Merge branch 'dev' into audio_upload_extend

AnkushMalaker · AnkushMalaker · commit e393250d2e4f · 2025-12-18T19:33:24.000Z
diff --git a/.github/workflows/advanced-docker-compose-build.yml b/.github/workflows/advanced-docker-compose-build.yml
@@ -199,7 +199,7 @@ jobs:
           cd ../../extras/asr-services
           for cuda_variant in cu121 cu126 cu128; do
             echo "Building parakeet-asr-${cuda_variant}"
-            export CUDA_VERSION="${cuda_variant}"
+            export PYTORCH_CUDA_VERSION="${cuda_variant}"
             docker compose build parakeet-asr
             
             img_id=$(docker compose images -q parakeet-asr | head -n1)
diff --git a/.github/workflows/robot-tests.yml b/.github/workflows/robot-tests.yml
@@ -63,10 +63,14 @@ jobs:
         python-version: "3.12"
         cache: 'pip'
 
+    - name: Install uv
+      uses: astral-sh/setup-uv@v4
+      with:
+        version: "latest"
+
     - name: Install Robot Framework and dependencies
       run: |
-        pip install --upgrade pip
-        pip install robotframework robotframework-requests python-dotenv websockets
+        uv pip install --system robotframework robotframework-requests python-dotenv websockets
 
     - name: Create test environment file
       working-directory: tests/setup
diff --git a/Docs/init-system.md b/Docs/init-system.md
@@ -148,13 +148,33 @@ uv run --with-requirements setup-requirements.txt python services.py start backe
 # Check service status
 uv run --with-requirements setup-requirements.txt python services.py status
 
+# Restart all services
+uv run --with-requirements setup-requirements.txt python services.py restart --all
+
+# Restart specific services
+uv run --with-requirements setup-requirements.txt python services.py restart backend
+
 # Stop all services
 uv run --with-requirements setup-requirements.txt python services.py stop --all
 
-# Stop specific services  
+# Stop specific services
 uv run --with-requirements setup-requirements.txt python services.py stop asr-services openmemory-mcp
 ```
 
+**Convenience Scripts:**
+```bash
+# Quick start (from project root)
+./start.sh
+
+# Quick restart (from project root)
+./restart.sh
+```
+
+**Important Notes:**
+- **Restart** restarts containers without rebuilding - use for configuration changes (.env updates)
+- **For code changes**, use `stop` + `start --build` to rebuild images
+- Example: `uv run --with-requirements setup-requirements.txt python services.py stop --all && uv run --with-requirements setup-requirements.txt python services.py start --all --build`
+
 ### Manual Service Management
 You can also manage services individually:
 
diff --git a/Docs/ports-and-access.md b/Docs/ports-and-access.md
@@ -101,10 +101,24 @@ uv run --with-requirements setup-requirements.txt python services.py start --all
 # Start only specific services
 uv run --with-requirements setup-requirements.txt python services.py start backend speaker-recognition
 
+# Restart all services
+uv run --with-requirements setup-requirements.txt python services.py restart --all
+
+# Restart specific services
+uv run --with-requirements setup-requirements.txt python services.py restart backend
+
 # Stop all services
 uv run --with-requirements setup-requirements.txt python services.py stop --all
 ```
 
+**Convenience Scripts:**
+```bash
+./start.sh    # Quick start all configured services
+./restart.sh  # Quick restart all configured services
+```
+
+**Important:** Use `restart` for configuration changes (.env updates). For code changes, use `stop` + `start --build` to rebuild images.
+
 ---
 
 ## Microphone Access Requirements
@@ -128,7 +142,7 @@ If you encounter port conflicts:
 1. **Check running services**: `uv run --with-requirements setup-requirements.txt python services.py status`
 2. **Stop conflicting services**: `uv run --with-requirements setup-requirements.txt python services.py stop --all`
 3. **Change ports in .env files** if needed
-4. **Restart services**: `uv run --with-requirements setup-requirements.txt python services.py start --all`
+4. **Restart services**: `uv run --with-requirements setup-requirements.txt python services.py restart --all` or `./restart.sh`
 
 ---
 
diff --git a/backends/advanced/docker-compose.yml b/backends/advanced/docker-compose.yml
@@ -18,7 +18,6 @@ services:
       - MISTRAL_MODEL=${MISTRAL_MODEL}
       - TRANSCRIPTION_PROVIDER=${TRANSCRIPTION_PROVIDER}
       - PARAKEET_ASR_URL=${PARAKEET_ASR_URL}
-      - OFFLINE_ASR_TCP_URI=${OFFLINE_ASR_TCP_URI}
       - OLLAMA_BASE_URL=${OLLAMA_BASE_URL}
       - HF_TOKEN=${HF_TOKEN}
       - SPEAKER_SERVICE_URL=${SPEAKER_SERVICE_URL}
diff --git a/backends/advanced/init.py b/backends/advanced/init.py
@@ -191,7 +191,7 @@ def setup_transcription(self):
                 self.console.print("[yellow][WARNING][/yellow] No API key provided - transcription will not work")
 
         elif choice == "3":
-            self.config["TRANSCRIPTION_PROVIDER"] = "offline"
+            self.config["TRANSCRIPTION_PROVIDER"] = "parakeet"
             self.console.print("[blue][INFO][/blue] Offline Parakeet ASR selected")
             parakeet_url = self.prompt_value("Parakeet ASR URL", "http://host.docker.internal:8767")
             self.config["PARAKEET_ASR_URL"] = parakeet_url
diff --git a/backends/advanced/run-test.sh b/backends/advanced/run-test.sh
@@ -39,33 +39,74 @@ print_info "Advanced Backend Integration Test Runner"
 print_info "========================================"
 
 # Load environment variables (CI or local)
-if [ -f ".env" ] && [ -z "$DEEPGRAM_API_KEY" ]; then
+# Priority: CI environment > .env.test > .env
+if [ -n "$DEEPGRAM_API_KEY" ]; then
+    print_info "Using environment variables from CI/environment..."
+elif [ -f ".env.test" ]; then
+    print_info "Loading environment variables from .env.test..."
+    set -a
+    source .env.test
+    set +a
+elif [ -f ".env" ]; then
     print_info "Loading environment variables from .env..."
     set -a
     source .env
     set +a
-elif [ -n "$DEEPGRAM_API_KEY" ]; then
-    print_info "Using environment variables from CI..."
 else
-    print_error "Neither .env file nor CI environment variables found!"
-    print_info "For local development: cp .env.template .env and configure API keys"
-    print_info "For CI: ensure DEEPGRAM_API_KEY and OPENAI_API_KEY secrets are set"
+    print_error "Neither .env.test nor .env file found, and no environment variables set!"
+    print_info "For local development: cp .env.template .env and configure required API keys"
+    print_info "For CI: ensure required API keys are set based on configured providers"
     exit 1
 fi
 
-# Verify required environment variables
-if [ -z "$DEEPGRAM_API_KEY" ]; then
-    print_error "DEEPGRAM_API_KEY not set"
-    exit 1
-fi
-
-if [ -z "$OPENAI_API_KEY" ]; then
-    print_error "OPENAI_API_KEY not set"
-    exit 1
-fi
-
-print_info "DEEPGRAM_API_KEY length: ${#DEEPGRAM_API_KEY}"
-print_info "OPENAI_API_KEY length: ${#OPENAI_API_KEY}"
+# Verify required environment variables based on configured providers
+TRANSCRIPTION_PROVIDER=${TRANSCRIPTION_PROVIDER:-deepgram}
+LLM_PROVIDER=${LLM_PROVIDER:-openai}
+
+print_info "Configured providers:"
+print_info "  TRANSCRIPTION_PROVIDER: $TRANSCRIPTION_PROVIDER"
+print_info "  LLM_PROVIDER: $LLM_PROVIDER"
+
+# Check transcription provider API key
+case "$TRANSCRIPTION_PROVIDER" in
+    deepgram)
+        if [ -z "$DEEPGRAM_API_KEY" ]; then
+            print_error "DEEPGRAM_API_KEY not set (required for TRANSCRIPTION_PROVIDER=deepgram)"
+            exit 1
+        fi
+        print_info "DEEPGRAM_API_KEY length: ${#DEEPGRAM_API_KEY}"
+        ;;
+    mistral)
+        if [ -z "$MISTRAL_API_KEY" ]; then
+            print_error "MISTRAL_API_KEY not set (required for TRANSCRIPTION_PROVIDER=mistral)"
+            exit 1
+        fi
+        print_info "MISTRAL_API_KEY length: ${#MISTRAL_API_KEY}"
+        ;;
+    offline|parakeet)
+        print_info "Using offline/local transcription - no API key required"
+        ;;
+    *)
+        print_warning "Unknown TRANSCRIPTION_PROVIDER: $TRANSCRIPTION_PROVIDER"
+        ;;
+esac
+
+# Check LLM provider API key (for memory extraction)
+case "$LLM_PROVIDER" in
+    openai)
+        if [ -z "$OPENAI_API_KEY" ]; then
+            print_error "OPENAI_API_KEY not set (required for LLM_PROVIDER=openai)"
+            exit 1
+        fi
+        print_info "OPENAI_API_KEY length: ${#OPENAI_API_KEY}"
+        ;;
+    ollama)
+        print_info "Using Ollama for LLM - no API key required"
+        ;;
+    *)
+        print_warning "Unknown LLM_PROVIDER: $LLM_PROVIDER"
+        ;;
+esac
 
 # Ensure memory_config.yaml exists
 if [ ! -f "memory_config.yaml" ] && [ -f "memory_config.yaml.template" ]; then
@@ -119,9 +160,19 @@ export DOCKER_BUILDKIT=0
 
 # Run the integration test with extended timeout (mem0 needs time for comprehensive extraction)
 print_info "Starting integration test (timeout: 15 minutes)..."
-timeout 900 uv run pytest tests/test_integration.py::test_full_pipeline_integration -v -s --tb=short --log-cli-level=INFO
+if timeout 900 uv run pytest tests/test_integration.py::test_full_pipeline_integration -v -s --tb=short --log-cli-level=INFO; then
+    print_success "Integration tests completed successfully!"
+else
+    TEST_EXIT_CODE=$?
+    print_error "Integration tests FAILED with exit code: $TEST_EXIT_CODE"
 
-print_success "Integration tests completed successfully!"
+    # Clean up test containers before exiting
+    print_info "Cleaning up test containers after failure..."
+    docker compose -f docker-compose-test.yml down -v || true
+    docker system prune -f || true
+
+    exit $TEST_EXIT_CODE
+fi
 
 # Clean up test containers
 print_info "Cleaning up test containers..."
diff --git a/backends/advanced/src/advanced_omi_backend/controllers/websocket_controller.py b/backends/advanced/src/advanced_omi_backend/controllers/websocket_controller.py
@@ -304,13 +304,13 @@ async def _initialize_streaming_session(
 
     # Determine transcription provider from environment
     transcription_provider = os.getenv("TRANSCRIPTION_PROVIDER", "").lower()
-    if transcription_provider in ["offline", "parakeet"]:
+    if transcription_provider == "parakeet":
         provider = "parakeet"
     elif transcription_provider == "deepgram":
         provider = "deepgram"
     else:
         # Auto-detect: prefer Parakeet if URL is set, otherwise Deepgram
-        parakeet_url = os.getenv("PARAKEET_ASR_URL") or os.getenv("OFFLINE_ASR_TCP_URI")
+        parakeet_url = os.getenv("PARAKEET_ASR_URL")
         deepgram_key = os.getenv("DEEPGRAM_API_KEY")
         if parakeet_url:
             provider = "parakeet"
diff --git a/backends/advanced/src/advanced_omi_backend/services/transcription/__init__.py b/backends/advanced/src/advanced_omi_backend/services/transcription/__init__.py
@@ -75,18 +75,6 @@ def get_transcription_provider(
         else:
             return ParakeetProvider(parakeet_url)
 
-    elif provider_name == "offline":
-        # "offline" is an alias for Parakeet ASR
-        if not parakeet_url:
-            raise RuntimeError(
-                "Offline transcription provider requested but PARAKEET_ASR_URL not configured"
-            )
-        logger.info(f"Using offline Parakeet transcription provider in {mode} mode")
-        if mode == "streaming":
-            return ParakeetStreamingProvider(parakeet_url)
-        else:
-            return ParakeetProvider(parakeet_url)
-
     # Auto-select provider based on available configuration (when provider_name is None)
     if provider_name is None:
         # Check TRANSCRIPTION_PROVIDER environment variable first
diff --git a/backends/advanced/src/advanced_omi_backend/services/transcription/parakeet_stream_consumer.py b/backends/advanced/src/advanced_omi_backend/services/transcription/parakeet_stream_consumer.py
@@ -35,9 +35,9 @@ def __init__(self, redis_client, service_url: str = None, buffer_chunks: int = 3
             service_url: Parakeet service URL (defaults to PARAKEET_ASR_URL env var)
             buffer_chunks: Number of chunks to buffer before transcribing (default: 30 = ~7.5s)
         """
-        self.service_url = service_url or os.getenv("PARAKEET_ASR_URL") or os.getenv("OFFLINE_ASR_TCP_URI")
+        self.service_url = service_url or os.getenv("PARAKEET_ASR_URL")
         if not self.service_url:
-            raise ValueError("PARAKEET_ASR_URL or OFFLINE_ASR_TCP_URI is required")
+            raise ValueError("PARAKEET_ASR_URL is required")
 
         # Initialize Parakeet provider
         self.provider = ParakeetProvider(service_url=self.service_url)
diff --git a/backends/advanced/src/advanced_omi_backend/workers/audio_stream_parakeet_worker.py b/backends/advanced/src/advanced_omi_backend/workers/audio_stream_parakeet_worker.py
@@ -28,9 +28,9 @@ async def main():
     logger.info("🚀 Starting Parakeet audio stream worker")
 
     # Get configuration from environment
-    service_url = os.getenv("PARAKEET_ASR_URL") or os.getenv("OFFLINE_ASR_TCP_URI")
+    service_url = os.getenv("PARAKEET_ASR_URL")
     if not service_url:
-        logger.warning("PARAKEET_ASR_URL or OFFLINE_ASR_TCP_URI environment variable not set - Parakeet audio stream worker will not start")
+        logger.warning("PARAKEET_ASR_URL environment variable not set - Parakeet audio stream worker will not start")
         logger.warning("Audio transcription will use alternative providers if configured")
         return
 
diff --git a/backends/advanced/start-workers.sh b/backends/advanced/start-workers.sh
@@ -62,13 +62,15 @@ start_workers() {
         AUDIO_STREAM_DEEPGRAM_WORKER_PID=""
     fi
 
-    # Only start Parakeet worker if PARAKEET_ASR_URL or OFFLINE_ASR_TCP_URI is set
-    if [ -n "$PARAKEET_ASR_URL" ] || [ -n "$OFFLINE_ASR_TCP_URI" ]; then
+
+    # Only start Parakeet worker if PARAKEET_ASR_URL is set
+    if [ -n "$PARAKEET_ASR_URL" ]; then
+
         echo "🎵 Starting audio stream Parakeet worker (1 worker for sequential processing)..."
         uv run python -m advanced_omi_backend.workers.audio_stream_parakeet_worker &
         AUDIO_STREAM_PARAKEET_WORKER_PID=$!
     else
-        echo "⏭️  Skipping Parakeet stream worker (PARAKEET_ASR_URL/OFFLINE_ASR_TCP_URI not set)"
+        echo "⏭️  Skipping Parakeet stream worker (PARAKEET_ASR_URL not set)"
         AUDIO_STREAM_PARAKEET_WORKER_PID=""
     fi
 
@@ -80,8 +82,8 @@ start_workers() {
     echo "  - RQ worker 5: PID $RQ_WORKER_5_PID (transcription, memory, default)"
     echo "  - RQ worker 6: PID $RQ_WORKER_6_PID (transcription, memory, default)"
     echo "  - Audio persistence worker: PID $AUDIO_PERSISTENCE_WORKER_PID (audio queue - file rotation)"
-    [ -n "$AUDIO_STREAM_DEEPGRAM_WORKER_PID" ] && echo "  - Deepgram stream worker: PID $AUDIO_STREAM_DEEPGRAM_WORKER_PID (real-time transcription)"
-    [ -n "$AUDIO_STREAM_PARAKEET_WORKER_PID" ] && echo "  - Parakeet stream worker: PID $AUDIO_STREAM_PARAKEET_WORKER_PID (real-time transcription)"
+    [ -n "$AUDIO_STREAM_DEEPGRAM_WORKER_PID" ] && echo "  - Audio stream Deepgram worker: PID $AUDIO_STREAM_DEEPGRAM_WORKER_PID (Redis Streams consumer)" || true
+    [ -n "$AUDIO_STREAM_PARAKEET_WORKER_PID" ] && echo "  - Audio stream Parakeet worker: PID $AUDIO_STREAM_PARAKEET_WORKER_PID (Redis Streams consumer)" || true
 }
 
 # Function to check worker registration health
diff --git a/backends/advanced/tests/test_integration.py b/backends/advanced/tests/test_integration.py
@@ -109,7 +109,7 @@
 # Test constants
 BACKEND_URL = "http://localhost:8001"  # Test backend port
 TEST_AUDIO_PATH = tests_dir.parent.parent.parent / "extras/test-audios/DIY Experts Glass Blowing_16khz_mono_4min.wav"
-TEST_AUDIO_PATH_OFFLINE = tests_dir / "assets" / "test_clip_10s.wav"  # Shorter clip for offline testing
+TEST_AUDIO_PATH_PARAKEET = tests_dir / "assets" / "test_clip_10s.wav"  # Shorter clip for parakeet testing
 MAX_STARTUP_WAIT = 60  # seconds
 PROCESSING_TIMEOUT = 300  # seconds for audio processing (5 minutes)
 
@@ -715,8 +715,8 @@ def authenticate(self):
         
     def upload_test_audio(self):
         """Upload test audio file and monitor processing."""
-        # Use different audio file for offline provider
-        audio_path = TEST_AUDIO_PATH_OFFLINE if self.provider == "offline" else TEST_AUDIO_PATH
+        # Use different audio file for parakeet provider (shorter for faster testing)
+        audio_path = TEST_AUDIO_PATH_PARAKEET if self.provider == "parakeet" else TEST_AUDIO_PATH
         
         logger.info(f"📤 Uploading test audio: {audio_path.name}")
         
@@ -1425,21 +1425,21 @@ def test_full_pipeline_integration(test_runner):
         phase_times['service_startup'] = time.time() - phase_start
         logger.info(f"✅ Service startup completed in {phase_times['service_startup']:.2f}s")
         
-        # Phase 2b: ASR service startup (offline only)
+        # Phase 2b: ASR service startup (parakeet only)
         phase_start = time.time()
         logger.info(f"🎤 Phase 2b: Starting ASR services ({TRANSCRIPTION_PROVIDER} provider)...")
         test_runner.start_asr_services()
         phase_times['asr_startup'] = time.time() - phase_start
         logger.info(f"✅ ASR service startup completed in {phase_times['asr_startup']:.2f}s")
-        
+
         # Phase 3: Wait for services
         phase_start = time.time()
         logger.info("⏳ Phase 3: Waiting for services to be ready...")
         test_runner.wait_for_services()
         phase_times['service_readiness'] = time.time() - phase_start
         logger.info(f"✅ Service readiness check completed in {phase_times['service_readiness']:.2f}s")
-        
-        # Phase 3b: Wait for ASR services (offline only)
+
+        # Phase 3b: Wait for ASR services (parakeet only)
         phase_start = time.time()
         logger.info("⏳ Phase 3b: Waiting for ASR services to be ready...")
         test_runner.wait_for_asr_ready()
diff --git a/backends/advanced/uv.lock b/backends/advanced/uv.lock
diff --git a/extras/asr-services/README.md b/extras/asr-services/README.md
diff --git a/extras/asr-services/docker-compose-test.yml b/extras/asr-services/docker-compose-test.yml
diff --git a/extras/asr-services/quickstart.md b/extras/asr-services/quickstart.md
diff --git a/quickstart.md b/quickstart.md
diff --git a/services.py b/services.py
