema for the result of an retrieval execution.
-    """
-
-    pipeline_id: str = pydantic.Field(description="The ID of the pipeline that the query was retrieved against.")
-    retrieval_nodes: typing.List[TextNodeWithScore] = pydantic.Field(
-        description="The nodes retrieved by the pipeline for the given query."
-    )
-    image_nodes: typing.Optional[typing.List[PageScreenshotNodeWithScore]] = pydantic.Field(
-        description="The image nodes retrieved by the pipeline for the given query. Deprecated - will soon be replaced with 'page_screenshot_nodes'."
-    )
-    page_figure_nodes: typing.Optional[typing.List[PageFigureNodeWithScore]] = pydantic.Field(
-        description="The page figure nodes retrieved by the pipeline for the given query."
-    )
-    retrieval_latency: typing.Optional[typing.Dict[str, float]] = pydantic.Field(
-        description="The end-to-end latency for retrieval and reranking."
-    )
-    metadata: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
-        description="Metadata associated with the retrieval execution"
-    )
-    inferred_search_filters: typing.Optional[MetadataFilters]
-    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/retriever_create.py

@@ -1,37 +0,0 @@
-# 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 .retriever_pipeline import RetrieverPipeline
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class RetrieverCreate(pydantic.BaseModel):
-    name: str = pydantic.Field(
-        description="A name for the retriever tool. Will default to the pipeline name if not provided."
-    )
-    pipelines: typing.Optional[typing.List[RetrieverPipeline]] = pydantic.Field(
-        description="The pipelines this retriever uses."
-    )
-
-    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/role.py

@@ -1,40 +0,0 @@
-# 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 .permission import Permission
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class Role(pydantic.BaseModel):
-    """
-    Schema for a role.
-    """
-
-    id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
-    name: str = pydantic.Field(description="A name for the role.")
-    permissions: typing.List[Permission] = pydantic.Field(description="The actual permissions of the role.")
-
-    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}