wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #1149 from pipecat-ai/mb/update-google-default-llm-model

Browse Source 
Use gemini-2.0-flash-001 as the default model for GoogleLLMService
This commit is contained in:
Mark Backman
2025-02-06 12:41:13 -05:00
committed by GitHub
parent 0efa2711ff 4904f52cee
commit 428e763814
8 changed files with 14 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
CHANGELOG.md
View File

@@ -18,6 +18,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
and should be set manually from the serializer constructor if a different and should be set manually from the serializer constructor if a different
value is needed. value is needed.
### Changed
- Use `gemini-2.0-flash-001` as the default model for `GoogleLLMSerivce`.
## [0.0.55] - 2025-02-05 ## [0.0.55] - 2025-02-05
### Added ### Added

6
examples/foundational/07s-interruptible-google-audio-in.py
View File

@@ -216,11 +216,7 @@ async def main():
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
) )
llm = GoogleLLMService( llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
model="gemini-1.5-flash-latest",
# model="gemini-exp-1114",
api_key=os.getenv("GOOGLE_API_KEY"),
)
messages = [ messages = [
{ {

4
examples/foundational/12a-describe-video-gemini-flash.py
View File

@@ -72,9 +72,7 @@ async def main():
vision_aggregator = VisionImageFrameAggregator() vision_aggregator = VisionImageFrameAggregator()
google = GoogleLLMService( google = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
model="gemini-1.5-flash-latest", api_key=os.getenv("GOOGLE_API_KEY")
)
tts = CartesiaTTSService( tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"), api_key=os.getenv("CARTESIA_API_KEY"),

6
examples/foundational/14e-function-calling-gemini.py
View File

@@ -62,11 +62,7 @@ async def main():
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
) )
llm = GoogleLLMService( llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
model="gemini-1.5-flash-latest",
# model="gemini-exp-1114",
api_key=os.getenv("GOOGLE_API_KEY"),
)
llm.register_function("get_weather", get_weather) llm.register_function("get_weather", get_weather)
llm.register_function("get_image", get_image) llm.register_function("get_image", get_image)

2
examples/foundational/20d-persistent-context-gemini.py
View File

@@ -237,7 +237,7 @@ async def main():
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
) )
llm = GoogleLLMService(model="gemini-1.5-flash-latest", api_key=os.getenv("GOOGLE_API_KEY")) llm = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
# you can either register a single function for all function calls, or specific functions # you can either register a single function for all function calls, or specific functions
# llm.register_function(None, fetch_weather_from_api) # llm.register_function(None, fetch_weather_from_api)

10
examples/foundational/22d-natural-conversation-gemini-audio.py
View File

@@ -55,13 +55,9 @@ load_dotenv(override=True)
logger.remove(0) logger.remove(0)
logger.add(sys.stderr, level="DEBUG") logger.add(sys.stderr, level="DEBUG")
# TRANSCRIBER_MODEL = "gemini-1.5-flash-latest" TRANSCRIBER_MODEL = "gemini-2.0-flash-001"
# CLASSIFIER_MODEL = "gemini-1.5-flash-latest" CLASSIFIER_MODEL = "gemini-2.0-flash-001"
# CONVERSATION_MODEL = "gemini-1.5-flash-latest" CONVERSATION_MODEL = "gemini-2.0-flash-001"
TRANSCRIBER_MODEL = "gemini-2.0-flash-exp"
CLASSIFIER_MODEL = "gemini-2.0-flash-exp"
CONVERSATION_MODEL = "gemini-2.0-flash-exp"
transcriber_system_instruction = """You are an audio transcriber. You are receiving audio from a user. Your job is to transcriber_system_instruction = """You are an audio transcriber. You are receiving audio from a user. Your job is to
transcribe the input audio to text exactly as it was said by the user. transcribe the input audio to text exactly as it was said by the user.

4
examples/foundational/25-google-audio-in.py
View File

@@ -292,7 +292,7 @@ async def main():
conversation_llm = GoogleLLMService( conversation_llm = GoogleLLMService(
name="Conversation", name="Conversation",
model="gemini-1.5-flash-latest", model="gemini-2.0-flash-001",
# model="gemini-exp-1121", # model="gemini-exp-1121",
api_key=os.getenv("GOOGLE_API_KEY"), api_key=os.getenv("GOOGLE_API_KEY"),
# we can give the GoogleLLMService a system instruction to use directly # we can give the GoogleLLMService a system instruction to use directly
@@ -303,7 +303,7 @@ async def main():
input_transcription_llm = GoogleLLMService( input_transcription_llm = GoogleLLMService(
name="Transcription", name="Transcription",
model="gemini-1.5-flash-latest", model="gemini-2.0-flash-001",
# model="gemini-exp-1121", # model="gemini-exp-1121",
api_key=os.getenv("GOOGLE_API_KEY"), api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=transcriber_system_message, system_instruction=transcriber_system_message,

2
src/pipecat/services/google/google.py
View File

@@ -639,7 +639,7 @@ class GoogleLLMService(LLMService):
self, self,
*, *,
api_key: str, api_key: str,
model: str = "gemini-1.5-flash-latest", model: str = "gemini-2.0-flash-001",
params: InputParams = InputParams(), params: InputParams = InputParams(),
system_instruction: Optional[str] = None, system_instruction: Optional[str] = None,
tools: Optional[List[Dict[str, Any]]] = None, tools: Optional[List[Dict[str, Any]]] = None,