Update examples

examples/foundational/07r-interruptible-nvidia.py

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.nvidia.llm import NvidiaLLMService
+from pipecat.services.nvidia.llm import NvidiaLLMService, NvidiaLLMSettings
 from pipecat.services.nvidia.stt import NvidiaSTTService
 from pipecat.services.nvidia.tts import NvidiaTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,7 +56,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = NvidiaLLMService(
         api_key=os.getenv("NVIDIA_API_KEY"),
-        model="meta/llama-3.3-70b-instruct",
+        settings=NvidiaLLMSettings(
+            model="meta/llama-3.3-70b-instruct",
+        ),
         system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )