Renames: remove "multimodal" from Gemini Live types

This commit is contained in:
Paul Kompfner
2025-10-09 09:40:47 -04:00
parent 99f008e927
commit f2d9063984
18 changed files with 1887 additions and 1793 deletions

View File

@@ -17,7 +17,7 @@ from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
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.gemini_live.gemini import GeminiLiveLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
Respond to what the user said in a creative and helpful way.
"""
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction,
voice_id="Puck", # Aoede, Charon, Fenrir, Kore, Puck

View File

@@ -20,7 +20,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.transcript_processor import TranscriptProcessor
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.gemini_live.gemini import GeminiLiveLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -65,7 +65,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
# system_instruction="Talk like a pirate."

View File

@@ -22,7 +22,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
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.gemini_live.gemini import GeminiLiveLLMService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -130,7 +130,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
custom_tools={AdapterType.GEMINI: [search_tool]},
)
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction,
tools=tools,

View File

@@ -24,7 +24,7 @@ from pipecat.runner.utils import (
maybe_capture_participant_camera,
maybe_capture_participant_screen,
)
from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
from pipecat.services.gemini_live.gemini import GeminiLiveLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -58,7 +58,7 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
# system_instruction="Talk like a pirate."

View File

@@ -20,9 +20,9 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.gemini_multimodal_live.gemini import (
GeminiMultimodalLiveLLMService,
GeminiMultimodalModalities,
from pipecat.services.gemini_live.gemini import (
GeminiLiveLLMService,
GeminiModalities,
InputParams,
)
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -82,11 +82,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# KNOWN ISSUE: If using GeminiVertexMultimodalLiveLLMService, it appears
# you cannot specify a modality other than AUDIO.
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=SYSTEM_INSTRUCTION,
tools=[{"google_search": {}}, {"code_execution": {}}],
params=InputParams(modalities=GeminiMultimodalModalities.TEXT),
params=InputParams(modalities=GeminiModalities.TEXT),
)
# Optionally, you can set the response modalities via a function

View File

@@ -19,7 +19,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
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.gemini_live.gemini import GeminiLiveLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -83,7 +83,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
# Initialize the Gemini Multimodal Live model
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Puck", # Aoede, Charon, Fenrir, Kore, Puck
system_instruction=system_instruction,

View File

@@ -19,8 +19,8 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
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.gemini_live.gemini import (
GeminiLiveLLMService,
)
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
"""
# Initialize Gemini service with File API support
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction,
voice_id="Charon", # Aoede, Charon, Fenrir, Kore, Puck

View File

@@ -14,7 +14,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
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.gemini_live.gemini import GeminiLiveLLMService
from pipecat.services.google.frames import LLMSearchResponseFrame
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -105,7 +105,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
custom_tools={AdapterType.GEMINI: [{"google_search": {}}, {"code_execution": {}}]},
)
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=SYSTEM_INSTRUCTION,
voice_id="Charon", # Aoede, Charon, Fenrir, Kore, Puck

View File

@@ -17,8 +17,8 @@ from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
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.gemini_multimodal_live.vertex import GeminiVertexMultimodalLiveLLMService
from pipecat.services.gemini_live.gemini import GeminiLiveLLMService
from pipecat.services.gemini_live.vertex import GeminiLiveVertexLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -66,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
Respond to what the user said in a creative and helpful way.
"""
llm = GeminiVertexMultimodalLiveLLMService(
llm = GeminiLiveVertexLLMService(
credentials=os.getenv("GOOGLE_VERTEX_TEST_CREDENTIALS"),
project_id=os.getenv("GOOGLE_CLOUD_PROJECT_ID"),
location=os.getenv("GOOGLE_CLOUD_LOCATION"),

View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.frame_processor import FrameDirection
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.gemini_live.gemini import GeminiLiveLLMService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -144,7 +144,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
custom_tools={AdapterType.GEMINI: [search_tool]},
)
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction,
tools=tools,

View File

@@ -20,7 +20,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
from pipecat.services.gemini_live import GeminiLiveLLMService
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.daily.transport import DailyParams, DailyTransport
@@ -94,7 +94,7 @@ Respond to what the user said in a creative and helpful way. Keep your responses
async def run_bot(pipecat_transport):
llm = GeminiMultimodalLiveLLMService(
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Puck", # Aoede, Charon, Fenrir, Kore, Puck
transcribe_user_audio=True,