llama-cloud 0.0.1__py3-none-any.whl

llama_cloud/types/json_node_parser.py

@@ -0,0 +1,43 @@
+# 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 JsonNodeParser(pydantic.BaseModel):
+    """
+    JSON node parser.
+
+    Splits a document into Nodes using custom JSON 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]]
+    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/llama_parse_supported_file_extensions.py

@@ -0,0 +1,161 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class LlamaParseSupportedFileExtensions(str, enum.Enum):
+    """
+    An enumeration.
+    """
+
+    PDF = ".pdf"
+    DOC = ".doc"
+    DOCX = ".docx"
+    DOCM = ".docm"
+    DOT = ".dot"
+    DOTX = ".dotx"
+    DOTM = ".dotm"
+    RTF = ".rtf"
+    WPS = ".wps"
+    WPD = ".wpd"
+    SXW = ".sxw"
+    STW = ".stw"
+    SXG = ".sxg"
+    PAGES = ".pages"
+    MW = ".mw"
+    MCW = ".mcw"
+    UOT = ".uot"
+    UOF = ".uof"
+    UOS = ".uos"
+    UOP = ".uop"
+    PPT = ".ppt"
+    PPTX = ".pptx"
+    POT = ".pot"
+    PPTM = ".pptm"
+    POTX = ".potx"
+    POTM = ".potm"
+    KEY = ".key"
+    ODP = ".odp"
+    ODG = ".odg"
+    OTP = ".otp"
+    FOPD = ".fopd"
+    SXI = ".sxi"
+    STI = ".sti"
+    EPUB = ".epub"
+    HTML = ".html"
+    HTM = ".htm"
+
+    def visit(
+        self,
+        pdf: typing.Callable[[], T_Result],
+        doc: typing.Callable[[], T_Result],
+        docx: typing.Callable[[], T_Result],
+        docm: typing.Callable[[], T_Result],
+        dot: typing.Callable[[], T_Result],
+        dotx: typing.Callable[[], T_Result],
+        dotm: typing.Callable[[], T_Result],
+        rtf: typing.Callable[[], T_Result],
+        wps: typing.Callable[[], T_Result],
+        wpd: typing.Callable[[], T_Result],
+        sxw: typing.Callable[[], T_Result],
+        stw: typing.Callable[[], T_Result],
+        sxg: typing.Callable[[], T_Result],
+        pages: typing.Callable[[], T_Result],
+        mw: typing.Callable[[], T_Result],
+        mcw: typing.Callable[[], T_Result],
+        uot: typing.Callable[[], T_Result],
+        uof: typing.Callable[[], T_Result],
+        uos: typing.Callable[[], T_Result],
+        uop: typing.Callable[[], T_Result],
+        ppt: typing.Callable[[], T_Result],
+        pptx: typing.Callable[[], T_Result],
+        pot: typing.Callable[[], T_Result],
+        pptm: typing.Callable[[], T_Result],
+        potx: typing.Callable[[], T_Result],
+        potm: typing.Callable[[], T_Result],
+        key: typing.Callable[[], T_Result],
+        odp: typing.Callable[[], T_Result],
+        odg: typing.Callable[[], T_Result],
+        otp: typing.Callable[[], T_Result],
+        fopd: typing.Callable[[], T_Result],
+        sxi: typing.Callable[[], T_Result],
+        sti: typing.Callable[[], T_Result],
+        epub: typing.Callable[[], T_Result],
+        html: typing.Callable[[], T_Result],
+        htm: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is LlamaParseSupportedFileExtensions.PDF:
+            return pdf()
+        if self is LlamaParseSupportedFileExtensions.DOC:
+            return doc()
+        if self is LlamaParseSupportedFileExtensions.DOCX:
+            return docx()
+        if self is LlamaParseSupportedFileExtensions.DOCM:
+            return docm()
+        if self is LlamaParseSupportedFileExtensions.DOT:
+            return dot()
+        if self is LlamaParseSupportedFileExtensions.DOTX:
+            return dotx()
+        if self is LlamaParseSupportedFileExtensions.DOTM:
+            return dotm()
+        if self is LlamaParseSupportedFileExtensions.RTF:
+            return rtf()
+        if self is LlamaParseSupportedFileExtensions.WPS:
+            return wps()
+        if self is LlamaParseSupportedFileExtensions.WPD:
+            return wpd()
+        if self is LlamaParseSupportedFileExtensions.SXW:
+            return sxw()
+        if self is LlamaParseSupportedFileExtensions.STW:
+            return stw()
+        if self is LlamaParseSupportedFileExtensions.SXG:
+            return sxg()
+        if self is LlamaParseSupportedFileExtensions.PAGES:
+            return pages()
+        if self is LlamaParseSupportedFileExtensions.MW:
+            return mw()
+        if self is LlamaParseSupportedFileExtensions.MCW:
+            return mcw()
+        if self is LlamaParseSupportedFileExtensions.UOT:
+            return uot()
+        if self is LlamaParseSupportedFileExtensions.UOF:
+            return uof()
+        if self is LlamaParseSupportedFileExtensions.UOS:
+            return uos()
+        if self is LlamaParseSupportedFileExtensions.UOP:
+            return uop()
+        if self is LlamaParseSupportedFileExtensions.PPT:
+            return ppt()
+        if self is LlamaParseSupportedFileExtensions.PPTX:
+            return pptx()
+        if self is LlamaParseSupportedFileExtensions.POT:
+            return pot()
+        if self is LlamaParseSupportedFileExtensions.PPTM:
+            return pptm()
+        if self is LlamaParseSupportedFileExtensions.POTX:
+            return potx()
+        if self is LlamaParseSupportedFileExtensions.POTM:
+            return potm()
+        if self is LlamaParseSupportedFileExtensions.KEY:
+            return key()
+        if self is LlamaParseSupportedFileExtensions.ODP:
+            return odp()
+        if self is LlamaParseSupportedFileExtensions.ODG:
+            return odg()
+        if self is LlamaParseSupportedFileExtensions.OTP:
+            return otp()
+        if self is LlamaParseSupportedFileExtensions.FOPD:
+            return fopd()
+        if self is LlamaParseSupportedFileExtensions.SXI:
+            return sxi()
+        if self is LlamaParseSupportedFileExtensions.STI:
+            return sti()
+        if self is LlamaParseSupportedFileExtensions.EPUB:
+            return epub()
+        if self is LlamaParseSupportedFileExtensions.HTML:
+            return html()
+        if self is LlamaParseSupportedFileExtensions.HTM:
+            return htm()

llama_cloud/types/llm.py

@@ -0,0 +1,55 @@
+# 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 .base_prompt_template import BasePromptTemplate
+from .pydantic_program_mode import PydanticProgramMode
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class Llm(pydantic.BaseModel):
+    """
+    The LLM class is the main class for interacting with language models.
+
+    Attributes:
+    system_prompt (Optional[str]):
+    System prompt for LLM calls.
+    messages_to_prompt (Callable):
+    Function to convert a list of messages to an LLM prompt.
+    completion_to_prompt (Callable):
+    Function to convert a completion to an LLM prompt.
+    output_parser (Optional[BaseOutputParser]):
+    Output parser to parse, validate, and correct errors programmatically.
+    pydantic_program_mode (PydanticProgramMode):
+    Pydantic program mode to use for structured prediction.
+    """
+
+    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
+    system_prompt: typing.Optional[str] = pydantic.Field(description="System prompt for LLM calls.")
+    output_parser: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
+        description="Output parser to parse, validate, and correct errors programmatically."
+    )
+    pydantic_program_mode: typing.Optional[PydanticProgramMode]
+    query_wrapper_prompt: typing.Optional[BasePromptTemplate] = pydantic.Field(
+        description="Query wrapper prompt for LLM calls."
+    )
+    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/local_eval.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 LocalEval(pydantic.BaseModel):
+    """
+    Evaluation result, EvaluationResult from llama_index.
+
+    Output of an BaseEvaluator.
+    """
+
+    query: typing.Optional[str] = pydantic.Field(description="Query string")
+    contexts: typing.Optional[typing.List[str]] = pydantic.Field(description="Context strings")
+    response: typing.Optional[str] = pydantic.Field(description="Response string")
+    passing: typing.Optional[bool] = pydantic.Field(description="Binary evaluation result (passing or not)")
+    feedback: typing.Optional[str] = pydantic.Field(description="Feedback or reasoning for the response")
+    score: typing.Optional[float] = pydantic.Field(description="Score for the response")
+    pairwise_source: typing.Optional[str] = pydantic.Field(
+        description="Used only for pairwise and specifies whether it is from original order of presented answers or flipped order"
+    )
+    invalid_result: typing.Optional[bool] = pydantic.Field(
+        description="Whether the evaluation result is an invalid one."
+    )
+    invalid_reason: typing.Optional[str] = pydantic.Field(description="Reason for invalid evaluation.")
+
+    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/local_eval_results.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
+from .local_eval import LocalEval
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class LocalEvalResults(pydantic.BaseModel):
+    """
+    Schema for the result of a local evaluation.
+    """
+
+    project_id: str = pydantic.Field(description="The ID of the project.")
+    eval_set_id: typing.Optional[str] = pydantic.Field(description="The ID of the local eval result set.")
+    app_name: str = pydantic.Field(description="The name of the app.")
+    eval_name: str = pydantic.Field(description="The name of the eval.")
+    result: LocalEval = pydantic.Field(description="The eval results.")
+
+    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/local_eval_sets.py

@@ -0,0 +1,30 @@
+# 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 LocalEvalSets(pydantic.BaseModel):
+    eval_set_id: str = pydantic.Field(description="The ID of the eval set.")
+    app_name: str = pydantic.Field(description="The name of the app.")
+    upload_time: dt.datetime = pydantic.Field(description="The time of the upload.")
+
+    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/managed_ingestion_status.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 ManagedIngestionStatus(str, enum.Enum):
+    """
+    Status of managed ingestion with partial Updates.
+    """
+
+    NOT_STARTED = "NOT_STARTED"
+    IN_PROGRESS = "IN_PROGRESS"
+    SUCCESS = "SUCCESS"
+    ERROR = "ERROR"
+    PARTIAL_SUCCESS = "PARTIAL_SUCCESS"
+
+    def visit(
+        self,
+        not_started: typing.Callable[[], T_Result],
+        in_progress: typing.Callable[[], T_Result],
+        success: typing.Callable[[], T_Result],
+        error: typing.Callable[[], T_Result],
+        partial_success: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is ManagedIngestionStatus.NOT_STARTED:
+            return not_started()
+        if self is ManagedIngestionStatus.IN_PROGRESS:
+            return in_progress()
+        if self is ManagedIngestionStatus.SUCCESS:
+            return success()
+        if self is ManagedIngestionStatus.ERROR:
+            return error()
+        if self is ManagedIngestionStatus.PARTIAL_SUCCESS:
+            return partial_success()

llama_cloud/types/markdown_element_node_parser.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 .llm import Llm
+from .node_parser import NodeParser
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class MarkdownElementNodeParser(pydantic.BaseModel):
+    """
+    Markdown element node parser.
+
+    Splits a markdown document into Text Nodes and Index Nodes corresponding to embedded objects
+    (e.g. tables).
+    """
+
+    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]]
+    llm: typing.Optional[Llm] = pydantic.Field(description="LLM model to use for summarization.")
+    summary_query_str: typing.Optional[str] = pydantic.Field(description="Query string to use for summarization.")
+    num_workers: typing.Optional[int] = pydantic.Field(description="Num of workers for async jobs.")
+    show_progress: typing.Optional[bool] = pydantic.Field(description="Whether to show progress.")
+    nested_node_parser: typing.Optional[NodeParser] = pydantic.Field(
+        description="Other types of node parsers to handle some types of nodes."
+    )
+    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/markdown_node_parser.py

@@ -0,0 +1,43 @@
+# 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 MarkdownNodeParser(pydantic.BaseModel):
+    """
+    Markdown node parser.
+
+    Splits a document into Nodes using custom Markdown 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]]
+    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/message_role.py

@@ -0,0 +1,45 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class MessageRole(str, enum.Enum):
+    """
+    Message role.
+    """
+
+    SYSTEM = "system"
+    USER = "user"
+    ASSISTANT = "assistant"
+    FUNCTION = "function"
+    TOOL = "tool"
+    CHATBOT = "chatbot"
+    MODEL = "model"
+
+    def visit(
+        self,
+        system: typing.Callable[[], T_Result],
+        user: typing.Callable[[], T_Result],
+        assistant: typing.Callable[[], T_Result],
+        function: typing.Callable[[], T_Result],
+        tool: typing.Callable[[], T_Result],
+        chatbot: typing.Callable[[], T_Result],
+        model: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is MessageRole.SYSTEM:
+            return system()
+        if self is MessageRole.USER:
+            return user()
+        if self is MessageRole.ASSISTANT:
+            return assistant()
+        if self is MessageRole.FUNCTION:
+            return function()
+        if self is MessageRole.TOOL:
+            return tool()
+        if self is MessageRole.CHATBOT:
+            return chatbot()
+        if self is MessageRole.MODEL:
+            return model()

llama_cloud/types/metadata_filter.py

@@ -0,0 +1,41 @@
+# 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 .filter_operator import FilterOperator
+from .metadata_filter_value import MetadataFilterValue
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class MetadataFilter(pydantic.BaseModel):
+    """
+    Comprehensive metadata filter for vector stores to support more operators.
+
+    Value uses Strict\* types, as int, float and str are compatible types and were all
+    converted to string before.
+
+    See: https://docs.pydantic.dev/latest/usage/types/#strict-types
+    """
+
+    key: str
+    value: MetadataFilterValue
+    operator: typing.Optional[FilterOperator]
+
+    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/metadata_filter_value.py

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

llama_cloud/types/metadata_filters.py

@@ -0,0 +1,41 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .filter_condition import FilterCondition
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class MetadataFilters(pydantic.BaseModel):
+    """
+    Metadata filters for vector stores.
+    """
+
+    filters: typing.List[MetadataFiltersFiltersItem]
+    condition: typing.Optional[FilterCondition]
+
+    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}
+
+
+from .metadata_filters_filters_item import MetadataFiltersFiltersItem  # noqa: E402
+
+MetadataFilters.update_forward_refs()

llama_cloud/types/metadata_filters_filters_item.py

@@ -0,0 +1,8 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .metadata_filter import MetadataFilter
+from .metadata_filters import MetadataFilters
+
+MetadataFiltersFiltersItem = typing.Union[MetadataFilter, MetadataFilters]

llama_cloud/types/metric_result.py

@@ -0,0 +1,30 @@
+# 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 MetricResult(pydantic.BaseModel):
+    passing: typing.Optional[bool] = pydantic.Field(description="Whether the metric passed or not.")
+    score: typing.Optional[float] = pydantic.Field(description="The score for the metric.")
+    feedback: typing.Optional[str] = pydantic.Field(description="The reasoning for the metric.")
+
+    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}