Praxis CI
bba99418df
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---
Praxis — v0.1 Foundation
Voice-first AI apprenticeship platform. v0.1 is a tech-validation harness (per G-008) for the minimal viable voice loop: a single learner speaks to an AI tutor playing a Customer Service role-play scenario, hears a <600ms-latency response, receives an end-of-session coaching debrief, and has the session logged to SQLite.
Status
Phase 1 (minimal viable voice loop) — code-complete, pending live API keys for runtime verification.
Stack
- Orchestration: Pipecat (D-017) with Silero VAD + interruptibility
- ASR: Deepgram Nova-3 streaming (D-013)
- LLM: Ollama Cloud direct API (D-020) —
gemma4:cloud(role-play) +deepseek-v4-flash:cloudno-think (debrief) - TTS: Cartesia Sonic (primary, D-014) / Piper (self-hosted, R4 mitigation) — behind an interface
- Client: React + Vite + WebRTC (Pipecat client SDK, D-015)
- State: SQLite
praxis.db(D-007, single hardcoded learner, no auth)
Layout
server/ Pipecat pipeline, services (TTS/LLM/Guardrail interfaces), scenario runtime, adapters
client/ React + Vite + WebRTC learner surface
scenarios/ YAML scenario definitions (D-018)
db/ SQLite schema, migrations, async store
scripts/ Latency probes (R1-R4), e2e smoke
tests/ Unit + e2e
docs/ Latency report, debrief templates
Quickstart
- Copy
.env.example→.env, fill inDEEPGRAM_API_KEY,CARTESIA_API_KEY,OLLAMA_API_KEY. - Install server deps:
pip install -e ".[dev]" - Install client deps:
cd client && npm install - Run probes:
python scripts/probe_deepgram.py(etc.) - Run server:
python -m server - Run client:
cd client && npm run dev
See docs/latency-report.md for the R1-R4 spike status and TTS decision.