From d8ac6f2c1a8713dadcd5b75ad65f2d6c68570d00 Mon Sep 17 00:00:00 2001 From: Joyce Er Date: Wed, 3 Sep 2025 12:23:36 -0700 Subject: [PATCH 1/3] fix: update default Cerebras model to Qwen 3 32B --- src/pipecat/services/cerebras/llm.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/pipecat/services/cerebras/llm.py b/src/pipecat/services/cerebras/llm.py index 5d6690d73..bdbc51896 100644 --- a/src/pipecat/services/cerebras/llm.py +++ b/src/pipecat/services/cerebras/llm.py @@ -26,7 +26,7 @@ class CerebrasLLMService(OpenAILLMService): *, api_key: str, base_url: str = "https://api.cerebras.ai/v1", - model: str = "llama-3.3-70b", + model: str = "qwen-3-32b", **kwargs, ): """Initialize the Cerebras LLM service. @@ -34,7 +34,7 @@ class CerebrasLLMService(OpenAILLMService): Args: api_key: The API key for accessing Cerebras's API. base_url: The base URL for Cerebras API. Defaults to "https://api.cerebras.ai/v1". - model: The model identifier to use. Defaults to "llama-3.3-70b". + model: The model identifier to use. Defaults to "qwen-3-32b". **kwargs: Additional keyword arguments passed to OpenAILLMService. """ super().__init__(api_key=api_key, base_url=base_url, model=model, **kwargs) From a001f6f193360a454d5850310e475af9cb7b346d Mon Sep 17 00:00:00 2001 From: Joyce Er Date: Wed, 3 Sep 2025 14:00:27 -0700 Subject: [PATCH 2/3] Switch to GPT-OSS-120B --- CHANGELOG.md | 2 ++ examples/foundational/14k-function-calling-cerebras.py | 2 +- src/pipecat/services/cerebras/llm.py | 4 ++-- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 78322bcc0..fca14487b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -90,6 +90,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Updated `RimeTTSService`'s flush_audio message to conform with Rime's official API. +- - Updated the default model for `CerebrasLLMService` to GPT-OSS-120B. + ### Removed - Remove `StopInterruptionFrame`. This was a legacy frame that was not being diff --git a/examples/foundational/14k-function-calling-cerebras.py b/examples/foundational/14k-function-calling-cerebras.py index e30b8f854..ec5f57241 100644 --- a/examples/foundational/14k-function-calling-cerebras.py +++ b/examples/foundational/14k-function-calling-cerebras.py @@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady ) - llm = CerebrasLLMService(api_key=os.getenv("CEREBRAS_API_KEY"), model="llama-3.3-70b") + llm = CerebrasLLMService(api_key=os.getenv("CEREBRAS_API_KEY"), model="gpt-oss-120b") # You can also register a function_name of None to get all functions # sent to the same callback with an additional function_name parameter. llm.register_function("get_current_weather", fetch_weather_from_api) diff --git a/src/pipecat/services/cerebras/llm.py b/src/pipecat/services/cerebras/llm.py index bdbc51896..bf08ff56e 100644 --- a/src/pipecat/services/cerebras/llm.py +++ b/src/pipecat/services/cerebras/llm.py @@ -26,7 +26,7 @@ class CerebrasLLMService(OpenAILLMService): *, api_key: str, base_url: str = "https://api.cerebras.ai/v1", - model: str = "qwen-3-32b", + model: str = "gpt-oss-120b", **kwargs, ): """Initialize the Cerebras LLM service. @@ -34,7 +34,7 @@ class CerebrasLLMService(OpenAILLMService): Args: api_key: The API key for accessing Cerebras's API. base_url: The base URL for Cerebras API. Defaults to "https://api.cerebras.ai/v1". - model: The model identifier to use. Defaults to "qwen-3-32b". + model: The model identifier to use. Defaults to "gpt-oss-120b". **kwargs: Additional keyword arguments passed to OpenAILLMService. """ super().__init__(api_key=api_key, base_url=base_url, model=model, **kwargs) From eba006d39c9de24c70b5d1da0411233b5cde24c5 Mon Sep 17 00:00:00 2001 From: Joyce Er Date: Wed, 3 Sep 2025 14:07:49 -0700 Subject: [PATCH 3/3] Fix nits --- CHANGELOG.md | 2 +- examples/foundational/14k-function-calling-cerebras.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index fca14487b..d84662857 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -90,7 +90,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Updated `RimeTTSService`'s flush_audio message to conform with Rime's official API. -- - Updated the default model for `CerebrasLLMService` to GPT-OSS-120B. +- Updated the default model for `CerebrasLLMService` to GPT-OSS-120B. ### Removed diff --git a/examples/foundational/14k-function-calling-cerebras.py b/examples/foundational/14k-function-calling-cerebras.py index ec5f57241..642880dd0 100644 --- a/examples/foundational/14k-function-calling-cerebras.py +++ b/examples/foundational/14k-function-calling-cerebras.py @@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady ) - llm = CerebrasLLMService(api_key=os.getenv("CEREBRAS_API_KEY"), model="gpt-oss-120b") + llm = CerebrasLLMService(api_key=os.getenv("CEREBRAS_API_KEY")) # You can also register a function_name of None to get all functions # sent to the same callback with an additional function_name parameter. llm.register_function("get_current_weather", fetch_weather_from_api)