Merge pull request #3980 from pipecat-ai/aleix/move-google-vertex-openai

Move Google Vertex and OpenAI LLM modules to subpackages

changelog/3980.deprecated.md

@@ -0,0 +1 @@
+- Deprecated `pipecat.services.google.llm_vertex`, `pipecat.services.google.llm_openai`, and `pipecat.services.google.gemini_live.llm_vertex` modules. Use `pipecat.services.google.vertex.llm`, `pipecat.services.google.openai.llm`, and `pipecat.services.google.gemini_live.vertex.llm` instead. The old import paths still work but will emit a `DeprecationWarning`.

examples/foundational/14o-function-calling-gemini-openai-format.py

@@ -26,7 +26,7 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
-from pipecat.services.google.llm_openai import GoogleLLMOpenAIBetaService
+from pipecat.services.google.openai.llm import GoogleLLMOpenAIBetaService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams

examples/foundational/14p-function-calling-gemini-vertex-ai.py

@@ -26,7 +26,7 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
-from pipecat.services.google.llm_vertex import GoogleVertexLLMService
+from pipecat.services.google.vertex.llm import GoogleVertexLLMService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams

examples/foundational/26h-gemini-live-vertex-function-calling.py

@@ -26,7 +26,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.google.gemini_live.llm_vertex import GeminiLiveVertexLLMService
+from pipecat.services.google.gemini_live.vertex.llm import GeminiLiveVertexLLMService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams

examples/foundational/55zk-update-settings-google-vertex-llm.py

@@ -24,7 +24,7 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.google.llm_vertex import GoogleVertexLLMService
+from pipecat.services.google.vertex.llm import GoogleVertexLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

examples/foundational/55zm-update-settings-gemini-live-vertex.py

@@ -19,7 +19,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.google.gemini_live.llm_vertex import GeminiLiveVertexLLMService
+from pipecat.services.google.gemini_live.vertex.llm import GeminiLiveVertexLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

src/pipecat/services/google/__init__.py

@@ -12,12 +12,12 @@ from .frames import *
 from .gemini_live import *
 from .image import *
 from .llm import *
-from .llm_openai import *
+from .openai import *
-from .llm_vertex import *
 from .rtvi import *
 from .stt import *
 from .tts import *
+from .vertex import *
 
 sys.modules[__name__] = DeprecatedModuleProxy(
-    globals(), "google", "google.[frames,image,llm,llm_openai,llm_vertex,rtvi,stt,tts]"
+    globals(), "google", "google.[frames,image,llm,openai,vertex,rtvi,stt,tts]"
 )

src/pipecat/services/google/gemini_live/__init__.py

@@ -1,6 +1,6 @@
 from .file_api import GeminiFileAPI
 from .llm import GeminiLiveLLMService
-from .llm_vertex import GeminiLiveVertexLLMService
+from .vertex.llm import GeminiLiveVertexLLMService
 
 __all__ = [
     "GeminiFileAPI",

src/pipecat/services/google/gemini_live/llm_vertex.py

@@ -4,277 +4,15 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""Service for accessing Gemini Live via Google Vertex AI.
+"""Deprecated: use ``pipecat.services.google.gemini_live.vertex.llm`` instead."""
 
-This module provides integration with Google's Gemini Live model via
+import warnings
-Vertex AI, supporting both text and audio modalities with voice transcription,
-streaming responses, and tool usage.
-"""
 
-import json
+warnings.warn(
-from dataclasses import dataclass
+    "Module `pipecat.services.google.gemini_live.llm_vertex` is deprecated, "
-from typing import List, Optional, Union
+    "use `pipecat.services.google.gemini_live.vertex.llm` instead.",
-
+    DeprecationWarning,
-from loguru import logger
+    stacklevel=2,
-
-from pipecat.adapters.schemas.tools_schema import ToolsSchema
-from pipecat.services.google.gemini_live.llm import (
-    GeminiLiveLLMService,
-    GeminiLiveLLMSettings,
-    GeminiMediaResolution,
-    GeminiModalities,
-    HttpOptions,
-    InputParams,
-    language_to_gemini_language,
 )
-from pipecat.services.settings import _warn_deprecated_param
 
-try:
+from pipecat.services.google.gemini_live.vertex.llm import *  # noqa: E402, F401, F403
-    from google.auth import default
-    from google.auth.exceptions import GoogleAuthError
-    from google.auth.transport.requests import Request
-    from google.genai import Client
-    from google.oauth2 import service_account
-
-except ModuleNotFoundError as e:
-    logger.error(f"Exception: {e}")
-    logger.error("In order to use Google Vertex AI, you need to `pip install pipecat-ai[google]`.")
-    raise Exception(f"Missing module: {e}")
-
-
-@dataclass
-class GeminiLiveVertexLLMSettings(GeminiLiveLLMSettings):
-    """Settings for GeminiLiveVertexLLMService."""
-
-    pass
-
-
-class GeminiLiveVertexLLMService(GeminiLiveLLMService):
-    """Provides access to Google's Gemini Live model via Vertex AI.
-
-    This service enables real-time conversations with Gemini, supporting both
-    text and audio modalities. It handles voice transcription, streaming audio
-    responses, and tool usage.
-    """
-
-    Settings = GeminiLiveVertexLLMSettings
-    _settings: GeminiLiveVertexLLMSettings
-
-    def __init__(
-        self,
-        *,
-        credentials: Optional[str] = None,
-        credentials_path: Optional[str] = None,
-        location: str,
-        project_id: str,
-        model: Optional[str] = None,
-        voice_id: str = "Charon",
-        start_audio_paused: bool = False,
-        start_video_paused: bool = False,
-        system_instruction: Optional[str] = None,
-        tools: Optional[Union[List[dict], ToolsSchema]] = None,
-        params: Optional[InputParams] = None,
-        settings: Optional[GeminiLiveVertexLLMSettings] = None,
-        inference_on_context_initialization: bool = True,
-        file_api_base_url: str = "https://generativelanguage.googleapis.com/v1beta/files",
-        http_options: Optional[HttpOptions] = None,
-        **kwargs,
-    ):
-        """Initialize the service for accessing Gemini Live via Google Vertex AI.
-
-        Args:
-            credentials: JSON string of service account credentials.
-            credentials_path: Path to the service account JSON file.
-            location: GCP region for Vertex AI endpoint (e.g., "us-east4").
-            project_id: Google Cloud project ID.
-            model: Model identifier to use.
-
-                .. deprecated:: 0.0.105
-                    Use ``settings=GeminiLiveLLMSettings(model=...)`` instead.
-
-            voice_id: TTS voice identifier. Defaults to "Charon".
-
-                .. deprecated:: 0.0.105
-                    Use ``settings=GeminiLiveVertexLLMSettings(voice=...)`` instead.
-            start_audio_paused: Whether to start with audio input paused. Defaults to False.
-            start_video_paused: Whether to start with video input paused. Defaults to False.
-            system_instruction: System prompt for the model. Defaults to None.
-            tools: Tools/functions available to the model. Defaults to None.
-            params: Configuration parameters for the model along with Vertex AI
-                location and project ID.
-
-                .. deprecated:: 0.0.105
-                    Use ``settings=GeminiLiveLLMSettings(...)`` instead.
-
-            settings: Gemini Live LLM settings. If provided together with deprecated
-                top-level parameters, the ``settings`` values take precedence.
-            inference_on_context_initialization: Whether to generate a response when context
-                is first set. Defaults to True.
-            file_api_base_url: Base URL for the Gemini File API. Defaults to the official endpoint.
-            http_options: HTTP options for the client.
-            **kwargs: Additional arguments passed to parent GeminiLiveLLMService.
-        """
-        # Check if user incorrectly passed api_key, which is used by parent
-        # class but not here.
-        if "api_key" in kwargs:
-            logger.error(
-                "GeminiLiveVertexLLMService does not accept 'api_key' parameter. "
-                "Use 'credentials' or 'credentials_path' instead for Vertex AI authentication."
-            )
-            raise ValueError(
-                "Invalid parameter 'api_key'. Use 'credentials' or 'credentials_path' for Vertex AI authentication."
-            )
-
-        # These need to be set before calling super().__init__() because
-        # super().__init__() invokes create_client(), which needs these.
-        self._credentials = self._get_credentials(credentials, credentials_path)
-        self._project_id = project_id
-        self._location = location
-
-        # Build default_settings from deprecated args, then apply settings delta.
-        # We pass settings= to super() instead of model=/params= to avoid
-        # double deprecation warnings from the parent.
-
-        # 1. Initialize default_settings with hardcoded defaults
-        default_settings = GeminiLiveVertexLLMSettings(
-            model="google/gemini-live-2.5-flash-native-audio",
-            voice="Charon",
-            frequency_penalty=None,
-            max_tokens=4096,
-            presence_penalty=None,
-            temperature=None,
-            top_k=None,
-            top_p=None,
-            seed=None,
-            filter_incomplete_user_turns=False,
-            user_turn_completion_config=None,
-            modalities=GeminiModalities.AUDIO,
-            language="en-US",
-            media_resolution=GeminiMediaResolution.UNSPECIFIED,
-            vad=None,
-            context_window_compression={},
-            thinking={},
-            enable_affective_dialog=False,
-            proactivity={},
-            extra={},
-        )
-
-        # 2. Apply direct init arg overrides (deprecated)
-        if model is not None:
-            _warn_deprecated_param("model", GeminiLiveVertexLLMSettings, "model")
-            default_settings.model = model
-        if voice_id != "Charon":
-            _warn_deprecated_param("voice_id", GeminiLiveVertexLLMSettings, "voice")
-            default_settings.voice = voice_id
-
-        # 3. Apply params overrides — only if settings not provided
-        if params is not None:
-            _warn_deprecated_param("params", GeminiLiveVertexLLMSettings)
-            if not settings:
-                default_settings.frequency_penalty = params.frequency_penalty
-                default_settings.max_tokens = params.max_tokens
-                default_settings.presence_penalty = params.presence_penalty
-                default_settings.temperature = params.temperature
-                default_settings.top_k = params.top_k
-                default_settings.top_p = params.top_p
-                default_settings.modalities = params.modalities
-                default_settings.language = (
-                    language_to_gemini_language(params.language) if params.language else "en-US"
-                )
-                default_settings.media_resolution = params.media_resolution
-                default_settings.vad = params.vad
-                default_settings.context_window_compression = (
-                    params.context_window_compression.model_dump()
-                    if params.context_window_compression
-                    else {}
-                )
-                default_settings.thinking = params.thinking or {}
-                default_settings.enable_affective_dialog = params.enable_affective_dialog or False
-                default_settings.proactivity = params.proactivity or {}
-                if isinstance(params.extra, dict):
-                    default_settings.extra = params.extra
-
-        # 4. Apply settings delta (canonical API, always wins)
-        if settings is not None:
-            default_settings.apply_update(settings)
-
-        # Call parent constructor with the obtained settings
-        super().__init__(
-            # api_key is required by parent class, but actually not used with
-            # Vertex
-            api_key="dummy",
-            start_audio_paused=start_audio_paused,
-            start_video_paused=start_video_paused,
-            system_instruction=system_instruction,
-            tools=tools,
-            settings=default_settings,
-            inference_on_context_initialization=inference_on_context_initialization,
-            file_api_base_url=file_api_base_url,
-            http_options=http_options,
-            **kwargs,
-        )
-
-    def create_client(self):
-        """Create the Gemini client instance."""
-        self._client = Client(
-            vertexai=True,
-            credentials=self._credentials,
-            project=self._project_id,
-            location=self._location,
-            http_options=self._http_options,
-        )
-
-    @property
-    def file_api(self):
-        """Gemini File API is not supported with Vertex AI."""
-        raise NotImplementedError(
-            "When using Vertex AI, the recommended approach is to use Google Cloud Storage for file handling. The Gemini File API is not directly supported in this context."
-        )
-
-    @staticmethod
-    def _get_credentials(credentials: Optional[str], credentials_path: Optional[str]) -> str:
-        """Retrieve Credentials using Google service account credentials JSON.
-
-        Supports multiple authentication methods:
-        1. Direct JSON credentials string
-        2. Path to service account JSON file
-        3. Default application credentials (ADC)
-
-        Args:
-            credentials: JSON string of service account credentials.
-            credentials_path: Path to the service account JSON file.
-
-        Returns:
-            OAuth token for API authentication.
-
-        Raises:
-            ValueError: If no valid credentials are provided or found.
-        """
-        creds: Optional[service_account.Credentials] = None
-
-        if credentials:
-            # Parse and load credentials from JSON string
-            creds = service_account.Credentials.from_service_account_info(
-                json.loads(credentials),
-                scopes=["https://www.googleapis.com/auth/cloud-platform"],
-            )
-        elif credentials_path:
-            # Load credentials from JSON file
-            creds = service_account.Credentials.from_service_account_file(
-                credentials_path,
-                scopes=["https://www.googleapis.com/auth/cloud-platform"],
-            )
-        else:
-            try:
-                creds, project_id = default(
-                    scopes=["https://www.googleapis.com/auth/cloud-platform"]
-                )
-            except GoogleAuthError:
-                pass
-
-        if not creds:
-            raise ValueError("No valid credentials provided.")
-
-        creds.refresh(Request())  # Ensure token is up-to-date, lifetime is 1 hour.
-
-        return creds

src/pipecat/services/google/gemini_live/vertex/__init__.py

@@ -0,0 +1,5 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#

src/pipecat/services/google/gemini_live/vertex/llm.py

@@ -0,0 +1,280 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Service for accessing Gemini Live via Google Vertex AI.
+
+This module provides integration with Google's Gemini Live model via
+Vertex AI, supporting both text and audio modalities with voice transcription,
+streaming responses, and tool usage.
+"""
+
+import json
+from dataclasses import dataclass
+from typing import List, Optional, Union
+
+from loguru import logger
+
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.services.google.gemini_live.llm import (
+    GeminiLiveLLMService,
+    GeminiLiveLLMSettings,
+    GeminiMediaResolution,
+    GeminiModalities,
+    HttpOptions,
+    InputParams,
+    language_to_gemini_language,
+)
+from pipecat.services.settings import _warn_deprecated_param
+
+try:
+    from google.auth import default
+    from google.auth.exceptions import GoogleAuthError
+    from google.auth.transport.requests import Request
+    from google.genai import Client
+    from google.oauth2 import service_account
+
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Google Vertex AI, you need to `pip install pipecat-ai[google]`.")
+    raise Exception(f"Missing module: {e}")
+
+
+@dataclass
+class GeminiLiveVertexLLMSettings(GeminiLiveLLMSettings):
+    """Settings for GeminiLiveVertexLLMService."""
+
+    pass
+
+
+class GeminiLiveVertexLLMService(GeminiLiveLLMService):
+    """Provides access to Google's Gemini Live model via Vertex AI.
+
+    This service enables real-time conversations with Gemini, supporting both
+    text and audio modalities. It handles voice transcription, streaming audio
+    responses, and tool usage.
+    """
+
+    Settings = GeminiLiveVertexLLMSettings
+    _settings: GeminiLiveVertexLLMSettings
+
+    def __init__(
+        self,
+        *,
+        credentials: Optional[str] = None,
+        credentials_path: Optional[str] = None,
+        location: str,
+        project_id: str,
+        model: Optional[str] = None,
+        voice_id: str = "Charon",
+        start_audio_paused: bool = False,
+        start_video_paused: bool = False,
+        system_instruction: Optional[str] = None,
+        tools: Optional[Union[List[dict], ToolsSchema]] = None,
+        params: Optional[InputParams] = None,
+        settings: Optional[GeminiLiveVertexLLMSettings] = None,
+        inference_on_context_initialization: bool = True,
+        file_api_base_url: str = "https://generativelanguage.googleapis.com/v1beta/files",
+        http_options: Optional[HttpOptions] = None,
+        **kwargs,
+    ):
+        """Initialize the service for accessing Gemini Live via Google Vertex AI.
+
+        Args:
+            credentials: JSON string of service account credentials.
+            credentials_path: Path to the service account JSON file.
+            location: GCP region for Vertex AI endpoint (e.g., "us-east4").
+            project_id: Google Cloud project ID.
+            model: Model identifier to use.
+
+                .. deprecated:: 0.0.105
+                    Use ``settings=GeminiLiveLLMSettings(model=...)`` instead.
+
+            voice_id: TTS voice identifier. Defaults to "Charon".
+
+                .. deprecated:: 0.0.105
+                    Use ``settings=GeminiLiveVertexLLMSettings(voice=...)`` instead.
+            start_audio_paused: Whether to start with audio input paused. Defaults to False.
+            start_video_paused: Whether to start with video input paused. Defaults to False.
+            system_instruction: System prompt for the model. Defaults to None.
+            tools: Tools/functions available to the model. Defaults to None.
+            params: Configuration parameters for the model along with Vertex AI
+                location and project ID.
+
+                .. deprecated:: 0.0.105
+                    Use ``settings=GeminiLiveLLMSettings(...)`` instead.
+
+            settings: Gemini Live LLM settings. If provided together with deprecated
+                top-level parameters, the ``settings`` values take precedence.
+            inference_on_context_initialization: Whether to generate a response when context
+                is first set. Defaults to True.
+            file_api_base_url: Base URL for the Gemini File API. Defaults to the official endpoint.
+            http_options: HTTP options for the client.
+            **kwargs: Additional arguments passed to parent GeminiLiveLLMService.
+        """
+        # Check if user incorrectly passed api_key, which is used by parent
+        # class but not here.
+        if "api_key" in kwargs:
+            logger.error(
+                "GeminiLiveVertexLLMService does not accept 'api_key' parameter. "
+                "Use 'credentials' or 'credentials_path' instead for Vertex AI authentication."
+            )
+            raise ValueError(
+                "Invalid parameter 'api_key'. Use 'credentials' or 'credentials_path' for Vertex AI authentication."
+            )
+
+        # These need to be set before calling super().__init__() because
+        # super().__init__() invokes create_client(), which needs these.
+        self._credentials = self._get_credentials(credentials, credentials_path)
+        self._project_id = project_id
+        self._location = location
+
+        # Build default_settings from deprecated args, then apply settings delta.
+        # We pass settings= to super() instead of model=/params= to avoid
+        # double deprecation warnings from the parent.
+
+        # 1. Initialize default_settings with hardcoded defaults
+        default_settings = GeminiLiveVertexLLMSettings(
+            model="google/gemini-live-2.5-flash-native-audio",
+            voice="Charon",
+            frequency_penalty=None,
+            max_tokens=4096,
+            presence_penalty=None,
+            temperature=None,
+            top_k=None,
+            top_p=None,
+            seed=None,
+            filter_incomplete_user_turns=False,
+            user_turn_completion_config=None,
+            modalities=GeminiModalities.AUDIO,
+            language="en-US",
+            media_resolution=GeminiMediaResolution.UNSPECIFIED,
+            vad=None,
+            context_window_compression={},
+            thinking={},
+            enable_affective_dialog=False,
+            proactivity={},
+            extra={},
+        )
+
+        # 2. Apply direct init arg overrides (deprecated)
+        if model is not None:
+            _warn_deprecated_param("model", GeminiLiveVertexLLMSettings, "model")
+            default_settings.model = model
+        if voice_id != "Charon":
+            _warn_deprecated_param("voice_id", GeminiLiveVertexLLMSettings, "voice")
+            default_settings.voice = voice_id
+
+        # 3. Apply params overrides — only if settings not provided
+        if params is not None:
+            _warn_deprecated_param("params", GeminiLiveVertexLLMSettings)
+            if not settings:
+                default_settings.frequency_penalty = params.frequency_penalty
+                default_settings.max_tokens = params.max_tokens
+                default_settings.presence_penalty = params.presence_penalty
+                default_settings.temperature = params.temperature
+                default_settings.top_k = params.top_k
+                default_settings.top_p = params.top_p
+                default_settings.modalities = params.modalities
+                default_settings.language = (
+                    language_to_gemini_language(params.language) if params.language else "en-US"
+                )
+                default_settings.media_resolution = params.media_resolution
+                default_settings.vad = params.vad
+                default_settings.context_window_compression = (
+                    params.context_window_compression.model_dump()
+                    if params.context_window_compression
+                    else {}
+                )
+                default_settings.thinking = params.thinking or {}
+                default_settings.enable_affective_dialog = params.enable_affective_dialog or False
+                default_settings.proactivity = params.proactivity or {}
+                if isinstance(params.extra, dict):
+                    default_settings.extra = params.extra
+
+        # 4. Apply settings delta (canonical API, always wins)
+        if settings is not None:
+            default_settings.apply_update(settings)
+
+        # Call parent constructor with the obtained settings
+        super().__init__(
+            # api_key is required by parent class, but actually not used with
+            # Vertex
+            api_key="dummy",
+            start_audio_paused=start_audio_paused,
+            start_video_paused=start_video_paused,
+            system_instruction=system_instruction,
+            tools=tools,
+            settings=default_settings,
+            inference_on_context_initialization=inference_on_context_initialization,
+            file_api_base_url=file_api_base_url,
+            http_options=http_options,
+            **kwargs,
+        )
+
+    def create_client(self):
+        """Create the Gemini client instance."""
+        self._client = Client(
+            vertexai=True,
+            credentials=self._credentials,
+            project=self._project_id,
+            location=self._location,
+            http_options=self._http_options,
+        )
+
+    @property
+    def file_api(self):
+        """Gemini File API is not supported with Vertex AI."""
+        raise NotImplementedError(
+            "When using Vertex AI, the recommended approach is to use Google Cloud Storage for file handling. The Gemini File API is not directly supported in this context."
+        )
+
+    @staticmethod
+    def _get_credentials(credentials: Optional[str], credentials_path: Optional[str]) -> str:
+        """Retrieve Credentials using Google service account credentials JSON.
+
+        Supports multiple authentication methods:
+        1. Direct JSON credentials string
+        2. Path to service account JSON file
+        3. Default application credentials (ADC)
+
+        Args:
+            credentials: JSON string of service account credentials.
+            credentials_path: Path to the service account JSON file.
+
+        Returns:
+            OAuth token for API authentication.
+
+        Raises:
+            ValueError: If no valid credentials are provided or found.
+        """
+        creds: Optional[service_account.Credentials] = None
+
+        if credentials:
+            # Parse and load credentials from JSON string
+            creds = service_account.Credentials.from_service_account_info(
+                json.loads(credentials),
+                scopes=["https://www.googleapis.com/auth/cloud-platform"],
+            )
+        elif credentials_path:
+            # Load credentials from JSON file
+            creds = service_account.Credentials.from_service_account_file(
+                credentials_path,
+                scopes=["https://www.googleapis.com/auth/cloud-platform"],
+            )
+        else:
+            try:
+                creds, project_id = default(
+                    scopes=["https://www.googleapis.com/auth/cloud-platform"]
+                )
+            except GoogleAuthError:
+                pass
+
+        if not creds:
+            raise ValueError("No valid credentials provided.")
+
+        creds.refresh(Request())  # Ensure token is up-to-date, lifetime is 1 hour.
+
+        return creds

src/pipecat/services/google/google.py

@@ -13,12 +13,12 @@ from pipecat.services import DeprecatedModuleProxy
 from .frames import *
 from .image import *
 from .llm import *
-from .llm_openai import *
+from .openai import *
-from .llm_vertex import *
 from .rtvi import *
 from .stt import *
 from .tts import *
+from .vertex import *
 
 sys.modules[__name__] = DeprecatedModuleProxy(
-    globals(), "google", "google.[frames,image,llm,llm_openai,llm_vertex,rtvi,stt,tts]"
+    globals(), "google", "google.[frames,image,llm,openai,vertex,rtvi,stt,tts]"
 )

src/pipecat/services/google/llm_openai.py

@@ -4,211 +4,15 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""Google LLM service using OpenAI-compatible API format.
+"""Deprecated: use ``pipecat.services.google.openai.llm`` instead."""
 
-This module provides integration with Google's AI LLM models using the OpenAI
+import warnings
-API format through Google's Gemini API OpenAI compatibility layer.
-"""
 
-import json
+warnings.warn(
-import os
+    "Module `pipecat.services.google.llm_openai` is deprecated, "
-from dataclasses import dataclass
+    "use `pipecat.services.google.openai.llm` instead.",
-from typing import Optional
+    DeprecationWarning,
+    stacklevel=2,
+)
 
-from openai import AsyncStream
+from pipecat.services.google.openai.llm import *  # noqa: E402, F401, F403
-from openai.types.chat import ChatCompletionChunk
-
-from pipecat.services.llm_service import FunctionCallFromLLM
-
-# Suppress gRPC fork warnings
-os.environ["GRPC_ENABLE_FORK_SUPPORT"] = "false"
-
-from loguru import logger
-
-from pipecat.frames.frames import LLMTextFrame
-from pipecat.metrics.metrics import LLMTokenUsage
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.openai.base_llm import OpenAILLMSettings
-from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.services.settings import _warn_deprecated_param
-
-
-@dataclass
-class GoogleOpenAILLMSettings(OpenAILLMSettings):
-    """Settings for GoogleLLMOpenAIBetaService."""
-
-    pass
-
-
-class GoogleLLMOpenAIBetaService(OpenAILLMService):
-    """Google LLM service using OpenAI-compatible API format.
-
-    This service provides access to Google's AI LLM models (like Gemini) through
-    the OpenAI API format. It handles streaming responses, function calls, and
-    tool usage while maintaining compatibility with OpenAI's interface.
-
-    Note: This service includes a workaround for a Google API bug where function
-    call indices may be incorrectly set to None, resulting in empty function names.
-
-    .. deprecated:: 0.0.82
-        GoogleLLMOpenAIBetaService is deprecated and will be removed in a future version.
-        Use GoogleLLMService instead for better integration with Google's native API.
-
-    Reference:
-        https://ai.google.dev/gemini-api/docs/openai
-    """
-
-    Settings = GoogleOpenAILLMSettings
-    _settings: GoogleOpenAILLMSettings
-
-    def __init__(
-        self,
-        *,
-        api_key: str,
-        base_url: str = "https://generativelanguage.googleapis.com/v1beta/openai/",
-        model: Optional[str] = None,
-        settings: Optional[GoogleOpenAILLMSettings] = None,
-        **kwargs,
-    ):
-        """Initialize the Google LLM service.
-
-        Args:
-            api_key: Google API key for authentication.
-            base_url: Base URL for Google's OpenAI-compatible API.
-            model: Google model name to use (e.g., "gemini-2.0-flash").
-
-                .. deprecated:: 0.0.105
-                    Use ``settings=OpenAILLMSettings(model=...)`` instead.
-
-            settings: Runtime-updatable settings. When provided alongside deprecated
-                parameters, ``settings`` values take precedence.
-            **kwargs: Additional arguments passed to the parent OpenAILLMService.
-        """
-        import warnings
-
-        with warnings.catch_warnings():
-            warnings.simplefilter("always")
-            warnings.warn(
-                "GoogleLLMOpenAIBetaService is deprecated and will be removed in a future version. "
-                "Use GoogleLLMService instead for better integration with Google's native API.",
-                DeprecationWarning,
-                stacklevel=2,
-            )
-
-        # 1. Initialize default_settings with hardcoded defaults
-        default_settings = GoogleOpenAILLMSettings(model="gemini-2.0-flash")
-
-        # 2. Apply direct init arg overrides (deprecated)
-        if model is not None:
-            _warn_deprecated_param("model", GoogleOpenAILLMSettings, "model")
-            default_settings.model = model
-
-        # 3. (No step 3, as there's no params object to apply)
-
-        # 4. Apply settings delta (canonical API, always wins)
-        if settings is not None:
-            default_settings.apply_update(settings)
-
-        super().__init__(api_key=api_key, base_url=base_url, settings=default_settings, **kwargs)
-
-    async def _process_context(self, context: OpenAILLMContext):
-        functions_list = []
-        arguments_list = []
-        tool_id_list = []
-        func_idx = 0
-        function_name = ""
-        arguments = ""
-        tool_call_id = ""
-
-        await self.start_ttfb_metrics()
-
-        chunk_stream: AsyncStream[
-            ChatCompletionChunk
-        ] = await self._stream_chat_completions_specific_context(context)
-
-        # Use context manager to ensure stream is closed on cancellation/exception.
-        # Without this, CancelledError during iteration leaves the underlying socket open.
-        async with chunk_stream:
-            async for chunk in chunk_stream:
-                if chunk.usage:
-                    tokens = LLMTokenUsage(
-                        prompt_tokens=chunk.usage.prompt_tokens or 0,
-                        completion_tokens=chunk.usage.completion_tokens or 0,
-                        total_tokens=chunk.usage.total_tokens or 0,
-                    )
-                    await self.start_llm_usage_metrics(tokens)
-
-                if chunk.choices is None or len(chunk.choices) == 0:
-                    continue
-
-                await self.stop_ttfb_metrics()
-
-                if not chunk.choices[0].delta:
-                    continue
-
-                if chunk.choices[0].delta.tool_calls:
-                    # We're streaming the LLM response to enable the fastest response times.
-                    # For text, we just yield each chunk as we receive it and count on consumers
-                    # to do whatever coalescing they need (eg. to pass full sentences to TTS)
-                    #
-                    # If the LLM is a function call, we'll do some coalescing here.
-                    # If the response contains a function name, we'll yield a frame to tell consumers
-                    # that they can start preparing to call the function with that name.
-                    # We accumulate all the arguments for the rest of the streamed response, then when
-                    # the response is done, we package up all the arguments and the function name and
-                    # yield a frame containing the function name and the arguments.
-                    logger.debug(f"Tool call: {chunk.choices[0].delta.tool_calls}")
-                    tool_call = chunk.choices[0].delta.tool_calls[0]
-                    if tool_call.index != func_idx:
-                        functions_list.append(function_name)
-                        arguments_list.append(arguments)
-                        tool_id_list.append(tool_call_id)
-                        function_name = ""
-                        arguments = ""
-                        tool_call_id = ""
-                        func_idx += 1
-                    if tool_call.function and tool_call.function.name:
-                        function_name += tool_call.function.name
-                        tool_call_id = tool_call.id
-                    if tool_call.function and tool_call.function.arguments:
-                        # Keep iterating through the response to collect all the argument fragments
-                        arguments += tool_call.function.arguments
-                elif chunk.choices[0].delta.content:
-                    await self.push_frame(LLMTextFrame(chunk.choices[0].delta.content))
-
-        # if we got a function name and arguments, check to see if it's a function with
-        # a registered handler. If so, run the registered callback, save the result to
-        # the context, and re-prompt to get a chat answer. If we don't have a registered
-        # handler, raise an exception.
-        if function_name and arguments:
-            # added to the list as last function name and arguments not added to the list
-            functions_list.append(function_name)
-            arguments_list.append(arguments)
-            tool_id_list.append(tool_call_id)
-
-            logger.debug(
-                f"Function list: {functions_list}, Arguments list: {arguments_list}, Tool ID list: {tool_id_list}"
-            )
-
-            function_calls = []
-            for function_name, arguments, tool_id in zip(
-                functions_list, arguments_list, tool_id_list
-            ):
-                if function_name == "":
-                    # TODO: Remove the _process_context method once Google resolves the bug
-                    # where the index is incorrectly set to None instead of returning the actual index,
-                    # which currently results in an empty function name('').
-                    continue
-
-                arguments = json.loads(arguments)
-
-                function_calls.append(
-                    FunctionCallFromLLM(
-                        context=context,
-                        tool_call_id=tool_id,
-                        function_name=function_name,
-                        arguments=arguments,
-                    )
-                )
-
-            await self.run_function_calls(function_calls)

src/pipecat/services/google/llm_vertex.py

@@ -4,306 +4,15 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""Google Vertex AI LLM service implementation.
+"""Deprecated: use ``pipecat.services.google.vertex.llm`` instead."""
 
-This module provides integration with Google's AI models via Vertex AI,
+import warnings
-extending the GoogleLLMService with Vertex AI authentication.
-"""
 
-import json
+warnings.warn(
-import os
+    "Module `pipecat.services.google.llm_vertex` is deprecated, "
-from dataclasses import dataclass
+    "use `pipecat.services.google.vertex.llm` instead.",
+    DeprecationWarning,
+    stacklevel=2,
+)
 
-# Suppress gRPC fork warnings
+from pipecat.services.google.vertex.llm import *  # noqa: E402, F401, F403
-os.environ["GRPC_ENABLE_FORK_SUPPORT"] = "false"
-
-from typing import Optional
-
-from loguru import logger
-
-from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
-from pipecat.services.settings import _warn_deprecated_param
-
-try:
-    from google.auth import default
-    from google.auth.exceptions import GoogleAuthError
-    from google.auth.transport.requests import Request
-    from google.genai import Client
-    from google.genai.types import HttpOptions
-    from google.oauth2 import service_account
-
-except ModuleNotFoundError as e:
-    logger.error(f"Exception: {e}")
-    logger.error(
-        "In order to use Google AI, you need to `pip install pipecat-ai[google]`. Also, set `GOOGLE_APPLICATION_CREDENTIALS` environment variable."
-    )
-    raise Exception(f"Missing module: {e}")
-
-
-@dataclass
-class GoogleVertexLLMSettings(GoogleLLMSettings):
-    """Settings for GoogleVertexLLMService."""
-
-    pass
-
-
-class GoogleVertexLLMService(GoogleLLMService):
-    """Google Vertex AI LLM service extending GoogleLLMService.
-
-    Provides access to Google's AI models via Vertex AI while using the same
-    Google AI client and message format as GoogleLLMService. Handles authentication
-    using Google service account credentials and configures the client for
-    Vertex AI endpoints.
-
-    Reference:
-        https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference
-    """
-
-    Settings = GoogleVertexLLMSettings
-    _settings: GoogleVertexLLMSettings
-
-    class InputParams(GoogleLLMService.InputParams):
-        """Input parameters specific to Vertex AI.
-
-        Parameters:
-            location: GCP region for Vertex AI endpoint (e.g., "us-east4").
-
-                .. deprecated:: 0.0.90
-                    Use `location` as a direct argument to
-                    `GoogleVertexLLMService.__init__()` instead.
-
-            project_id: Google Cloud project ID.
-
-                .. deprecated:: 0.0.90
-                    Use `project_id` as a direct argument to
-                    `GoogleVertexLLMService.__init__()` instead.
-        """
-
-        # https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations
-        location: Optional[str] = None
-        project_id: Optional[str] = None
-
-        def __init__(self, **kwargs):
-            """Initializes the InputParams."""
-            import warnings
-
-            with warnings.catch_warnings():
-                warnings.simplefilter("always")
-                if "location" in kwargs and kwargs["location"] is not None:
-                    warnings.warn(
-                        "GoogleVertexLLMService.InputParams.location is deprecated. "
-                        "Please provide 'location' as a direct argument to GoogleVertexLLMService.__init__() instead.",
-                        DeprecationWarning,
-                        stacklevel=2,
-                    )
-
-                if "project_id" in kwargs and kwargs["project_id"] is not None:
-                    warnings.warn(
-                        "GoogleVertexLLMService.InputParams.project_id is deprecated. "
-                        "Please provide 'project_id' as a direct argument to GoogleVertexLLMService.__init__() instead.",
-                        DeprecationWarning,
-                        stacklevel=2,
-                    )
-            super().__init__(**kwargs)
-
-    def __init__(
-        self,
-        *,
-        credentials: Optional[str] = None,
-        credentials_path: Optional[str] = None,
-        model: Optional[str] = None,
-        location: Optional[str] = None,
-        project_id: Optional[str] = None,
-        params: Optional[GoogleLLMService.InputParams] = None,
-        settings: Optional[GoogleVertexLLMSettings] = None,
-        system_instruction: Optional[str] = None,
-        tools: Optional[list] = None,
-        tool_config: Optional[dict] = None,
-        http_options: Optional[HttpOptions] = None,
-        **kwargs,
-    ):
-        """Initializes the VertexLLMService.
-
-        Args:
-            credentials: JSON string of service account credentials.
-            credentials_path: Path to the service account JSON file.
-            model: Model identifier (e.g., "gemini-2.5-flash").
-
-                .. deprecated:: 0.0.105
-                    Use ``settings=GoogleLLMSettings(model=...)`` instead.
-
-            location: GCP region for Vertex AI endpoint (e.g., "us-east4").
-            project_id: Google Cloud project ID.
-            params: Input parameters for the model.
-
-                .. deprecated:: 0.0.105
-                    Use ``settings=GoogleLLMSettings(...)`` instead.
-
-            settings: Runtime-updatable settings for this service.  When both
-                deprecated parameters and *settings* are provided, *settings*
-                values take precedence.
-            system_instruction: System instruction/prompt for the model.
-
-                .. deprecated:: 0.0.105
-                    Use ``settings=GoogleVertexLLMSettings(system_instruction=...)`` instead.
-            tools: List of available tools/functions.
-            tool_config: Configuration for tool usage.
-            http_options: HTTP options for the client.
-            **kwargs: Additional arguments passed to GoogleLLMService.
-        """
-        # Check if user incorrectly passed api_key, which is used by parent
-        # class but not here.
-        if "api_key" in kwargs:
-            logger.error(
-                "GoogleVertexLLMService does not accept 'api_key' parameter. "
-                "Use 'credentials' or 'credentials_path' instead for Vertex AI authentication."
-            )
-            raise ValueError(
-                "Invalid parameter 'api_key'. Use 'credentials' or 'credentials_path' for Vertex AI authentication."
-            )
-
-        # Handle deprecated InputParams fields (location/project_id extraction
-        # must happen before validation, regardless of settings)
-        if params and isinstance(params, GoogleVertexLLMService.InputParams):
-            if project_id is None:
-                project_id = params.project_id
-            if location is None:
-                location = params.location
-            # Convert to base InputParams
-            params = GoogleLLMService.InputParams(
-                **params.model_dump(exclude={"location", "project_id"}, exclude_unset=True)
-            )
-
-        # Validate project_id and location parameters
-        # NOTE: once we remove Vertex-specific InputParams class, we can update
-        #       __init__() signature as follows:
-        #       - location: str = "us-east4",
-        #       - project_id: str,
-        #       But for now, we need them as-is to maintain proper backward
-        #       compatibility.
-        if project_id is None:
-            raise ValueError("project_id is required")
-        if location is None:
-            # If location is not provided, default to "us-east4".
-            # Note: this is legacy behavior; ideally location would be
-            # required.
-            logger.warning("location is not provided. Defaulting to 'us-east4'.")
-            location = "us-east4"  # Default location if not provided
-
-        # These need to be set before calling super().__init__() because
-        # super().__init__() invokes _create_client(), which needs these.
-        self._credentials = self._get_credentials(credentials, credentials_path)
-        self._project_id = project_id
-        self._location = location
-
-        # 1. Initialize default_settings with hardcoded defaults
-        default_settings = GoogleVertexLLMSettings(
-            model="gemini-2.5-flash",
-            system_instruction=None,
-            max_tokens=4096,
-            temperature=None,
-            top_k=None,
-            top_p=None,
-            frequency_penalty=None,
-            presence_penalty=None,
-            seed=None,
-            filter_incomplete_user_turns=False,
-            user_turn_completion_config=None,
-            thinking=None,
-            extra={},
-        )
-
-        # 2. Apply direct init arg overrides (deprecated)
-        if model is not None:
-            _warn_deprecated_param("model", GoogleVertexLLMSettings, "model")
-            default_settings.model = model
-        if system_instruction is not None:
-            _warn_deprecated_param(
-                "system_instruction", GoogleVertexLLMSettings, "system_instruction"
-            )
-            default_settings.system_instruction = system_instruction
-
-        # 3. Apply params overrides — only if settings not provided
-        if params is not None:
-            _warn_deprecated_param("params", GoogleVertexLLMSettings)
-            if not settings:
-                default_settings.max_tokens = params.max_tokens
-                default_settings.temperature = params.temperature
-                default_settings.top_k = params.top_k
-                default_settings.top_p = params.top_p
-                default_settings.thinking = params.thinking
-                if isinstance(params.extra, dict):
-                    default_settings.extra = params.extra
-
-        # 4. Apply settings delta (canonical API, always wins)
-        if settings is not None:
-            default_settings.apply_update(settings)
-
-        # Call parent constructor with dummy api_key
-        # (api_key is required by parent class, but not actually used with Vertex)
-        super().__init__(
-            api_key="dummy",
-            settings=default_settings,
-            tools=tools,
-            tool_config=tool_config,
-            http_options=http_options,
-            **kwargs,
-        )
-
-    def create_client(self):
-        """Create the Gemini client instance configured for Vertex AI."""
-        self._client = Client(
-            vertexai=True,
-            credentials=self._credentials,
-            project=self._project_id,
-            location=self._location,
-            http_options=self._http_options,
-        )
-
-    @staticmethod
-    def _get_credentials(credentials: Optional[str], credentials_path: Optional[str]):
-        """Retrieve Credentials using Google service account credentials.
-
-        Supports multiple authentication methods:
-        1. Direct JSON credentials string
-        2. Path to service account JSON file
-        3. Default application credentials (ADC)
-
-        Args:
-            credentials: JSON string of service account credentials.
-            credentials_path: Path to the service account JSON file.
-
-        Returns:
-            Google credentials object for API authentication.
-
-        Raises:
-            ValueError: If no valid credentials are provided or found.
-        """
-        creds: Optional[service_account.Credentials] = None
-
-        if credentials:
-            # Parse and load credentials from JSON string
-            creds = service_account.Credentials.from_service_account_info(
-                json.loads(credentials),
-                scopes=["https://www.googleapis.com/auth/cloud-platform"],
-            )
-        elif credentials_path:
-            # Load credentials from JSON file
-            creds = service_account.Credentials.from_service_account_file(
-                credentials_path,
-                scopes=["https://www.googleapis.com/auth/cloud-platform"],
-            )
-        else:
-            try:
-                creds, project_id = default(
-                    scopes=["https://www.googleapis.com/auth/cloud-platform"]
-                )
-            except GoogleAuthError:
-                pass
-
-        if not creds:
-            raise ValueError("No valid credentials provided.")
-
-        creds.refresh(Request())  # Ensure token is up-to-date, lifetime is 1 hour.
-
-        return creds

src/pipecat/services/google/openai/__init__.py

@@ -0,0 +1,5 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#

src/pipecat/services/google/openai/llm.py

@@ -0,0 +1,214 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Google LLM service using OpenAI-compatible API format.
+
+This module provides integration with Google's AI LLM models using the OpenAI
+API format through Google's Gemini API OpenAI compatibility layer.
+"""
+
+import json
+import os
+from dataclasses import dataclass
+from typing import Optional
+
+from openai import AsyncStream
+from openai.types.chat import ChatCompletionChunk
+
+from pipecat.services.llm_service import FunctionCallFromLLM
+
+# Suppress gRPC fork warnings
+os.environ["GRPC_ENABLE_FORK_SUPPORT"] = "false"
+
+from loguru import logger
+
+from pipecat.frames.frames import LLMTextFrame
+from pipecat.metrics.metrics import LLMTokenUsage
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.openai.base_llm import OpenAILLMSettings
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.settings import _warn_deprecated_param
+
+
+@dataclass
+class GoogleOpenAILLMSettings(OpenAILLMSettings):
+    """Settings for GoogleLLMOpenAIBetaService."""
+
+    pass
+
+
+class GoogleLLMOpenAIBetaService(OpenAILLMService):
+    """Google LLM service using OpenAI-compatible API format.
+
+    This service provides access to Google's AI LLM models (like Gemini) through
+    the OpenAI API format. It handles streaming responses, function calls, and
+    tool usage while maintaining compatibility with OpenAI's interface.
+
+    Note: This service includes a workaround for a Google API bug where function
+    call indices may be incorrectly set to None, resulting in empty function names.
+
+    .. deprecated:: 0.0.82
+        GoogleLLMOpenAIBetaService is deprecated and will be removed in a future version.
+        Use GoogleLLMService instead for better integration with Google's native API.
+
+    Reference:
+        https://ai.google.dev/gemini-api/docs/openai
+    """
+
+    Settings = GoogleOpenAILLMSettings
+    _settings: GoogleOpenAILLMSettings
+
+    def __init__(
+        self,
+        *,
+        api_key: str,
+        base_url: str = "https://generativelanguage.googleapis.com/v1beta/openai/",
+        model: Optional[str] = None,
+        settings: Optional[GoogleOpenAILLMSettings] = None,
+        **kwargs,
+    ):
+        """Initialize the Google LLM service.
+
+        Args:
+            api_key: Google API key for authentication.
+            base_url: Base URL for Google's OpenAI-compatible API.
+            model: Google model name to use (e.g., "gemini-2.0-flash").
+
+                .. deprecated:: 0.0.105
+                    Use ``settings=OpenAILLMSettings(model=...)`` instead.
+
+            settings: Runtime-updatable settings. When provided alongside deprecated
+                parameters, ``settings`` values take precedence.
+            **kwargs: Additional arguments passed to the parent OpenAILLMService.
+        """
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "GoogleLLMOpenAIBetaService is deprecated and will be removed in a future version. "
+                "Use GoogleLLMService instead for better integration with Google's native API.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
+        # 1. Initialize default_settings with hardcoded defaults
+        default_settings = GoogleOpenAILLMSettings(model="gemini-2.0-flash")
+
+        # 2. Apply direct init arg overrides (deprecated)
+        if model is not None:
+            _warn_deprecated_param("model", GoogleOpenAILLMSettings, "model")
+            default_settings.model = model
+
+        # 3. (No step 3, as there's no params object to apply)
+
+        # 4. Apply settings delta (canonical API, always wins)
+        if settings is not None:
+            default_settings.apply_update(settings)
+
+        super().__init__(api_key=api_key, base_url=base_url, settings=default_settings, **kwargs)
+
+    async def _process_context(self, context: OpenAILLMContext):
+        functions_list = []
+        arguments_list = []
+        tool_id_list = []
+        func_idx = 0
+        function_name = ""
+        arguments = ""
+        tool_call_id = ""
+
+        await self.start_ttfb_metrics()
+
+        chunk_stream: AsyncStream[
+            ChatCompletionChunk
+        ] = await self._stream_chat_completions_specific_context(context)
+
+        # Use context manager to ensure stream is closed on cancellation/exception.
+        # Without this, CancelledError during iteration leaves the underlying socket open.
+        async with chunk_stream:
+            async for chunk in chunk_stream:
+                if chunk.usage:
+                    tokens = LLMTokenUsage(
+                        prompt_tokens=chunk.usage.prompt_tokens or 0,
+                        completion_tokens=chunk.usage.completion_tokens or 0,
+                        total_tokens=chunk.usage.total_tokens or 0,
+                    )
+                    await self.start_llm_usage_metrics(tokens)
+
+                if chunk.choices is None or len(chunk.choices) == 0:
+                    continue
+
+                await self.stop_ttfb_metrics()
+
+                if not chunk.choices[0].delta:
+                    continue
+
+                if chunk.choices[0].delta.tool_calls:
+                    # We're streaming the LLM response to enable the fastest response times.
+                    # For text, we just yield each chunk as we receive it and count on consumers
+                    # to do whatever coalescing they need (eg. to pass full sentences to TTS)
+                    #
+                    # If the LLM is a function call, we'll do some coalescing here.
+                    # If the response contains a function name, we'll yield a frame to tell consumers
+                    # that they can start preparing to call the function with that name.
+                    # We accumulate all the arguments for the rest of the streamed response, then when
+                    # the response is done, we package up all the arguments and the function name and
+                    # yield a frame containing the function name and the arguments.
+                    logger.debug(f"Tool call: {chunk.choices[0].delta.tool_calls}")
+                    tool_call = chunk.choices[0].delta.tool_calls[0]
+                    if tool_call.index != func_idx:
+                        functions_list.append(function_name)
+                        arguments_list.append(arguments)
+                        tool_id_list.append(tool_call_id)
+                        function_name = ""
+                        arguments = ""
+                        tool_call_id = ""
+                        func_idx += 1
+                    if tool_call.function and tool_call.function.name:
+                        function_name += tool_call.function.name
+                        tool_call_id = tool_call.id
+                    if tool_call.function and tool_call.function.arguments:
+                        # Keep iterating through the response to collect all the argument fragments
+                        arguments += tool_call.function.arguments
+                elif chunk.choices[0].delta.content:
+                    await self.push_frame(LLMTextFrame(chunk.choices[0].delta.content))
+
+        # if we got a function name and arguments, check to see if it's a function with
+        # a registered handler. If so, run the registered callback, save the result to
+        # the context, and re-prompt to get a chat answer. If we don't have a registered
+        # handler, raise an exception.
+        if function_name and arguments:
+            # added to the list as last function name and arguments not added to the list
+            functions_list.append(function_name)
+            arguments_list.append(arguments)
+            tool_id_list.append(tool_call_id)
+
+            logger.debug(
+                f"Function list: {functions_list}, Arguments list: {arguments_list}, Tool ID list: {tool_id_list}"
+            )
+
+            function_calls = []
+            for function_name, arguments, tool_id in zip(
+                functions_list, arguments_list, tool_id_list
+            ):
+                if function_name == "":
+                    # TODO: Remove the _process_context method once Google resolves the bug
+                    # where the index is incorrectly set to None instead of returning the actual index,
+                    # which currently results in an empty function name('').
+                    continue
+
+                arguments = json.loads(arguments)
+
+                function_calls.append(
+                    FunctionCallFromLLM(
+                        context=context,
+                        tool_call_id=tool_id,
+                        function_name=function_name,
+                        arguments=arguments,
+                    )
+                )
+
+            await self.run_function_calls(function_calls)

src/pipecat/services/google/vertex/__init__.py

@@ -0,0 +1,5 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#

src/pipecat/services/google/vertex/llm.py

@@ -0,0 +1,309 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Google Vertex AI LLM service implementation.
+
+This module provides integration with Google's AI models via Vertex AI,
+extending the GoogleLLMService with Vertex AI authentication.
+"""
+
+import json
+import os
+from dataclasses import dataclass
+
+# Suppress gRPC fork warnings
+os.environ["GRPC_ENABLE_FORK_SUPPORT"] = "false"
+
+from typing import Optional
+
+from loguru import logger
+
+from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
+from pipecat.services.settings import _warn_deprecated_param
+
+try:
+    from google.auth import default
+    from google.auth.exceptions import GoogleAuthError
+    from google.auth.transport.requests import Request
+    from google.genai import Client
+    from google.genai.types import HttpOptions
+    from google.oauth2 import service_account
+
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error(
+        "In order to use Google AI, you need to `pip install pipecat-ai[google]`. Also, set `GOOGLE_APPLICATION_CREDENTIALS` environment variable."
+    )
+    raise Exception(f"Missing module: {e}")
+
+
+@dataclass
+class GoogleVertexLLMSettings(GoogleLLMSettings):
+    """Settings for GoogleVertexLLMService."""
+
+    pass
+
+
+class GoogleVertexLLMService(GoogleLLMService):
+    """Google Vertex AI LLM service extending GoogleLLMService.
+
+    Provides access to Google's AI models via Vertex AI while using the same
+    Google AI client and message format as GoogleLLMService. Handles authentication
+    using Google service account credentials and configures the client for
+    Vertex AI endpoints.
+
+    Reference:
+        https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference
+    """
+
+    Settings = GoogleVertexLLMSettings
+    _settings: GoogleVertexLLMSettings
+
+    class InputParams(GoogleLLMService.InputParams):
+        """Input parameters specific to Vertex AI.
+
+        Parameters:
+            location: GCP region for Vertex AI endpoint (e.g., "us-east4").
+
+                .. deprecated:: 0.0.90
+                    Use `location` as a direct argument to
+                    `GoogleVertexLLMService.__init__()` instead.
+
+            project_id: Google Cloud project ID.
+
+                .. deprecated:: 0.0.90
+                    Use `project_id` as a direct argument to
+                    `GoogleVertexLLMService.__init__()` instead.
+        """
+
+        # https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations
+        location: Optional[str] = None
+        project_id: Optional[str] = None
+
+        def __init__(self, **kwargs):
+            """Initializes the InputParams."""
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                if "location" in kwargs and kwargs["location"] is not None:
+                    warnings.warn(
+                        "GoogleVertexLLMService.InputParams.location is deprecated. "
+                        "Please provide 'location' as a direct argument to GoogleVertexLLMService.__init__() instead.",
+                        DeprecationWarning,
+                        stacklevel=2,
+                    )
+
+                if "project_id" in kwargs and kwargs["project_id"] is not None:
+                    warnings.warn(
+                        "GoogleVertexLLMService.InputParams.project_id is deprecated. "
+                        "Please provide 'project_id' as a direct argument to GoogleVertexLLMService.__init__() instead.",
+                        DeprecationWarning,
+                        stacklevel=2,
+                    )
+            super().__init__(**kwargs)
+
+    def __init__(
+        self,
+        *,
+        credentials: Optional[str] = None,
+        credentials_path: Optional[str] = None,
+        model: Optional[str] = None,
+        location: Optional[str] = None,
+        project_id: Optional[str] = None,
+        params: Optional[GoogleLLMService.InputParams] = None,
+        settings: Optional[GoogleVertexLLMSettings] = None,
+        system_instruction: Optional[str] = None,
+        tools: Optional[list] = None,
+        tool_config: Optional[dict] = None,
+        http_options: Optional[HttpOptions] = None,
+        **kwargs,
+    ):
+        """Initializes the VertexLLMService.
+
+        Args:
+            credentials: JSON string of service account credentials.
+            credentials_path: Path to the service account JSON file.
+            model: Model identifier (e.g., "gemini-2.5-flash").
+
+                .. deprecated:: 0.0.105
+                    Use ``settings=GoogleLLMSettings(model=...)`` instead.
+
+            location: GCP region for Vertex AI endpoint (e.g., "us-east4").
+            project_id: Google Cloud project ID.
+            params: Input parameters for the model.
+
+                .. deprecated:: 0.0.105
+                    Use ``settings=GoogleLLMSettings(...)`` instead.
+
+            settings: Runtime-updatable settings for this service.  When both
+                deprecated parameters and *settings* are provided, *settings*
+                values take precedence.
+            system_instruction: System instruction/prompt for the model.
+
+                .. deprecated:: 0.0.105
+                    Use ``settings=GoogleVertexLLMSettings(system_instruction=...)`` instead.
+            tools: List of available tools/functions.
+            tool_config: Configuration for tool usage.
+            http_options: HTTP options for the client.
+            **kwargs: Additional arguments passed to GoogleLLMService.
+        """
+        # Check if user incorrectly passed api_key, which is used by parent
+        # class but not here.
+        if "api_key" in kwargs:
+            logger.error(
+                "GoogleVertexLLMService does not accept 'api_key' parameter. "
+                "Use 'credentials' or 'credentials_path' instead for Vertex AI authentication."
+            )
+            raise ValueError(
+                "Invalid parameter 'api_key'. Use 'credentials' or 'credentials_path' for Vertex AI authentication."
+            )
+
+        # Handle deprecated InputParams fields (location/project_id extraction
+        # must happen before validation, regardless of settings)
+        if params and isinstance(params, GoogleVertexLLMService.InputParams):
+            if project_id is None:
+                project_id = params.project_id
+            if location is None:
+                location = params.location
+            # Convert to base InputParams
+            params = GoogleLLMService.InputParams(
+                **params.model_dump(exclude={"location", "project_id"}, exclude_unset=True)
+            )
+
+        # Validate project_id and location parameters
+        # NOTE: once we remove Vertex-specific InputParams class, we can update
+        #       __init__() signature as follows:
+        #       - location: str = "us-east4",
+        #       - project_id: str,
+        #       But for now, we need them as-is to maintain proper backward
+        #       compatibility.
+        if project_id is None:
+            raise ValueError("project_id is required")
+        if location is None:
+            # If location is not provided, default to "us-east4".
+            # Note: this is legacy behavior; ideally location would be
+            # required.
+            logger.warning("location is not provided. Defaulting to 'us-east4'.")
+            location = "us-east4"  # Default location if not provided
+
+        # These need to be set before calling super().__init__() because
+        # super().__init__() invokes _create_client(), which needs these.
+        self._credentials = self._get_credentials(credentials, credentials_path)
+        self._project_id = project_id
+        self._location = location
+
+        # 1. Initialize default_settings with hardcoded defaults
+        default_settings = GoogleVertexLLMSettings(
+            model="gemini-2.5-flash",
+            system_instruction=None,
+            max_tokens=4096,
+            temperature=None,
+            top_k=None,
+            top_p=None,
+            frequency_penalty=None,
+            presence_penalty=None,
+            seed=None,
+            filter_incomplete_user_turns=False,
+            user_turn_completion_config=None,
+            thinking=None,
+            extra={},
+        )
+
+        # 2. Apply direct init arg overrides (deprecated)
+        if model is not None:
+            _warn_deprecated_param("model", GoogleVertexLLMSettings, "model")
+            default_settings.model = model
+        if system_instruction is not None:
+            _warn_deprecated_param(
+                "system_instruction", GoogleVertexLLMSettings, "system_instruction"
+            )
+            default_settings.system_instruction = system_instruction
+
+        # 3. Apply params overrides — only if settings not provided
+        if params is not None:
+            _warn_deprecated_param("params", GoogleVertexLLMSettings)
+            if not settings:
+                default_settings.max_tokens = params.max_tokens
+                default_settings.temperature = params.temperature
+                default_settings.top_k = params.top_k
+                default_settings.top_p = params.top_p
+                default_settings.thinking = params.thinking
+                if isinstance(params.extra, dict):
+                    default_settings.extra = params.extra
+
+        # 4. Apply settings delta (canonical API, always wins)
+        if settings is not None:
+            default_settings.apply_update(settings)
+
+        # Call parent constructor with dummy api_key
+        # (api_key is required by parent class, but not actually used with Vertex)
+        super().__init__(
+            api_key="dummy",
+            settings=default_settings,
+            tools=tools,
+            tool_config=tool_config,
+            http_options=http_options,
+            **kwargs,
+        )
+
+    def create_client(self):
+        """Create the Gemini client instance configured for Vertex AI."""
+        self._client = Client(
+            vertexai=True,
+            credentials=self._credentials,
+            project=self._project_id,
+            location=self._location,
+            http_options=self._http_options,
+        )
+
+    @staticmethod
+    def _get_credentials(credentials: Optional[str], credentials_path: Optional[str]):
+        """Retrieve Credentials using Google service account credentials.
+
+        Supports multiple authentication methods:
+        1. Direct JSON credentials string
+        2. Path to service account JSON file
+        3. Default application credentials (ADC)
+
+        Args:
+            credentials: JSON string of service account credentials.
+            credentials_path: Path to the service account JSON file.
+
+        Returns:
+            Google credentials object for API authentication.
+
+        Raises:
+            ValueError: If no valid credentials are provided or found.
+        """
+        creds: Optional[service_account.Credentials] = None
+
+        if credentials:
+            # Parse and load credentials from JSON string
+            creds = service_account.Credentials.from_service_account_info(
+                json.loads(credentials),
+                scopes=["https://www.googleapis.com/auth/cloud-platform"],
+            )
+        elif credentials_path:
+            # Load credentials from JSON file
+            creds = service_account.Credentials.from_service_account_file(
+                credentials_path,
+                scopes=["https://www.googleapis.com/auth/cloud-platform"],
+            )
+        else:
+            try:
+                creds, project_id = default(
+                    scopes=["https://www.googleapis.com/auth/cloud-platform"]
+                )
+            except GoogleAuthError:
+                pass
+
+        if not creds:
+            raise ValueError("No valid credentials provided.")
+
+        creds.refresh(Request())  # Ensure token is up-to-date, lifetime is 1 hour.
+
+        return creds

tests/test_google_llm_openai.py

@@ -15,7 +15,7 @@ import pytest
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 
 try:
-    from pipecat.services.google.llm_openai import GoogleLLMOpenAIBetaService
+    from pipecat.services.google.openai.llm import GoogleLLMOpenAIBetaService
 
     google_available = True
 except Exception: