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

Move system_instruction into LLMSettings

Browse Source 
Add `system_instruction` field to `LLMSettings` so it is runtime-updatable via settings.
For Google (GoogleLLMService, GoogleVertexLLMService), deprecate the init-time arg since it was already shipped. For Anthropic, AWS Bedrock, and OpenAI, remove the init-time arg entirely since it was never shipped.

Add system instruction prepend logic to `build_chat_completion_params` overrides in Cerebras, SambaNova, Fireworks, Mistral, and Perplexity, which build params from scratch rather than calling `super()`.

Still need to handle realtime services (OpenAI Realtime, Grok Realtime, Gemini Live).
This commit is contained in:
Paul Kompfner
2026-03-05 14:03:32 -05:00
parent 1fcae91e5d
commit 560d2306e8
223 changed files with 860 additions and 424 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/foundational/53-concurrent-llm-evaluation.py
View File

@@ -27,7 +27,7 @@ from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.groq.llm import GroqLLMService, GroqLLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -69,13 +69,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
openai_llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
groq_llm = GroqLLMService(
api_key=os.getenv("GROQ_API_KEY"),
settings=GroqLLMSettings(model="meta-llama/llama-4-maverick-17b-128e-instruct"),
system_instruction="You are a very helpful assistant. Your goal is to demonstrate your capabilities in detail in a creative and helpful way.",
settings=GroqLLMSettings(
model="meta-llama/llama-4-maverick-17b-128e-instruct",
system_instruction="You are a very helpful assistant. Your goal is to demonstrate your capabilities in detail in a creative and helpful way.",
),
)
openai_context = LLMContext()