Merge pull request #81 from pipecat-ai/pk/update-gemini-live-imports

Update examples to use `GeminiLiveLLMService` instead of the deprecat…

Author: kompfner

deployment/modal-example/server/src/bot_gemini.py

@@ -6,7 +6,7 @@
 
 """Gemini Bot Implementation.
 
-This module implements a chatbot using Google's Gemini Multimodal Live model.
+This module implements a chatbot using Google's Gemini Live model.
 It includes:
 - Real-time audio/video interaction through Daily
 - Animated robot avatar
@@ -38,7 +38,7 @@
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
-from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.daily.transport import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -108,7 +108,7 @@ async def run_bot(room_url: str, token: str):
 
     Sets up and runs the bot pipeline including:
     - Daily video transport with specific audio parameters
-    - Gemini Live multimodal model integration
+    - Gemini Live model integration
     - Voice activity detection
     - Animation processing
     - RTVI event handling
@@ -129,8 +129,8 @@ async def run_bot(room_url: str, token: str):
         ),
     )
 
-    # Initialize the Gemini Multimodal Live model
-    llm = GeminiMultimodalLiveLLMService(
+    # Initialize the Gemini Live model
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         transcribe_user_audio=True,

instant-voice/server/src/single_bot.py

@@ -17,7 +17,7 @@
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
-from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.daily.transport import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -65,7 +65,7 @@ async def main():
         ),
     )
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         transcribe_user_audio=True,

p2p-webrtc/docker/bot.py

@@ -13,7 +13,7 @@
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
 
@@ -41,7 +41,7 @@ async def run_bot(webrtc_connection):
         ),
     )
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         transcribe_user_audio=True,

p2p-webrtc/video-transform/server/bot.py

@@ -17,7 +17,7 @@
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
-from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
 
@@ -84,7 +84,7 @@ async def run_bot(webrtc_connection):
         webrtc_connection=webrtc_connection, params=transport_params
     )
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         transcribe_user_audio=True,

p2p-webrtc/voice-agent/bot.py

@@ -14,7 +14,7 @@
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
 
@@ -42,7 +42,7 @@ async def run_bot(webrtc_connection):
         ),
     )
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         transcribe_user_audio=True,

simple-chatbot/README.md

@@ -12,7 +12,7 @@ This repository demonstrates a simple AI chatbot with real-time audio/video inte
    - Requires OpenAI API key
 
 2. **Gemini Bot**
-   - Uses Google's Gemini Multimodal Live model
+   - Uses Google's Gemini Live model
    - Requires Gemini API key
 
 ## Six Client Options

simple-chatbot/server/bot-gemini.py

@@ -6,7 +6,7 @@
 
 """Gemini Bot Implementation.
 
-This module implements a chatbot using Google's Gemini Multimodal Live model.
+This module implements a chatbot using Google's Gemini Live model.
 It includes:
 - Real-time audio/video interaction through Daily
 - Animated robot avatar
@@ -37,7 +37,7 @@
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
 from pipecat.runner.types import RunnerArguments
-from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import BaseTransport
 from pipecat.transports.daily.transport import DailyParams, DailyTransport
 
@@ -101,14 +101,14 @@ async def run_bot(transport: BaseTransport):
     """Main bot execution function.
 
     Sets up and runs the bot pipeline including:
-    - Gemini Live multimodal model integration
+    - Gemini Live model integration
     - Voice activity detection
     - Animation processing
     - RTVI event handling
     """
 
-    # Initialize the Gemini Multimodal Live model
-    llm = GeminiMultimodalLiveLLMService(
+    # Initialize the Gemini Live model
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
     )

travel-companion/README.md

@@ -1,6 +1,6 @@
 # Pipecat Travel Companion
 
-Pipecat Travel Companion is a smart travel assistant powered by the `GeminiMultimodalLiveLLMService`. 
+Pipecat Travel Companion is a smart travel assistant powered by the `GeminiLiveLLMService`.
 It offers personalized recommendations and services like checking the weather, suggesting nearby restaurants,
 and providing recent news based on your current location. 
 

travel-companion/server/bot-gemini.py

@@ -6,7 +6,7 @@
 
 """Gemini Travel Companion
 
-This module implements a chatbot using Google's Gemini Multimodal Live model.
+This module implements a chatbot using Google's Gemini Live model.
 It includes:
 - Real-time audio interaction through Daily
 - Function calling
@@ -32,7 +32,7 @@
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 
@@ -47,14 +47,14 @@
         audio_out_enabled=True,
         video_in_enabled=True,
         # set stop_secs to something roughly similar to the internal setting
-        # of the Multimodal Live api, just to align events. This doesn't really
-        # matter because we can only use the Multimodal Live API's phrase
+        # of the Gemini Live api, just to align events. This doesn't really
+        # matter because we can only use the Gemini Live API's phrase
         # endpointing, for now.
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
     ),
 }
 
-# Search tool can only be used together with other tools when using the Multimodal Live API
+# Search tool can only be used together with other tools when using the Gemini Live API
 # Otherwise it should be used alone.
 # We are registering the tools here, but who are handling them is the RTVI client
 get_location_function = FunctionSchema(
@@ -113,14 +113,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     """Main bot execution function.
 
     Sets up and runs the bot pipeline including:
-    - Gemini Live multimodal model integration
+    - Gemini Live model integration
     - Voice activity detection
     - Animation processing
     - RTVI event handling
     """
 
-    # Initialize the Gemini Multimodal Live model
-    llm = GeminiMultimodalLiveLLMService(
+    # Initialize the Gemini Live model
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         system_instruction=system_instruction,

websocket/server/bot_fast_api.py

@@ -16,7 +16,7 @@
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
 from pipecat.serializers.protobuf import ProtobufFrameSerializer
-from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.websocket.fastapi import (
     FastAPIWebsocketParams,
     FastAPIWebsocketTransport,
@@ -51,7 +51,7 @@ async def run_bot(websocket_client):
         ),
     )
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         transcribe_model_audio=True,