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

10
examples/foundational/53-concurrent-llm-rtvi-ignored-sources.py
View File

@@ -33,7 +33,7 @@ from pipecat.runner.types import RunnerArguments
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.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
@@ -75,7 +75,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Main LLM — drives the conversation. Its RTVI events reach the client.
main_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.",
),
)
# Evaluator LLM — silently grades the user's message in the background.
@@ -83,7 +85,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
evaluator_llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
name="EvaluatorLLM",
system_instruction="You are a silent quality evaluator. When given a user message, respond with a single JSON object: {'score': <1-5>, 'reason': '<brief reason>'}. Do not respond conversationally.",
settings=OpenAILLMSettings(
system_instruction="You are a silent quality evaluator. When given a user message, respond with a single JSON object: {'score': <1-5>, 'reason': '<brief reason>'}. Do not respond conversationally.",
),
)
main_context = LLMContext()