gllm-inference-binary 0.5.35__cp312-cp312-macosx_13_0_x86_64.whl → 0.5.36__cp312-cp312-macosx_13_0_x86_64.whl

gllm_inference/realtime_chat/__init__.pyi

@@ -0,0 +1,3 @@
+from gllm_inference.realtime_chat.google_realtime_chat import GoogleRealtimeChat as GoogleRealtimeChat
+
+__all__ = ['GoogleRealtimeChat']

gllm_inference/realtime_chat/google_realtime_chat.pyi

@@ -0,0 +1,205 @@
+import asyncio
+import logging
+from _typeshed import Incomplete
+from gllm_inference.constants import GOOGLE_SCOPES as GOOGLE_SCOPES
+from gllm_inference.realtime_chat.input_streamer import KeyboardInputStreamer as KeyboardInputStreamer
+from gllm_inference.realtime_chat.input_streamer.input_streamer import BaseInputStreamer as BaseInputStreamer
+from gllm_inference.realtime_chat.output_streamer import ConsoleOutputStreamer as ConsoleOutputStreamer
+from gllm_inference.realtime_chat.output_streamer.output_streamer import BaseOutputStreamer as BaseOutputStreamer
+from gllm_inference.realtime_chat.realtime_chat import BaseRealtimeChat as BaseRealtimeChat
+from pydantic import BaseModel
+from typing import Literal
+
+DEFAULT_POST_OUTPUT_AUDIO_DELAY: float
+LIVE_CONNECT_CONFIG: Incomplete
+
+class GoogleIOStreamerState(BaseModel):
+    '''[BETA] Defines the state of the GoogleIOStreamer with thread-safe properties.
+
+    Attributes:
+        is_streaming_output (bool): Whether the output is streaming.
+        console_mode (Literal["input", "user", "assistant"]): The current console mode.
+        terminated (bool): Whether the conversation is terminated.
+    '''
+    is_streaming_output: bool
+    console_mode: Literal['input', 'user', 'assistant']
+    terminated: bool
+    async def set_streaming_output(self, value: bool) -> None:
+        """Thread-safe setter for is_streaming_output.
+
+        Args:
+            value (bool): The value to set for is_streaming_output.
+        """
+    async def get_streaming_output(self) -> bool:
+        """Thread-safe getter for is_streaming_output.
+
+        Returns:
+            bool: The value of is_streaming_output.
+        """
+    async def set_console_mode(self, value: Literal['input', 'user', 'assistant']) -> None:
+        '''Thread-safe setter for console_mode.
+
+        Args:
+            value (Literal["input", "user", "assistant"]): The value to set for console_mode.
+        '''
+    async def get_console_mode(self) -> Literal['input', 'user', 'assistant']:
+        '''Thread-safe getter for console_mode.
+
+        Returns:
+            Literal["input", "user", "assistant"]: The value of console_mode.
+        '''
+    async def set_terminated(self, value: bool) -> None:
+        """Thread-safe setter for terminated.
+
+        Args:
+            value (bool): The value to set for terminated.
+        """
+    async def get_terminated(self) -> bool:
+        """Thread-safe getter for terminated.
+
+        Returns:
+            bool: The value of terminated.
+        """
+
+class GoogleIOStreamer:
+    """[BETA] Defines the GoogleIOStreamer.
+
+    This class manages the realtime conversation lifecycle.
+    It handles the IO operations between the model and the input/output streamers.
+
+    Attributes:
+        session (AsyncSession): The session of the GoogleIOStreamer.
+        task_group (asyncio.TaskGroup): The task group of the GoogleIOStreamer.
+        input_queue (asyncio.Queue): The input queue of the GoogleIOStreamer.
+        output_queue (asyncio.Queue): The output queue of the GoogleIOStreamer.
+        input_streamers (list[BaseInputStreamer]): The input streamers of the GoogleIOStreamer.
+        output_streamers (list[BaseOutputStreamer]): The output streamers of the GoogleIOStreamer.
+        post_output_audio_delay (float): The delay in seconds to post the output audio.
+    """
+    session: AsyncSession
+    task_group: Incomplete
+    input_queue: Incomplete
+    output_queue: Incomplete
+    state: Incomplete
+    input_streamers: Incomplete
+    output_streamers: Incomplete
+    post_output_audio_delay: Incomplete
+    def __init__(self, session: AsyncSession, task_group: asyncio.TaskGroup, input_queue: asyncio.Queue, output_queue: asyncio.Queue, input_streamers: list[BaseInputStreamer], output_streamers: list[BaseOutputStreamer], post_output_audio_delay: float, logger: logging.Logger) -> None:
+        """Initializes a new instance of the GoogleIOStreamer class.
+
+        Args:
+            session (AsyncSession): The session of the GoogleIOStreamer.
+            task_group (asyncio.TaskGroup): The task group of the GoogleIOStreamer.
+            input_queue (asyncio.Queue): The input queue of the GoogleIOStreamer.
+            output_queue (asyncio.Queue): The output queue of the GoogleIOStreamer.
+            input_streamers (list[BaseInputStreamer]): The input streamers of the GoogleIOStreamer.
+            output_streamers (list[BaseOutputStreamer]): The output streamers of the GoogleIOStreamer.
+            post_output_audio_delay (float): The delay in seconds to post the output audio.
+            logger (logging.Logger): The logger of the GoogleIOStreamer.
+        """
+    async def start(self) -> None:
+        """Processes the realtime conversation.
+
+        This method is used to start the realtime conversation.
+        It initializes the input and output streamers, creates the necessary tasks, and starts the conversation.
+        When the conversation is terminated, it cleans up the input and output streamers.
+        """
+
+class GoogleRealtimeChat(BaseRealtimeChat):
+    '''[BETA] A realtime chat module to interact with Gemini Live models.
+
+    Warning:
+        The \'GoogleRealtimeChat\' class is currently in beta and may be subject to changes in the future.
+        It is intended only for quick prototyping in local environments.
+        Please avoid using it in production environments.
+
+    Attributes:
+        model_name (str): The name of the language model.
+        client_params (dict[str, Any]): The Google client instance init parameters.
+
+    Basic usage:
+        The `GoogleRealtimeChat` can be used as started as follows:
+        ```python
+        realtime_chat = GoogleRealtimeChat(model_name="gemini-live-2.5-flash-preview")
+        await realtime_chat.invoke()
+        ```
+
+    Custom IO streamers:
+        The `GoogleRealtimeChat` can be used with custom IO streamers.
+        ```python
+        input_streamers = [KeyboardInputStreamer(), LinuxMicInputStreamer()]
+        output_streamers = [ConsoleOutputStreamer(), LinuxSpeakerOutputStreamer()]
+        realtime_chat = GoogleRealtimeChat(model_name="gemini-live-2.5-flash-preview")
+        await realtime_chat.start(input_streamers=input_streamers, output_streamers=output_streamers)
+        ```
+
+        In the above example, we added a capability to use a Linux system microphone and speaker,
+        allowing realtime audio input and output to the model.
+
+    Authentication:
+        The `GoogleRealtimeChat` can use either Google Gen AI or Google Vertex AI.
+
+        Google Gen AI is recommended for quick prototyping and development.
+        It requires a Gemini API key for authentication.
+
+        Usage example:
+        ```python
+        realtime_chat = GoogleRealtimeChat(
+            model_name="gemini-live-2.5-flash-preview",
+            api_key="your_api_key"
+        )
+        ```
+
+        Google Vertex AI is recommended to build production-ready applications.
+        It requires a service account JSON file for authentication.
+
+        Usage example:
+        ```python
+        realtime_chat = GoogleRealtimeChat(
+            model_name="gemini-live-2.5-flash-preview",
+            credentials_path="path/to/service_account.json"
+        )
+        ```
+
+        If neither `api_key` nor `credentials_path` is provided, Google Gen AI will be used by default.
+        The `GOOGLE_API_KEY` environment variable will be used for authentication.
+    '''
+    model_name: Incomplete
+    client_params: Incomplete
+    def __init__(self, model_name: str, api_key: str | None = None, credentials_path: str | None = None, project_id: str | None = None, location: str = 'us-central1') -> None:
+        '''Initializes a new instance of the GoogleRealtimeChat class.
+
+        Args:
+            model_name (str): The name of the model to use.
+            api_key (str | None, optional): Required for Google Gen AI authentication. Cannot be used together
+                with `credentials_path`. Defaults to None.
+            credentials_path (str | None, optional): Required for Google Vertex AI authentication. Path to the service
+                account credentials JSON file. Cannot be used together with `api_key`. Defaults to None.
+            project_id (str | None, optional): The Google Cloud project ID for Vertex AI. Only used when authenticating
+                with `credentials_path`. Defaults to None, in which case it will be loaded from the credentials file.
+            location (str, optional): The location of the Google Cloud project for Vertex AI. Only used when
+                authenticating with `credentials_path`. Defaults to "us-central1".
+
+        Note:
+            If neither `api_key` nor `credentials_path` is provided, Google Gen AI will be used by default.
+            The `GOOGLE_API_KEY` environment variable will be used for authentication.
+        '''
+    async def start(self, input_streamers: list[BaseInputStreamer] | None = None, output_streamers: list[BaseOutputStreamer] | None = None, post_output_audio_delay: float = ...) -> None:
+        """Starts the realtime conversation using the provided input and output streamers.
+
+        This method is used to start the realtime conversation using a `GoogleIOStreamer`.
+        The streamers are responsible for handling the input and output of the conversation.
+
+        Args:
+            input_streamers (list[BaseInputStreamer] | None, optional): The input streamers to use.
+                Defaults to None, in which case a `KeyboardInputStreamer` will be used.
+            output_streamers (list[BaseOutputStreamer] | None, optional): The output streamers to use.
+                Defaults to None, in which case a `ConsoleOutputStreamer` will be used.
+            post_output_audio_delay (float, optional): The delay in seconds to post the output audio.
+                Defaults to 0.5 seconds.
+
+        Raises:
+            ValueError: If the `input_streamers` or `output_streamers` is an empty list.
+            ValueError: If the `post_output_audio_delay` is not greater than 0.
+            Exception: If the conversation fails to process.
+        """

gllm_inference/realtime_chat/input_streamer/__init__.pyi

@@ -0,0 +1,4 @@
+from gllm_inference.realtime_chat.input_streamer.keyboard_input_streamer import KeyboardInputStreamer as KeyboardInputStreamer
+from gllm_inference.realtime_chat.input_streamer.linux_mic_input_streamer import LinuxMicInputStreamer as LinuxMicInputStreamer
+
+__all__ = ['KeyboardInputStreamer', 'LinuxMicInputStreamer']

gllm_inference/realtime_chat/input_streamer/input_streamer.pyi

@@ -0,0 +1,36 @@
+import abc
+import asyncio
+from abc import ABC, abstractmethod
+from pydantic import BaseModel as BaseModel
+
+class BaseInputStreamer(ABC, metaclass=abc.ABCMeta):
+    """[BETA] A base class for input streamers.
+
+    Attributes:
+        state (BaseModel | None): The state of the input streamer.
+        input_queue (asyncio.Queue | None): The queue to put the input events.
+    """
+    state: BaseModel | None
+    input_queue: asyncio.Queue | None
+    async def initialize(self, state: BaseModel, input_queue: asyncio.Queue) -> None:
+        """Initializes the input streamer.
+
+        Args:
+            input_queue (asyncio.Queue): The queue to put the input events.
+            state (BaseModel): The state of the input streamer.
+        """
+    @abstractmethod
+    async def stream_input(self) -> None:
+        """Streams the input from a certain source.
+
+        This method must be implemented by subclasses to define the logic for streaming the input.
+
+        Raises:
+            NotImplementedError: If the method is not implemented in a subclass.
+        """
+    async def close(self) -> None:
+        """Closes the input streamer.
+
+        This method is used to close the input streamer.
+        It is used to clean up the input streamer.
+        """

gllm_inference/realtime_chat/input_streamer/keyboard_input_streamer.pyi

@@ -0,0 +1,27 @@
+import asyncio
+from _typeshed import Incomplete
+from gllm_inference.realtime_chat.input_streamer.input_streamer import BaseInputStreamer as BaseInputStreamer
+
+DEFAULT_QUIT_CMD: str
+
+class KeyboardInputStreamer(BaseInputStreamer):
+    """[BETA] A keyboard input streamer that reads the input text from the keyboard.
+
+    Attributes:
+        state (BaseModel): The state of the input streamer.
+        input_queue (asyncio.Queue): The queue to put the input events.
+        quit_cmd (str): The command to quit the conversation.
+    """
+    record_process: asyncio.subprocess.Process | None
+    quit_cmd: Incomplete
+    def __init__(self, quit_cmd: str = ...) -> None:
+        """Initializes the KeyboardInputStreamer.
+
+        Args:
+            quit_cmd (str, optional): The command to quit the conversation. Defaults to DEFAULT_QUIT_CMD.
+        """
+    async def stream_input(self) -> None:
+        """Streams the input from the keyboard.
+
+        This method is used to stream the input text from the keyboard to the input queue.
+        """

gllm_inference/realtime_chat/input_streamer/linux_mic_input_streamer.pyi

@@ -0,0 +1,36 @@
+import asyncio
+from _typeshed import Incomplete
+from gllm_inference.realtime_chat.input_streamer.input_streamer import BaseInputStreamer as BaseInputStreamer
+
+SEND_SAMPLE_RATE: int
+CHANNELS: int
+RECORD_CMD: Incomplete
+CHUNK_DURATION: float
+CHUNK_SIZE: Incomplete
+
+class LinuxMicInputStreamer(BaseInputStreamer):
+    """[BETA] A Linux microphone input streamer that reads the input audio from the microphone.
+
+    Attributes:
+        state (BaseModel): The state of the input streamer.
+        input_queue (asyncio.Queue): The queue to put the input events.
+        record_process (asyncio.subprocess.Process | None): The process to record the input audio.
+    """
+    record_process: asyncio.subprocess.Process | None
+    def __init__(self) -> None:
+        """Initializes the LinuxMicInputStreamer.
+
+        Raises:
+            OSError: If the current system is not Linux.
+        """
+    async def stream_input(self) -> None:
+        """Streams the input audio from the Linux system microphone.
+
+        This method is used to stream the recorded input audio from the Linux system microphone to the input queue.
+        """
+    async def close(self) -> None:
+        """Closes the LinuxMicInputStreamer.
+
+        This method is used to close the LinuxMicInputStreamer.
+        It is used to clean up the recording process.
+        """

gllm_inference/realtime_chat/output_streamer/__init__.pyi

@@ -0,0 +1,4 @@
+from gllm_inference.realtime_chat.output_streamer.console_output_streamer import ConsoleOutputStreamer as ConsoleOutputStreamer
+from gllm_inference.realtime_chat.output_streamer.linux_speaker_output_streamer import LinuxSpeakerOutputStreamer as LinuxSpeakerOutputStreamer
+
+__all__ = ['ConsoleOutputStreamer', 'LinuxSpeakerOutputStreamer']

gllm_inference/realtime_chat/output_streamer/console_output_streamer.pyi

@@ -0,0 +1,21 @@
+from gllm_inference.realtime_chat.output_streamer.output_streamer import BaseOutputStreamer as BaseOutputStreamer
+from typing import Any
+
+USER_HEADER: str
+ASSISTANT_HEADER: str
+FOOTER: str
+
+class ConsoleOutputStreamer(BaseOutputStreamer):
+    """[BETA] A console output streamer that prints the output to the console.
+
+    Attributes:
+        state (BaseModel): The state of the output streamer.
+    """
+    async def handle(self, data: dict[str, Any]) -> None:
+        """Handles the output events.
+
+        This method is used to handle the text output events and print them to the console.
+
+        Args:
+            data (dict[str, Any]): The output events.
+        """

gllm_inference/realtime_chat/output_streamer/linux_speaker_output_streamer.pyi

@@ -0,0 +1,42 @@
+import asyncio
+from _typeshed import Incomplete
+from gllm_inference.realtime_chat.output_streamer.output_streamer import BaseOutputStreamer as BaseOutputStreamer
+from pydantic import BaseModel as BaseModel
+from typing import Any
+
+PLAY_AUDIO_SAMPLE_RATE: int
+CHANNELS: int
+PLAY_CMD: Incomplete
+OUTPUT_AUDIO_DELAY: float
+
+class LinuxSpeakerOutputStreamer(BaseOutputStreamer):
+    """[BETA] A Linux speaker output streamer that plays the output audio through the speakers.
+
+    Attributes:
+        state (BaseModel): The state of the output streamer.
+        play_process (asyncio.subprocess.Process | None): The process to play the output audio.
+    """
+    play_process: asyncio.subprocess.Process | None
+    async def initialize(self, state: BaseModel) -> None:
+        """Initializes the LinuxSpeakerOutputStreamer.
+
+        Args:
+            state (BaseModel): The state of the output streamer.
+
+        Raises:
+            OSError: If the current system is not Linux.
+        """
+    async def handle(self, data: dict[str, Any]) -> None:
+        """Handles the output events.
+
+        This method is used to handle the audio output events and play them through the Linux system speakers.
+
+        Args:
+            data (dict[str, Any]): The output events.
+        """
+    async def close(self) -> None:
+        """Closes the LinuxSpeakerOutputStreamer.
+
+        This method is used to close the LinuxSpeakerOutputStreamer.
+        It is used to clean up playing process.
+        """

gllm_inference/realtime_chat/output_streamer/output_streamer.pyi

@@ -0,0 +1,33 @@
+import abc
+from abc import ABC, abstractmethod
+from pydantic import BaseModel as BaseModel
+from typing import Any
+
+class BaseOutputStreamer(ABC, metaclass=abc.ABCMeta):
+    """[BETA] A base class for output streamers.
+
+    Attributes:
+        state (BaseModel | None): The state of the output streamer.
+    """
+    state: BaseModel | None
+    async def initialize(self, state: BaseModel) -> None:
+        """Initializes the output streamer.
+
+        Args:
+            state (BaseModel): The state of the output streamer.
+        """
+    @abstractmethod
+    async def handle(self, data: dict[str, Any]) -> None:
+        """Handles output events streamed from the model.
+
+        This method must be implemented by subclasses to define the logic for handling the output events.
+
+        Raises:
+            NotImplementedError: If the method is not implemented in a subclass.
+        """
+    async def close(self) -> None:
+        """Closes the output streamer.
+
+        This method is used to close the output streamer.
+        It is used to clean up the output streamer.
+        """

gllm_inference/realtime_chat/realtime_chat.pyi

@@ -0,0 +1,28 @@
+import abc
+from abc import ABC, abstractmethod
+from gllm_inference.realtime_chat.input_streamer.input_streamer import BaseInputStreamer as BaseInputStreamer
+from gllm_inference.realtime_chat.output_streamer.output_streamer import BaseOutputStreamer as BaseOutputStreamer
+
+class BaseRealtimeChat(ABC, metaclass=abc.ABCMeta):
+    """[BETA] A base class for realtime chat modules.
+
+    The `BaseRealtimeChat` class provides a framework for processing real-time conversations.
+    """
+    def __init__(self) -> None:
+        """Initializes a new instance of the BaseRealtimeChat class."""
+    @abstractmethod
+    async def start(self, input_streamers: list[BaseInputStreamer] | None = None, output_streamers: list[BaseOutputStreamer] | None = None) -> None:
+        """Starts the real-time conversation using the provided input and output streamers.
+
+        This abstract method must be implemented by subclasses to define the logic
+        for starting the real-time conversation.
+
+        Args:
+            input_streamers (list[BaseInputStreamer] | None, optional): The input streamers to use.
+                Defaults to None.
+            output_streamers (list[BaseOutputStreamer] | None, optional): The output streamers to use.
+                Defaults to None.
+
+        Raises:
+            NotImplementedError: If the method is not implemented in a subclass.
+        """

gllm_inference.pyi

@@ -122,6 +122,11 @@ import xai_sdk.proto.v5
 import xai_sdk.proto.v5.chat_pb2
 import transformers
 import gllm_inference.prompt_formatter.HuggingFacePromptFormatter
+import logging
+import traceback
+import gllm_inference.realtime_chat.input_streamer.KeyboardInputStreamer
+import gllm_inference.realtime_chat.output_streamer.ConsoleOutputStreamer
+import google.genai.live
 import gllm_core.utils.logger_manager
 import mimetypes
 import uuid

{gllm_inference_binary-0.5.35.dist-info → gllm_inference_binary-0.5.36.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: gllm-inference-binary
-Version: 0.5.35
+Version: 0.5.36
 Summary: A library containing components related to model inferences in Gen AI applications.
 Author-email: Henry Wicaksono <henry.wicaksono@gdplabs.id>, Resti Febrina <resti.febrina@gdplabs.id>
 Requires-Python: <3.14,>=3.11

{gllm_inference_binary-0.5.35.dist-info → gllm_inference_binary-0.5.36.dist-info}/RECORD

@@ -1,5 +1,5 @@
-gllm_inference.cpython-312-darwin.so,sha256=E1PlR0FzO-TAj4olr100cmHNjfBRsnv_QV8XiJZEFAc,4557176
-gllm_inference.pyi,sha256=bOGYhW7SnMMPCLRRlkVbSq8I8xn8YwHssI1zZoD1lVU,4263
+gllm_inference.cpython-312-darwin.so,sha256=BsIPawxmSj4KcBpNwu39bem2oEt7YcXexLZpLSz1oPk,4913496
+gllm_inference.pyi,sha256=iM7lOtfdpE_YvCEfI5mcK57dnBO8zNOZlzaPborXUCI,4467
 gllm_inference/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gllm_inference/constants.pyi,sha256=uCf0Rc8GkKwUKeMC5wx5WG_x0iV_piKhjZQl1gNffSQ,291
 gllm_inference/builder/__init__.pyi,sha256=usz2lvfwO4Yk-ZGKXbCWG1cEr3nlQXxMNDNC-2yc1NM,500
@@ -81,6 +81,17 @@ gllm_inference/prompt_formatter/llama_prompt_formatter.pyi,sha256=nz24trAqHsUY_z
 gllm_inference/prompt_formatter/mistral_prompt_formatter.pyi,sha256=DgFitxfvCSJf8_6NUfSre-PXYMuPI4vX4AN6BPF1cBE,2650
 gllm_inference/prompt_formatter/openai_prompt_formatter.pyi,sha256=QB7gHddipQuAolUKO01ApZeaRxBtRZzglS5B78mzsV8,1286
 gllm_inference/prompt_formatter/prompt_formatter.pyi,sha256=UkcPi5ao98OGJyNRsqfhYTlMW-ZLNITaGZUTwzvBzqk,1146
+gllm_inference/realtime_chat/__init__.pyi,sha256=Fhxr_sYOt_p43BT2uvJmCp5FMhfb3dDMoIZglq2y6G8,137
+gllm_inference/realtime_chat/google_realtime_chat.pyi,sha256=S5FOCacuc7j4J2tjpUHCdp91YlalxIJ3V3Bh0t0GGus,10112
+gllm_inference/realtime_chat/realtime_chat.pyi,sha256=qG0fXyhTPLw6wGpnDX6wQrLfs6RBaxCK2ASwIqOymp4,1375
+gllm_inference/realtime_chat/input_streamer/__init__.pyi,sha256=REN1dEEZB-I2RX5QsBMxWcUiGm0-fWLevgj7IT18W6Y,317
+gllm_inference/realtime_chat/input_streamer/input_streamer.pyi,sha256=DOVBe_lxievONS_t14opNNuv0zM3MWyBcCwmxzR4_BE,1259
+gllm_inference/realtime_chat/input_streamer/keyboard_input_streamer.pyi,sha256=3L0y91efGmb4YFWigs2WGAURQ48EwNxLgcVMm15yrIg,1043
+gllm_inference/realtime_chat/input_streamer/linux_mic_input_streamer.pyi,sha256=o8rOootmcKHmKRUCCHvfGlCcfeBow5UTbQHIw89XIqg,1337
+gllm_inference/realtime_chat/output_streamer/__init__.pyi,sha256=FP5amnApQcIvW7YfQEnLzJBzEDz51npgocfCcRWDQXA,339
+gllm_inference/realtime_chat/output_streamer/console_output_streamer.pyi,sha256=pO_llZK7JDjllTWEZjujEVo83Hvrv_8LwVqEkQiIOOo,674
+gllm_inference/realtime_chat/output_streamer/linux_speaker_output_streamer.pyi,sha256=yie6VaOyozzE4bKtvWr-6hRiobK-8mshCqeUOhK1PVA,1487
+gllm_inference/realtime_chat/output_streamer/output_streamer.pyi,sha256=GPAw1wPSrwHpJ2MeZJB3V9CCESTDZpyYYgsoy_LI2Nk,1083
 gllm_inference/request_processor/__init__.pyi,sha256=hVnfdNZnkTBJHnmLtN3Na4ANP0yK6AstWdIizVr2Apo,227
 gllm_inference/request_processor/lm_request_processor.pyi,sha256=VnYc8E3Iayyhw-rPnGPfTKuO3ohgFsS8HPrZJeyES5I,5889
 gllm_inference/request_processor/uses_lm_mixin.pyi,sha256=Yu0XPNuHxq1tWBviHTPw1oThojneFwGHepvGjBXxKQA,6382
@@ -106,7 +117,7 @@ gllm_inference/utils/io_utils.pyi,sha256=7kUTacHAVRYoemFUOjCH7-Qmw-YsQGd6rGYxjf_
 gllm_inference/utils/langchain.pyi,sha256=VluQiHkGigDdqLUbhB6vnXiISCP5hHqV0qokYY6dC1A,1164
 gllm_inference/utils/validation.pyi,sha256=toxBtRp-VItC_X7sNi-GDd7sjibBdWMrR0q01OI2D7k,385
 gllm_inference.build/.gitignore,sha256=aEiIwOuxfzdCmLZe4oB1JsBmCUxwG8x-u-HBCV9JT8E,1
-gllm_inference_binary-0.5.35.dist-info/METADATA,sha256=JtNz8vJg6sEu2MkCc6uZEmk7c3m5dGQADzei_1sq7E0,5636
-gllm_inference_binary-0.5.35.dist-info/WHEEL,sha256=ar3KUKk5QtasLek_3_fVX4zgPzX-lxtBGErPgJ515rA,105
-gllm_inference_binary-0.5.35.dist-info/top_level.txt,sha256=FpOjtN80F-qVNgbScXSEyqa0w09FYn6301iq6qt69IQ,15
-gllm_inference_binary-0.5.35.dist-info/RECORD,,
+gllm_inference_binary-0.5.36.dist-info/METADATA,sha256=FVOLq7mG-Lu_C3as9f33x5eZgNBjLzk5CqsQjyEpGq8,5636
+gllm_inference_binary-0.5.36.dist-info/WHEEL,sha256=ar3KUKk5QtasLek_3_fVX4zgPzX-lxtBGErPgJ515rA,105
+gllm_inference_binary-0.5.36.dist-info/top_level.txt,sha256=FpOjtN80F-qVNgbScXSEyqa0w09FYn6301iq6qt69IQ,15
+gllm_inference_binary-0.5.36.dist-info/RECORD,,