perplexityai 0.22.3__py3-none-any.whl

perplexity/_streaming.py

@@ -0,0 +1,371 @@
+# Note: initially copied from https://github.com/florimondmanca/httpx-sse/blob/master/src/httpx_sse/_decoders.py
+from __future__ import annotations
+
+import json
+import inspect
+from types import TracebackType
+from typing import TYPE_CHECKING, Any, Generic, TypeVar, Iterator, AsyncIterator, cast
+from typing_extensions import Self, Protocol, TypeGuard, override, get_origin, runtime_checkable
+
+import httpx
+
+from ._utils import extract_type_var_from_base
+
+if TYPE_CHECKING:
+    from ._client import Perplexity, AsyncPerplexity
+
+
+_T = TypeVar("_T")
+
+
+class Stream(Generic[_T]):
+    """Provides the core interface to iterate over a synchronous stream response."""
+
+    response: httpx.Response
+
+    _decoder: SSEBytesDecoder
+
+    def __init__(
+        self,
+        *,
+        cast_to: type[_T],
+        response: httpx.Response,
+        client: Perplexity,
+    ) -> None:
+        self.response = response
+        self._cast_to = cast_to
+        self._client = client
+        self._decoder = client._make_sse_decoder()
+        self._iterator = self.__stream__()
+
+    def __next__(self) -> _T:
+        return self._iterator.__next__()
+
+    def __iter__(self) -> Iterator[_T]:
+        for item in self._iterator:
+            yield item
+
+    def _iter_events(self) -> Iterator[ServerSentEvent]:
+        yield from self._decoder.iter_bytes(self.response.iter_bytes())
+
+    def __stream__(self) -> Iterator[_T]:
+        cast_to = cast(Any, self._cast_to)
+        response = self.response
+        process_data = self._client._process_response_data
+        iterator = self._iter_events()
+
+        try:
+            for sse in iterator:
+                if sse.data.startswith("[DONE]"):
+                    break
+
+                if sse.event == "error":
+                    body = sse.data
+
+                    try:
+                        body = sse.json()
+                        err_msg = f"{body}"
+                    except Exception:
+                        err_msg = sse.data or f"Error code: {response.status_code}"
+
+                    raise self._client._make_status_error(
+                        err_msg,
+                        body=body,
+                        response=self.response,
+                    )
+
+                if sse.event is None:
+                    yield process_data(data=sse.json(), cast_to=cast_to, response=response)
+        finally:
+            # Ensure the response is closed even if the consumer doesn't read all data
+            response.close()
+
+    def __enter__(self) -> Self:
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        self.close()
+
+    def close(self) -> None:
+        """
+        Close the response and release the connection.
+
+        Automatically called if the response body is read to completion.
+        """
+        self.response.close()
+
+
+class AsyncStream(Generic[_T]):
+    """Provides the core interface to iterate over an asynchronous stream response."""
+
+    response: httpx.Response
+
+    _decoder: SSEDecoder | SSEBytesDecoder
+
+    def __init__(
+        self,
+        *,
+        cast_to: type[_T],
+        response: httpx.Response,
+        client: AsyncPerplexity,
+    ) -> None:
+        self.response = response
+        self._cast_to = cast_to
+        self._client = client
+        self._decoder = client._make_sse_decoder()
+        self._iterator = self.__stream__()
+
+    async def __anext__(self) -> _T:
+        return await self._iterator.__anext__()
+
+    async def __aiter__(self) -> AsyncIterator[_T]:
+        async for item in self._iterator:
+            yield item
+
+    async def _iter_events(self) -> AsyncIterator[ServerSentEvent]:
+        async for sse in self._decoder.aiter_bytes(self.response.aiter_bytes()):
+            yield sse
+
+    async def __stream__(self) -> AsyncIterator[_T]:
+        cast_to = cast(Any, self._cast_to)
+        response = self.response
+        process_data = self._client._process_response_data
+        iterator = self._iter_events()
+
+        try:
+            async for sse in iterator:
+                if sse.data.startswith("[DONE]"):
+                    break
+
+                if sse.event == "error":
+                    body = sse.data
+
+                    try:
+                        body = sse.json()
+                        err_msg = f"{body}"
+                    except Exception:
+                        err_msg = sse.data or f"Error code: {response.status_code}"
+
+                    raise self._client._make_status_error(
+                        err_msg,
+                        body=body,
+                        response=self.response,
+                    )
+
+                if sse.event is None:
+                    yield process_data(data=sse.json(), cast_to=cast_to, response=response)
+        finally:
+            # Ensure the response is closed even if the consumer doesn't read all data
+            await response.aclose()
+
+    async def __aenter__(self) -> Self:
+        return self
+
+    async def __aexit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        await self.close()
+
+    async def close(self) -> None:
+        """
+        Close the response and release the connection.
+
+        Automatically called if the response body is read to completion.
+        """
+        await self.response.aclose()
+
+
+class ServerSentEvent:
+    def __init__(
+        self,
+        *,
+        event: str | None = None,
+        data: str | None = None,
+        id: str | None = None,
+        retry: int | None = None,
+    ) -> None:
+        if data is None:
+            data = ""
+
+        self._id = id
+        self._data = data
+        self._event = event or None
+        self._retry = retry
+
+    @property
+    def event(self) -> str | None:
+        return self._event
+
+    @property
+    def id(self) -> str | None:
+        return self._id
+
+    @property
+    def retry(self) -> int | None:
+        return self._retry
+
+    @property
+    def data(self) -> str:
+        return self._data
+
+    def json(self) -> Any:
+        return json.loads(self.data)
+
+    @override
+    def __repr__(self) -> str:
+        return f"ServerSentEvent(event={self.event}, data={self.data}, id={self.id}, retry={self.retry})"
+
+
+class SSEDecoder:
+    _data: list[str]
+    _event: str | None
+    _retry: int | None
+    _last_event_id: str | None
+
+    def __init__(self) -> None:
+        self._event = None
+        self._data = []
+        self._last_event_id = None
+        self._retry = None
+
+    def iter_bytes(self, iterator: Iterator[bytes]) -> Iterator[ServerSentEvent]:
+        """Given an iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        for chunk in self._iter_chunks(iterator):
+            # Split before decoding so splitlines() only uses \r and \n
+            for raw_line in chunk.splitlines():
+                line = raw_line.decode("utf-8")
+                sse = self.decode(line)
+                if sse:
+                    yield sse
+
+    def _iter_chunks(self, iterator: Iterator[bytes]) -> Iterator[bytes]:
+        """Given an iterator that yields raw binary data, iterate over it and yield individual SSE chunks"""
+        data = b""
+        for chunk in iterator:
+            for line in chunk.splitlines(keepends=True):
+                data += line
+                if data.endswith((b"\r\r", b"\n\n", b"\r\n\r\n")):
+                    yield data
+                    data = b""
+        if data:
+            yield data
+
+    async def aiter_bytes(self, iterator: AsyncIterator[bytes]) -> AsyncIterator[ServerSentEvent]:
+        """Given an iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        async for chunk in self._aiter_chunks(iterator):
+            # Split before decoding so splitlines() only uses \r and \n
+            for raw_line in chunk.splitlines():
+                line = raw_line.decode("utf-8")
+                sse = self.decode(line)
+                if sse:
+                    yield sse
+
+    async def _aiter_chunks(self, iterator: AsyncIterator[bytes]) -> AsyncIterator[bytes]:
+        """Given an iterator that yields raw binary data, iterate over it and yield individual SSE chunks"""
+        data = b""
+        async for chunk in iterator:
+            for line in chunk.splitlines(keepends=True):
+                data += line
+                if data.endswith((b"\r\r", b"\n\n", b"\r\n\r\n")):
+                    yield data
+                    data = b""
+        if data:
+            yield data
+
+    def decode(self, line: str) -> ServerSentEvent | None:
+        # See: https://html.spec.whatwg.org/multipage/server-sent-events.html#event-stream-interpretation  # noqa: E501
+
+        if not line:
+            if not self._event and not self._data and not self._last_event_id and self._retry is None:
+                return None
+
+            sse = ServerSentEvent(
+                event=self._event,
+                data="\n".join(self._data),
+                id=self._last_event_id,
+                retry=self._retry,
+            )
+
+            # NOTE: as per the SSE spec, do not reset last_event_id.
+            self._event = None
+            self._data = []
+            self._retry = None
+
+            return sse
+
+        if line.startswith(":"):
+            return None
+
+        fieldname, _, value = line.partition(":")
+
+        if value.startswith(" "):
+            value = value[1:]
+
+        if fieldname == "event":
+            self._event = value
+        elif fieldname == "data":
+            self._data.append(value)
+        elif fieldname == "id":
+            if "\0" in value:
+                pass
+            else:
+                self._last_event_id = value
+        elif fieldname == "retry":
+            try:
+                self._retry = int(value)
+            except (TypeError, ValueError):
+                pass
+        else:
+            pass  # Field is ignored.
+
+        return None
+
+
+@runtime_checkable
+class SSEBytesDecoder(Protocol):
+    def iter_bytes(self, iterator: Iterator[bytes]) -> Iterator[ServerSentEvent]:
+        """Given an iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        ...
+
+    def aiter_bytes(self, iterator: AsyncIterator[bytes]) -> AsyncIterator[ServerSentEvent]:
+        """Given an async iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        ...
+
+
+def is_stream_class_type(typ: type) -> TypeGuard[type[Stream[object]] | type[AsyncStream[object]]]:
+    """TypeGuard for determining whether or not the given type is a subclass of `Stream` / `AsyncStream`"""
+    origin = get_origin(typ) or typ
+    return inspect.isclass(origin) and issubclass(origin, (Stream, AsyncStream))
+
+
+def extract_stream_chunk_type(
+    stream_cls: type,
+    *,
+    failure_message: str | None = None,
+) -> type:
+    """Given a type like `Stream[T]`, returns the generic type variable `T`.
+
+    This also handles the case where a concrete subclass is given, e.g.
+    ```py
+    class MyStream(Stream[bytes]):
+        ...
+
+    extract_stream_chunk_type(MyStream) -> bytes
+    ```
+    """
+    from ._base_client import Stream, AsyncStream
+
+    return extract_type_var_from_base(
+        stream_cls,
+        index=0,
+        generic_bases=cast("tuple[type, ...]", (Stream, AsyncStream)),
+        failure_message=failure_message,
+    )

perplexity/_types.py

@@ -0,0 +1,261 @@
+from __future__ import annotations
+
+from os import PathLike
+from typing import (
+    IO,
+    TYPE_CHECKING,
+    Any,
+    Dict,
+    List,
+    Type,
+    Tuple,
+    Union,
+    Mapping,
+    TypeVar,
+    Callable,
+    Iterator,
+    Optional,
+    Sequence,
+)
+from typing_extensions import (
+    Set,
+    Literal,
+    Protocol,
+    TypeAlias,
+    TypedDict,
+    SupportsIndex,
+    overload,
+    override,
+    runtime_checkable,
+)
+
+import httpx
+import pydantic
+from httpx import URL, Proxy, Timeout, Response, BaseTransport, AsyncBaseTransport
+
+if TYPE_CHECKING:
+    from ._models import BaseModel
+    from ._response import APIResponse, AsyncAPIResponse
+
+Transport = BaseTransport
+AsyncTransport = AsyncBaseTransport
+Query = Mapping[str, object]
+Body = object
+AnyMapping = Mapping[str, object]
+ModelT = TypeVar("ModelT", bound=pydantic.BaseModel)
+_T = TypeVar("_T")
+
+
+# Approximates httpx internal ProxiesTypes and RequestFiles types
+# while adding support for `PathLike` instances
+ProxiesDict = Dict["str | URL", Union[None, str, URL, Proxy]]
+ProxiesTypes = Union[str, Proxy, ProxiesDict]
+if TYPE_CHECKING:
+    Base64FileInput = Union[IO[bytes], PathLike[str]]
+    FileContent = Union[IO[bytes], bytes, PathLike[str]]
+else:
+    Base64FileInput = Union[IO[bytes], PathLike]
+    FileContent = Union[IO[bytes], bytes, PathLike]  # PathLike is not subscriptable in Python 3.8.
+FileTypes = Union[
+    # file (or bytes)
+    FileContent,
+    # (filename, file (or bytes))
+    Tuple[Optional[str], FileContent],
+    # (filename, file (or bytes), content_type)
+    Tuple[Optional[str], FileContent, Optional[str]],
+    # (filename, file (or bytes), content_type, headers)
+    Tuple[Optional[str], FileContent, Optional[str], Mapping[str, str]],
+]
+RequestFiles = Union[Mapping[str, FileTypes], Sequence[Tuple[str, FileTypes]]]
+
+# duplicate of the above but without our custom file support
+HttpxFileContent = Union[IO[bytes], bytes]
+HttpxFileTypes = Union[
+    # file (or bytes)
+    HttpxFileContent,
+    # (filename, file (or bytes))
+    Tuple[Optional[str], HttpxFileContent],
+    # (filename, file (or bytes), content_type)
+    Tuple[Optional[str], HttpxFileContent, Optional[str]],
+    # (filename, file (or bytes), content_type, headers)
+    Tuple[Optional[str], HttpxFileContent, Optional[str], Mapping[str, str]],
+]
+HttpxRequestFiles = Union[Mapping[str, HttpxFileTypes], Sequence[Tuple[str, HttpxFileTypes]]]
+
+# Workaround to support (cast_to: Type[ResponseT]) -> ResponseT
+# where ResponseT includes `None`. In order to support directly
+# passing `None`, overloads would have to be defined for every
+# method that uses `ResponseT` which would lead to an unacceptable
+# amount of code duplication and make it unreadable. See _base_client.py
+# for example usage.
+#
+# This unfortunately means that you will either have
+# to import this type and pass it explicitly:
+#
+# from perplexity import NoneType
+# client.get('/foo', cast_to=NoneType)
+#
+# or build it yourself:
+#
+# client.get('/foo', cast_to=type(None))
+if TYPE_CHECKING:
+    NoneType: Type[None]
+else:
+    NoneType = type(None)
+
+
+class RequestOptions(TypedDict, total=False):
+    headers: Headers
+    max_retries: int
+    timeout: float | Timeout | None
+    params: Query
+    extra_json: AnyMapping
+    idempotency_key: str
+    follow_redirects: bool
+
+
+# Sentinel class used until PEP 0661 is accepted
+class NotGiven:
+    """
+    For parameters with a meaningful None value, we need to distinguish between
+    the user explicitly passing None, and the user not passing the parameter at
+    all.
+
+    User code shouldn't need to use not_given directly.
+
+    For example:
+
+    ```py
+    def create(timeout: Timeout | None | NotGiven = not_given): ...
+
+
+    create(timeout=1)  # 1s timeout
+    create(timeout=None)  # No timeout
+    create()  # Default timeout behavior
+    ```
+    """
+
+    def __bool__(self) -> Literal[False]:
+        return False
+
+    @override
+    def __repr__(self) -> str:
+        return "NOT_GIVEN"
+
+
+not_given = NotGiven()
+# for backwards compatibility:
+NOT_GIVEN = NotGiven()
+
+
+class Omit:
+    """
+    To explicitly omit something from being sent in a request, use `omit`.
+
+    ```py
+    # as the default `Content-Type` header is `application/json` that will be sent
+    client.post("/upload/files", files={"file": b"my raw file content"})
+
+    # you can't explicitly override the header as it has to be dynamically generated
+    # to look something like: 'multipart/form-data; boundary=0d8382fcf5f8c3be01ca2e11002d2983'
+    client.post(..., headers={"Content-Type": "multipart/form-data"})
+
+    # instead you can remove the default `application/json` header by passing omit
+    client.post(..., headers={"Content-Type": omit})
+    ```
+    """
+
+    def __bool__(self) -> Literal[False]:
+        return False
+
+
+omit = Omit()
+
+
+@runtime_checkable
+class ModelBuilderProtocol(Protocol):
+    @classmethod
+    def build(
+        cls: type[_T],
+        *,
+        response: Response,
+        data: object,
+    ) -> _T: ...
+
+
+Headers = Mapping[str, Union[str, Omit]]
+
+
+class HeadersLikeProtocol(Protocol):
+    def get(self, __key: str) -> str | None: ...
+
+
+HeadersLike = Union[Headers, HeadersLikeProtocol]
+
+ResponseT = TypeVar(
+    "ResponseT",
+    bound=Union[
+        object,
+        str,
+        None,
+        "BaseModel",
+        List[Any],
+        Dict[str, Any],
+        Response,
+        ModelBuilderProtocol,
+        "APIResponse[Any]",
+        "AsyncAPIResponse[Any]",
+    ],
+)
+
+StrBytesIntFloat = Union[str, bytes, int, float]
+
+# Note: copied from Pydantic
+# https://github.com/pydantic/pydantic/blob/6f31f8f68ef011f84357330186f603ff295312fd/pydantic/main.py#L79
+IncEx: TypeAlias = Union[Set[int], Set[str], Mapping[int, Union["IncEx", bool]], Mapping[str, Union["IncEx", bool]]]
+
+PostParser = Callable[[Any], Any]
+
+
+@runtime_checkable
+class InheritsGeneric(Protocol):
+    """Represents a type that has inherited from `Generic`
+
+    The `__orig_bases__` property can be used to determine the resolved
+    type variable for a given base class.
+    """
+
+    __orig_bases__: tuple[_GenericAlias]
+
+
+class _GenericAlias(Protocol):
+    __origin__: type[object]
+
+
+class HttpxSendArgs(TypedDict, total=False):
+    auth: httpx.Auth
+    follow_redirects: bool
+
+
+_T_co = TypeVar("_T_co", covariant=True)
+
+
+if TYPE_CHECKING:
+    # This works because str.__contains__ does not accept object (either in typeshed or at runtime)
+    # https://github.com/hauntsaninja/useful_types/blob/5e9710f3875107d068e7679fd7fec9cfab0eff3b/useful_types/__init__.py#L285
+    #
+    # Note: index() and count() methods are intentionally omitted to allow pyright to properly
+    # infer TypedDict types when dict literals are used in lists assigned to SequenceNotStr.
+    class SequenceNotStr(Protocol[_T_co]):
+        @overload
+        def __getitem__(self, index: SupportsIndex, /) -> _T_co: ...
+        @overload
+        def __getitem__(self, index: slice, /) -> Sequence[_T_co]: ...
+        def __contains__(self, value: object, /) -> bool: ...
+        def __len__(self) -> int: ...
+        def __iter__(self) -> Iterator[_T_co]: ...
+        def __reversed__(self) -> Iterator[_T_co]: ...
+else:
+    # just point this to a normal `Sequence` at runtime to avoid having to special case
+    # deserializing our custom sequence type
+    SequenceNotStr = Sequence

perplexity/_utils/__init__.py

@@ -0,0 +1,64 @@
+from ._sync import asyncify as asyncify
+from ._proxy import LazyProxy as LazyProxy
+from ._utils import (
+    flatten as flatten,
+    is_dict as is_dict,
+    is_list as is_list,
+    is_given as is_given,
+    is_tuple as is_tuple,
+    json_safe as json_safe,
+    lru_cache as lru_cache,
+    is_mapping as is_mapping,
+    is_tuple_t as is_tuple_t,
+    is_iterable as is_iterable,
+    is_sequence as is_sequence,
+    coerce_float as coerce_float,
+    is_mapping_t as is_mapping_t,
+    removeprefix as removeprefix,
+    removesuffix as removesuffix,
+    extract_files as extract_files,
+    is_sequence_t as is_sequence_t,
+    required_args as required_args,
+    coerce_boolean as coerce_boolean,
+    coerce_integer as coerce_integer,
+    file_from_path as file_from_path,
+    strip_not_given as strip_not_given,
+    deepcopy_minimal as deepcopy_minimal,
+    get_async_library as get_async_library,
+    maybe_coerce_float as maybe_coerce_float,
+    get_required_header as get_required_header,
+    maybe_coerce_boolean as maybe_coerce_boolean,
+    maybe_coerce_integer as maybe_coerce_integer,
+)
+from ._compat import (
+    get_args as get_args,
+    is_union as is_union,
+    get_origin as get_origin,
+    is_typeddict as is_typeddict,
+    is_literal_type as is_literal_type,
+)
+from ._typing import (
+    is_list_type as is_list_type,
+    is_union_type as is_union_type,
+    extract_type_arg as extract_type_arg,
+    is_iterable_type as is_iterable_type,
+    is_required_type as is_required_type,
+    is_sequence_type as is_sequence_type,
+    is_annotated_type as is_annotated_type,
+    is_type_alias_type as is_type_alias_type,
+    strip_annotated_type as strip_annotated_type,
+    extract_type_var_from_base as extract_type_var_from_base,
+)
+from ._streams import consume_sync_iterator as consume_sync_iterator, consume_async_iterator as consume_async_iterator
+from ._transform import (
+    PropertyInfo as PropertyInfo,
+    transform as transform,
+    async_transform as async_transform,
+    maybe_transform as maybe_transform,
+    async_maybe_transform as async_maybe_transform,
+)
+from ._reflection import (
+    function_has_argument as function_has_argument,
+    assert_signatures_in_sync as assert_signatures_in_sync,
+)
+from ._datetime_parse import parse_date as parse_date, parse_datetime as parse_datetime