llama-cloud 0.1.18__py3-none-any.whl → 0.1.20__py3-none-any.whl

llama_cloud/types/llm.py

@@ -1,60 +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 .base_prompt_template import BasePromptTemplate
-from .pydantic_program_mode import PydanticProgramMode
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    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.Any]
-    system_prompt: typing.Optional[str]
-    messages_to_prompt: typing.Optional[str] = pydantic.Field(
-        description="Function to convert a list of messages to an LLM prompt."
-    )
-    completion_to_prompt: typing.Optional[str] = pydantic.Field(
-        description="Function to convert a completion to an LLM prompt."
-    )
-    output_parser: typing.Optional[typing.Any]
-    pydantic_program_mode: typing.Optional[PydanticProgramMode]
-    query_wrapper_prompt: typing.Optional[BasePromptTemplate]
-    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_element_node_parser.py

@@ -1,51 +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 .llm import Llm
-from .node_parser import NodeParser
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    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.Any]
-    id_func: typing.Optional[str]
-    llm: typing.Optional[Llm]
-    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]
-    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/page_splitter_node_parser.py

@@ -1,42 +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 PageSplitterNodeParser(pydantic.BaseModel):
-    """
-    Split text into pages.
-    """
-
-    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.Any]
-    id_func: typing.Optional[str]
-    page_separator: 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/pydantic_program_mode.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 PydanticProgramMode(str, enum.Enum):
-    """
-    Pydantic program mode.
-    """
-
-    DEFAULT = "default"
-    OPENAI = "openai"
-    LLM = "llm"
-    FUNCTION = "function"
-    GUIDANCE = "guidance"
-    LM_FORMAT_ENFORCER = "lm-format-enforcer"
-
-    def visit(
-        self,
-        default: typing.Callable[[], T_Result],
-        openai: typing.Callable[[], T_Result],
-        llm: typing.Callable[[], T_Result],
-        function: typing.Callable[[], T_Result],
-        guidance: typing.Callable[[], T_Result],
-        lm_format_enforcer: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is PydanticProgramMode.DEFAULT:
-            return default()
-        if self is PydanticProgramMode.OPENAI:
-            return openai()
-        if self is PydanticProgramMode.LLM:
-            return llm()
-        if self is PydanticProgramMode.FUNCTION:
-            return function()
-        if self is PydanticProgramMode.GUIDANCE:
-            return guidance()
-        if self is PydanticProgramMode.LM_FORMAT_ENFORCER:
-            return lm_format_enforcer()

llama_cloud/types/sentence_splitter.py

@@ -1,50 +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 SentenceSplitter(pydantic.BaseModel):
-    """
-    Parse text with a preference for complete sentences.
-
-    In general, this class tries to keep sentences and paragraphs together. Therefore
-    compared to the original TokenTextSplitter, there are less likely to be
-    hanging sentences or parts of sentences at the end of the node chunk.
-    """
-
-    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.Any]
-    id_func: typing.Optional[str]
-    chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
-    chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
-    separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")
-    paragraph_separator: typing.Optional[str] = pydantic.Field(description="Separator between paragraphs.")
-    secondary_chunking_regex: 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/token_text_splitter.py

@@ -1,47 +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 TokenTextSplitter(pydantic.BaseModel):
-    """
-    Implementation of splitting text that looks at word tokens.
-    """
-
-    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.Any]
-    id_func: typing.Optional[str]
-    chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
-    chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
-    separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")
-    backup_separators: typing.Optional[typing.List[typing.Any]] = pydantic.Field(
-        description="Additional separators for splitting."
-    )
-    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}