llama-cloud 0.1.41__py3-none-any.whl → 0.1.43__py3-none-any.whl

llama_cloud/types/chunk_mode.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 ChunkMode(str, enum.Enum):
-    PAGE = "PAGE"
-    DOCUMENT = "DOCUMENT"
-    SECTION = "SECTION"
-    GROUPED_PAGES = "GROUPED_PAGES"
-
-    def visit(
-        self,
-        page: typing.Callable[[], T_Result],
-        document: typing.Callable[[], T_Result],
-        section: typing.Callable[[], T_Result],
-        grouped_pages: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is ChunkMode.PAGE:
-            return page()
-        if self is ChunkMode.DOCUMENT:
-            return document()
-        if self is ChunkMode.SECTION:
-            return section()
-        if self is ChunkMode.GROUPED_PAGES:
-            return grouped_pages()

llama_cloud/types/llama_extract_settings.py

@@ -1,67 +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 .chunk_mode import ChunkMode
-from .llama_parse_parameters import LlamaParseParameters
-from .multimodal_parse_resolution import MultimodalParseResolution
-from .struct_parse_conf import StructParseConf
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class LlamaExtractSettings(pydantic.BaseModel):
-    """
-    All settings for the extraction agent. Only the settings in ExtractConfig
-    are exposed to the user.
-    """
-
-    max_file_size: typing.Optional[int] = pydantic.Field(
-        description="The maximum file size (in bytes) allowed for the document."
-    )
-    max_file_size_ui: typing.Optional[int] = pydantic.Field(
-        description="The maximum file size (in bytes) allowed for the document."
-    )
-    max_pages: typing.Optional[int] = pydantic.Field(
-        description="The maximum number of pages allowed for the document."
-    )
-    chunk_mode: typing.Optional[ChunkMode] = pydantic.Field(description="The mode to use for chunking the document.")
-    max_chunk_size: typing.Optional[int] = pydantic.Field(
-        description="The maximum size of the chunks (in tokens) to use for chunking the document."
-    )
-    extraction_agent_config: typing.Optional[typing.Dict[str, StructParseConf]] = pydantic.Field(
-        description="The configuration for the extraction agent."
-    )
-    use_multimodal_parsing: typing.Optional[bool] = pydantic.Field(
-        description="Whether to use experimental multimodal parsing."
-    )
-    use_pixel_extraction: typing.Optional[bool] = pydantic.Field(
-        description="DEPRECATED: Whether to use extraction over pixels for multimodal mode."
-    )
-    llama_parse_params: typing.Optional[LlamaParseParameters] = pydantic.Field(
-        description="LlamaParse related settings."
-    )
-    multimodal_parse_resolution: typing.Optional[MultimodalParseResolution] = pydantic.Field(
-        description="The resolution to use for multimodal parsing."
-    )
-
-    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/multimodal_parse_resolution.py

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

llama_cloud/types/schema_relax_mode.py

@@ -1,25 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import enum
-import typing
-
-T_Result = typing.TypeVar("T_Result")
-
-
-class SchemaRelaxMode(str, enum.Enum):
-    FULL = "FULL"
-    TOP_LEVEL = "TOP_LEVEL"
-    LEAF = "LEAF"
-
-    def visit(
-        self,
-        full: typing.Callable[[], T_Result],
-        top_level: typing.Callable[[], T_Result],
-        leaf: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is SchemaRelaxMode.FULL:
-            return full()
-        if self is SchemaRelaxMode.TOP_LEVEL:
-            return top_level()
-        if self is SchemaRelaxMode.LEAF:
-            return leaf()

llama_cloud/types/struct_mode.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 StructMode(str, enum.Enum):
-    STRUCT_PARSE = "STRUCT_PARSE"
-    JSON_MODE = "JSON_MODE"
-    FUNC_CALL = "FUNC_CALL"
-    STRUCT_RELAXED = "STRUCT_RELAXED"
-    UNSTRUCTURED = "UNSTRUCTURED"
-
-    def visit(
-        self,
-        struct_parse: typing.Callable[[], T_Result],
-        json_mode: typing.Callable[[], T_Result],
-        func_call: typing.Callable[[], T_Result],
-        struct_relaxed: typing.Callable[[], T_Result],
-        unstructured: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is StructMode.STRUCT_PARSE:
-            return struct_parse()
-        if self is StructMode.JSON_MODE:
-            return json_mode()
-        if self is StructMode.FUNC_CALL:
-            return func_call()
-        if self is StructMode.STRUCT_RELAXED:
-            return struct_relaxed()
-        if self is StructMode.UNSTRUCTURED:
-            return unstructured()

llama_cloud/types/struct_parse_conf.py

@@ -1,63 +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 .extract_models import ExtractModels
-from .prompt_conf import PromptConf
-from .schema_relax_mode import SchemaRelaxMode
-from .struct_mode import StructMode
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class StructParseConf(pydantic.BaseModel):
-    """
-    Configuration for the structured parsing agent.
-    """
-
-    model: typing.Optional[ExtractModels] = pydantic.Field(description="The model to use for the structured parsing.")
-    temperature: typing.Optional[float] = pydantic.Field(
-        description="The temperature to use for the structured parsing."
-    )
-    relaxation_mode: typing.Optional[SchemaRelaxMode] = pydantic.Field(
-        description="The relaxation mode to use for the structured parsing."
-    )
-    struct_mode: typing.Optional[StructMode] = pydantic.Field(
-        description="The struct mode to use for the structured parsing."
-    )
-    fetch_logprobs: typing.Optional[bool] = pydantic.Field(
-        description="Whether to fetch logprobs for the structured parsing."
-    )
-    handle_missing: typing.Optional[bool] = pydantic.Field(
-        description="Whether to handle missing fields in the schema."
-    )
-    use_reasoning: typing.Optional[bool] = pydantic.Field(
-        description="Whether to use reasoning for the structured extraction."
-    )
-    cite_sources: typing.Optional[bool] = pydantic.Field(
-        description="Whether to cite sources for the structured extraction."
-    )
-    prompt_conf: typing.Optional[PromptConf] = pydantic.Field(
-        description="The prompt configuration for the structured parsing."
-    )
-
-    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}