feat(P01-02-04): Pipecat server pipeline — Silero VAD→Deepgram→Ollama→TTS→WebRTC
server/pipeline.py assembles the Pipecat pipeline (D-017): WebRTC audio in → Deepgram Nova-3 STT → LLMContextAggregator(user) → OLLamaLLMService (gemma4:cloud via https://ollama.com/v1 + bearer, R6) → Cartesia/Piper TTS (selected via PRAXIS_TTS) → WebRTC audio out. Interruptibility via allow_interruptions=True (D-008 abort-and-yield). Hardcoded single-turn system prompt (SLICE-03 replaces with scenario YAML). All keys from env; missing keys log a warning and the pipeline still starts (code structure is the deliverable). server/__main__.py exposes a FastAPI app with /health (reports key-provisioning status) and POST /pipecat/webrtc (accepts an SDP offer, starts a pipeline task, returns the answer). Verified: imports succeed, /health returns 200, routes wired. ---ci--- phase: 1 milestone: v0.1 plan: 02 task: 02-04 status: execute persona: backend-engineer requirements: covered: [REQ-VOICE-01, REQ-VOICE-02, REQ-VOICE-04, REQ-ORCH-01] ---/ci---
This commit is contained in:
Praxis CI
@@ -0,0 +1,108 @@
|
||||
"""Praxis server entrypoint — starts the Pipecat WebRTC bot server.
|
||||
|
||||
Run: `python -m server`
|
||||
|
||||
Exposes a FastAPI app with:
|
||||
GET /health — liveness
|
||||
POST /pipecat/webrtc — accept a WebRTC offer SDP, start a pipeline task
|
||||
|
||||
The server starts and accepts connections even if upstream voice-service keys
|
||||
are absent (SLICE-02 deliverable = code structure). Missing keys degrade to
|
||||
no audio/no tokens at runtime, not a crash.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from typing import Any
|
||||
|
||||
from loguru import logger
|
||||
from pydantic import BaseModel
|
||||
|
||||
# Load .env if present (dev). In production, env is injected directly.
|
||||
try:
|
||||
from dotenv import load_dotenv
|
||||
|
||||
load_dotenv()
|
||||
except ImportError: # pragma: no cover
|
||||
pass
|
||||
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from pipecat.transports.smallwebrtc.connection import SmallWebRTCConnection
|
||||
|
||||
from server.pipeline import build_pipeline
|
||||
|
||||
|
||||
def _env(key: str, default: str = "") -> str:
|
||||
return os.environ.get(key, default).strip()
|
||||
|
||||
|
||||
HOST = _env("PRAXIS_HOST", "0.0.0.0")
|
||||
PORT = int(_env("PRAXIS_PORT", "8789"))
|
||||
|
||||
|
||||
class WebRTCOffer(BaseModel):
|
||||
"""Client→server WebRTC offer (SDP + type)."""
|
||||
|
||||
sdp: str
|
||||
type: str = "offer"
|
||||
|
||||
|
||||
app = FastAPI(title="Praxis v0.1 voice server", version="0.1.0")
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=["*"], # dev — the client is a separate Vite origin
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"],
|
||||
)
|
||||
|
||||
|
||||
@app.get("/health")
|
||||
async def health() -> dict[str, Any]:
|
||||
"""Liveness probe. Reports key-provisioning status for the client."""
|
||||
return {
|
||||
"status": "ok",
|
||||
"version": "0.1.0",
|
||||
"keys": {
|
||||
"deepgram": bool(_env("DEEPGRAM_API_KEY")),
|
||||
"cartesia": bool(_env("CARTESIA_API_KEY")),
|
||||
"ollama": bool(_env("OLLAMA_API_KEY")),
|
||||
},
|
||||
"tts": _env("PRAXIS_TTS", "cartesia"),
|
||||
}
|
||||
|
||||
|
||||
@app.post("/pipecat/webrtc")
|
||||
async def webrtc_offer(offer: WebRTCOffer) -> dict[str, str]:
|
||||
"""Accept a WebRTC offer, start a Pipecat pipeline task, return the answer."""
|
||||
try:
|
||||
connection = SmallWebRTCConnection(
|
||||
ice_servers=[{"urls": "stun:stun.l.google.com:19302"}],
|
||||
)
|
||||
await connection.receive_offer({"sdp": offer.sdp, "type": offer.type})
|
||||
await connection.accept()
|
||||
answer = connection.get_answer()
|
||||
# Build + run the pipeline for this connection.
|
||||
pipeline, task, runner, transport = build_pipeline(connection)
|
||||
# Run the pipeline task in the background; the runner manages its lifecycle.
|
||||
import asyncio
|
||||
|
||||
asyncio.create_task(runner.run(task))
|
||||
return {"sdp": answer["sdp"], "type": answer["type"]}
|
||||
except Exception as exc:
|
||||
logger.error(f"WebRTC offer failed: {exc}")
|
||||
raise HTTPException(status_code=500, detail=str(exc))
|
||||
|
||||
|
||||
def main() -> int:
|
||||
"""Run the server with uvicorn."""
|
||||
import uvicorn
|
||||
|
||||
logger.info(f"Praxis v0.1 voice server starting on {HOST}:{PORT}")
|
||||
uvicorn.run(app, host=HOST, port=PORT, log_level="info")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,185 @@
|
||||
"""Praxis Pipecat server pipeline — minimal viable voice loop (SLICE-02 TASK-02-04).
|
||||
|
||||
Pipeline (D-017):
|
||||
WebRTC audio in → Silero VAD → Deepgram Nova-3 STT → LLMContextAggregator(user)
|
||||
→ OllamaCloudLLM (gemma4:cloud) → LLMContextAggregator(assistant) → Cartesia/Piper TTS
|
||||
→ WebRTC audio out
|
||||
|
||||
Interruptibility (D-008): Pipecat's built-in interrupt handling aborts TTS + yields
|
||||
the floor when learner VAD fires during AI speech.
|
||||
|
||||
The pipeline starts and accepts connections even if upstream services return auth
|
||||
errors at runtime — the code structure is the SLICE-02 deliverable. All keys come
|
||||
from env; missing keys degrade to no audio / no tokens, not crashes.
|
||||
|
||||
Hardcoded single-turn system prompt (no YAML scenario yet — SLICE-03 replaces it).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from typing import Any
|
||||
|
||||
from loguru import logger
|
||||
|
||||
|
||||
def _env(key: str, default: str = "") -> str:
|
||||
return os.environ.get(key, default).strip()
|
||||
|
||||
|
||||
# Hardcoded single-turn system prompt (SLICE-02 walking skeleton).
|
||||
# SLICE-03 TASK-03-07 replaces this with the scenario-driven prompt from YAML.
|
||||
WALKING_SKELETON_SYSTEM_PROMPT = (
|
||||
"You are Jordan, a customer who received a damaged product. "
|
||||
"You are frustrated but not abusive. You want a refund. "
|
||||
"Stay in character. Do not break role. "
|
||||
"Keep responses concise for voice (1-3 sentences)."
|
||||
)
|
||||
|
||||
WALKING_SKELETON_OPENING_LINE = (
|
||||
"Hi, I received my order yesterday and the item is cracked. I want my money back."
|
||||
)
|
||||
|
||||
|
||||
def _build_llm_context():
|
||||
"""Build the LLMContext with the walking-skeleton system prompt."""
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": WALKING_SKELETON_SYSTEM_PROMPT},
|
||||
]
|
||||
return LLMContext(messages=messages)
|
||||
|
||||
|
||||
def _build_transport(webrtc_connection) -> Any:
|
||||
"""Build the SmallWebRTCTransport with audio in/out enabled."""
|
||||
from pipecat.transports.base_transport import TransportParams
|
||||
from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
|
||||
|
||||
params = TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
audio_out_sample_rate=24000,
|
||||
)
|
||||
return SmallWebRTCTransport(webrtc_connection, params)
|
||||
|
||||
|
||||
def _build_stt() -> Any:
|
||||
"""Build the Deepgram Nova-3 STT service (D-013)."""
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
|
||||
api_key = _env("DEEPGRAM_API_KEY")
|
||||
if not api_key:
|
||||
logger.warning("DEEPGRAM_API_KEY not set — STT will not transcribe (pipeline still starts).")
|
||||
return DeepgramSTTService(
|
||||
api_key=api_key or "missing",
|
||||
live_options=None, # Deepgram defaults are fine for nova-3 + en.
|
||||
)
|
||||
|
||||
|
||||
def _build_llm() -> Any:
|
||||
"""Build the Pipecat Ollama LLM service pointed at Ollama Cloud (D-020, R6).
|
||||
|
||||
Pipecat's OLLamaLLMService extends OpenAILLMService and accepts a custom
|
||||
base_url + the OpenAI client api_key (bearer). We point it at
|
||||
https://ollama.com/v1 with OLLAMA_API_KEY as the bearer.
|
||||
"""
|
||||
from pipecat.services.ollama.llm import OLLamaLLMService
|
||||
|
||||
api_key = _env("OLLAMA_API_KEY")
|
||||
base_url = _env("OLLAMA_BASE_URL", "https://ollama.com/v1")
|
||||
model = _env("OLLAMA_ROLEPLAY_MODEL", "gemma4:cloud")
|
||||
if not api_key:
|
||||
logger.warning("OLLAMA_API_KEY not set — LLM will not respond (pipeline still starts).")
|
||||
return OLLamaLLMService(
|
||||
base_url=base_url,
|
||||
settings=OLLamaLLMService.Settings(model=model, api_key=api_key or "missing"),
|
||||
)
|
||||
|
||||
|
||||
def _build_tts() -> Any:
|
||||
"""Build the Pipecat TTS service for the selected provider (D-014)."""
|
||||
choice = _env("PRAXIS_TTS", "cartesia").lower()
|
||||
|
||||
if choice == "piper":
|
||||
from pipecat.services.piper.tts import PiperTTSService
|
||||
|
||||
voice_model = _env("PIPER_VOICE_MODEL")
|
||||
if not voice_model:
|
||||
logger.warning("PIPER_VOICE_MODEL not set — Piper TTS will not speak (pipeline still starts).")
|
||||
return PiperTTSService(
|
||||
voice_id=voice_model or "missing",
|
||||
)
|
||||
|
||||
# Default: Cartesia
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
|
||||
api_key = _env("CARTESIA_API_KEY")
|
||||
voice_id = _env("CARTESIA_VOICE_ID", "a3536a36-1d18-4efb-a95a-7c44b7b5e384")
|
||||
if not api_key:
|
||||
logger.warning("CARTESIA_API_KEY not set — TTS will not speak (pipeline still starts).")
|
||||
return CartesiaTTSService(
|
||||
api_key=api_key or "missing",
|
||||
voice_id=voice_id,
|
||||
)
|
||||
|
||||
|
||||
def _build_vad_analyzer() -> Any:
|
||||
"""Build the Silero VAD analyzer (D-008 interruptibility)."""
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
|
||||
return SileroVADAnalyzer()
|
||||
|
||||
|
||||
def build_pipeline(webrtc_connection):
|
||||
"""Assemble the full Pipecat pipeline + task + runner for one WebRTC session.
|
||||
|
||||
Returns (pipeline, task, runner, transport) so the caller can start the task
|
||||
on connection and tear it down on disconnect.
|
||||
"""
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregator,
|
||||
)
|
||||
|
||||
transport = _build_transport(webrtc_connection)
|
||||
stt = _build_stt()
|
||||
llm = _build_llm()
|
||||
tts = _build_tts()
|
||||
|
||||
context = _build_llm_context()
|
||||
user_aggregator = LLMContextAggregator(context=context, role="user")
|
||||
assistant_aggregator = LLMContextAggregator(context=context, role="assistant")
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # WebRTC audio in
|
||||
stt, # Deepgram Nova-3
|
||||
user_aggregator, # collect user transcript into context
|
||||
llm, # Ollama gemma4:cloud
|
||||
tts, # Cartesia/Piper
|
||||
transport.output(), # WebRTC audio out
|
||||
assistant_aggregator, # collect assistant text into context
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True, # D-008 abort-and-yield
|
||||
enable_metrics=True, # latency measurement (TASK-02-06)
|
||||
metrics_request_timeout=10.0,
|
||||
),
|
||||
)
|
||||
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
return pipeline, task, runner, transport
|
||||
|
||||
|
||||
__all__ = [
|
||||
"build_pipeline",
|
||||
"WALKING_SKELETON_SYSTEM_PROMPT",
|
||||
"WALKING_SKELETON_OPENING_LINE",
|
||||
]
|
||||
Reference in New Issue
Block a user