HF Spaces Deployment Added

.dockerignore

@@ -0,0 +1,22 @@
+venv/
+__pycache__/
+.pytest_cache/
+.git/
+.gitignore
+.env
+*.pyc
+*.pyo
+*.pyd
+.DS_Store
+node_modules/
+dist/
+build/
+*.egg-info/
+.vscode/
+.idea/
+.coverage
+htmlcov/
+*.db
+data/audio_output/
+data/sessions.db
+latency_results.json

.github/workflows/docker-build.yml

@@ -0,0 +1,95 @@
+name: Build and Push Docker Image
+
+on:
+  push:
+    branches:
+      - main
+      - develop
+  pull_request:
+    branches:
+      - main
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=pr
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=sha,prefix={{branch}}-
+            type=raw,value=latest,enable={{is_default_branch}}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Image digest
+        run: echo "Image pushed with digest: ${{ steps.build.outputs.digest }}"
+
+  deploy-to-hf-spaces:
+    needs: build-and-push
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Push to HuggingFace Spaces
+        run: |
+          git config --global credential.helper store
+          echo "https://${{ secrets.HF_USERNAME }}:${{ secrets.HF_TOKEN }}@huggingface.co" > ~/.git-credentials
+          
+          git remote add spaces https://huggingface.co/spaces/${{ secrets.HF_SPACE_REPO }}.git || true
+          git push --force spaces main
+        env:
+          HF_USERNAME: ${{ secrets.HF_USERNAME }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+
+  notify:
+    needs: [build-and-push]
+    runs-on: ubuntu-latest
+    if: always()
+    
+    steps:
+      - name: Build status
+        run: |
+          if [ "${{ needs.build-and-push.result }}" = "success" ]; then
+            echo "✅ Docker image built and pushed successfully!"
+          else
+            echo "❌ Docker build failed"
+          fi

Dockerfile

@@ -0,0 +1,35 @@
+# Voice RAG Bot - Multi-stage Dockerfile
+
+FROM python:3.11-slim as base
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    libsndfile1 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy project files
+COPY . .
+
+# Expose ports
+# 8000 = FastAPI backend
+# 8501 = Streamlit frontend
+EXPOSE 8000 8501
+
+# Create startup script
+RUN echo '#!/bin/bash\n\
+if [ "$APP_TYPE" = "backend" ]; then\n\
+  uvicorn backend.main:app --host 0.0.0.0 --port 8000\n\
+else\n\
+  streamlit run frontend/streamlit_app.py --server.port 8501 --server.address 0.0.0.0\n\
+fi' > /app/start.sh && chmod +x /app/start.sh
+
+CMD ["/app/start.sh"]

README.md

@@ -58,7 +58,219 @@ streamlit run frontend/streamlit_app.py
 
 ---
 
-## 📖 Usage Guide
+## � Docker Deployment
+
+### Option A: Docker Compose (Recommended for Development)
+
+Start all services (Backend + Frontend + Qdrant + Redis):
+```bash
+docker-compose up -d
+```
+
+**Access Points:**
+- 🎤 Frontend: http://localhost:8501
+- ⚙️ Backend: http://localhost:8000
+- 📚 Qdrant: http://localhost:6333
+- 💾 Redis: localhost:6379
+
+**Stop Services:**
+```bash
+docker-compose down
+```
+
+### Option B: Individual Docker Images
+
+**Build Image:**
+```bash
+docker build -t voice-rag-bot:latest .
+```
+
+**Run Backend:**
+```bash
+docker run -p 8000:8000 \
+  -e APP_TYPE=backend \
+  -e GROQ_API_KEY=your_key \
+  -e QDRANT_URL=http://localhost:6333 \
+  voice-rag-bot:latest
+```
+
+**Run Frontend:**
+```bash
+docker run -p 8501:8501 \
+  -e APP_TYPE=frontend \
+  -e GROQ_API_KEY=your_key \
+  -e QDRANT_URL=http://localhost:6333 \
+  voice-rag-bot:latest
+```
+
+---
+
+## 🚀 GitHub Actions CI/CD
+
+### Setup GitHub Secrets
+
+Add these secrets to your GitHub repository (Settings → Secrets and Variables → Actions):
+
+| Secret Name | Value | Description |
+|------------|-------|-------------|
+| `GROQ_API_KEY` | `gsk_xxxxxxxxxxxx` | Groq API key for LLM |
+| `HF_USERNAME` | `your_username` | HuggingFace username |
+| `HF_TOKEN` | `hf_xxxxxxxxxxxx` | HuggingFace access token |
+| `HF_SPACE_REPO` | `username/voice-rag-bot` | HF Spaces repo path |
+
+**How to Add Secrets:**
+1. Go to GitHub repository → Settings
+2. Click "Secrets and variables" → "Actions"
+3. Click "New repository secret"
+4. Add each secret with name and value
+
+### Automatic Deployment
+
+The workflow (`.github/workflows/docker-build.yml`) automatically:
+
+1. **On `main` branch push:**
+   - Builds Docker image
+   - Pushes to GitHub Container Registry (GHCR)
+   - Deploys to HuggingFace Spaces
+   - Generates tags: `main`, `latest`, `sha-xxxxx`
+
+2. **On Pull Request:**
+   - Builds Docker image (no push)
+   - Validates Dockerfile syntax
+   - Tests image build
+
+**Workflow File:**
+- Location: `.github/workflows/docker-build.yml`
+- Triggers: Push to `main`/`develop`, Pull requests
+- Status: View in GitHub → Actions tab
+
+**Access Docker Images:**
+```bash
+docker pull ghcr.io/your-username/voice-rag-bot:latest
+docker pull ghcr.io/your-username/voice-rag-bot:main
+```
+
+---
+
+## 🤗 HuggingFace Spaces Deployment
+
+### Option A: Automatic Deployment (Via GitHub Actions)
+
+1. Create HuggingFace Space: https://huggingface.co/spaces
+   - Name: `voice-rag-bot`
+   - License: OpenRAIL
+   - Private/Public: Your choice
+
+2. Get HF credentials:
+   - Username: Your HF account name
+   - Token: https://huggingface.co/settings/tokens (create "write" token)
+
+3. Add GitHub Secrets (see above):
+   - `HF_USERNAME`
+   - `HF_TOKEN`
+   - `HF_SPACE_REPO` = `username/voice-rag-bot`
+
+4. **Push to main branch → Automatic deployment!**
+
+### Option B: Manual Deployment to HF Spaces
+
+1. **Create HF Space (if not exists):**
+   ```bash
+   huggingface-cli repo create voice-rag-bot --type space --space-sdk streamlit
+   ```
+
+2. **Clone & Push:**
+   ```bash
+   git clone https://huggingface.co/spaces/your-username/voice-rag-bot
+   cd voice-rag-bot
+   
+   # Add your project files
+   cp -r /path/to/voice-rag-bot/* .
+   
+   # Push to HF Spaces
+   git add .
+   git commit -m "Deploy Voice RAG Bot"
+   git push origin main
+   ```
+
+3. **Configure Secrets in HF Spaces:**
+   - Go to Space Settings → Variables and secrets
+   - Add: `GROQ_API_KEY`, `QDRANT_URL`, etc.
+
+4. **App File:** `app.py` (automatically created)
+
+### HF Spaces Configuration (`spaces.yaml`)
+
+```yaml
+title: Voice RAG Bot
+description: Voice-enabled RAG chatbot
+app_file: app.py
+sdk: streamlit
+sdk_version: "1.28.0"
+python_version: "3.11"
+cpu: true
+gpu: true
+startup_duration_timeout: 600
+```
+
+### HF Spaces Requirements
+
+**Note:** HuggingFace Spaces runs Streamlit frontend only (no backend microservices).
+
+**Options:**
+1. **Use External Backend:**
+   - Deploy backend separately (Railway, Render, Heroku)
+   - Update `BACKEND_URL` in Streamlit config
+   - Spaces frontend connects to external backend
+
+2. **Self-contained (Frontend Only):**
+   - Remove backend API calls
+   - Use Streamlit session state for data
+   - Limited functionality (no vector DB, LLM caching)
+
+3. **Docker-based Space (Advanced):**
+   - Deploy full stack in Docker container
+   - Requires HF Spaces Docker runtime
+   - Use `Dockerfile` + `docker-compose.yml`
+
+**Recommended:** Use external FastAPI backend on Render/Railway + Streamlit on HF Spaces
+
+---
+
+## 🔧 Environment Variables for Deployment
+
+### Local Development
+```
+GROQ_API_KEY=gsk_xxxxxxxxxxxx
+QDRANT_URL=http://localhost:6333
+DEBUG=True
+LOG_LEVEL=INFO
+```
+
+### Docker Compose
+```
+GROQ_API_KEY=gsk_xxxxxxxxxxxx
+QDRANT_URL=http://qdrant:6333
+BACKEND_URL=http://backend:8000
+DEBUG=False
+LOG_LEVEL=INFO
+```
+
+### HuggingFace Spaces
+```
+GROQ_API_KEY=gsk_xxxxxxxxxxxx
+BACKEND_URL=https://your-backend-api.herokuapp.com
+FRONTEND_MODE=SPACES
+```
+
+### GitHub Actions (Auto-set)
+- `REGISTRY`: ghcr.io
+- `IMAGE_NAME`: ${{ github.repository }}
+- Secrets: See above
+
+---
+
+## �📖 Usage Guide
 
 ### Via Streamlit Frontend (Recommended)
 

app.py

@@ -0,0 +1,10 @@
+"""HuggingFace Spaces Entry Point - Streamlit Frontend"""
+
+import sys
+from pathlib import Path
+
+# Add project root to path
+sys.path.insert(0, str(Path(__file__).parent))
+
+# Import and run the main Streamlit app
+from frontend.streamlit_app import *

data/latency_results.json

@@ -138,5 +138,141 @@
       "tts_generation": 16.6,
       "workflow_orchestration": 50.1
     }
+  },
+  {
+    "timestamp": "2026-06-03T18:29:39.252430",
+    "total_time_ms": 26031.32,
+    "modules": {
+      "sentiment_analysis": 0.0,
+      "entity_extraction": 2683.74,
+      "intent_detection": 2149.76,
+      "retrieval_router": 13606.48,
+      "context_builder": 0.0,
+      "response_generation": 1417.41,
+      "validation": 0.0,
+      "memory_persistence": 1065.74,
+      "tts_generation": 1723.5,
+      "workflow_orchestration": 26031.32
+    },
+    "breakdown_percent": {
+      "sentiment_analysis": 0.0,
+      "entity_extraction": 5.5,
+      "intent_detection": 4.4,
+      "retrieval_router": 28.0,
+      "context_builder": 0.0,
+      "response_generation": 2.9,
+      "validation": 0.0,
+      "memory_persistence": 2.2,
+      "tts_generation": 3.5,
+      "workflow_orchestration": 53.5
+    }
+  },
+  {
+    "timestamp": "2026-06-03T18:31:59.635819",
+    "total_time_ms": 7009.19,
+    "modules": {
+      "sentiment_analysis": 0.0,
+      "entity_extraction": 570.99,
+      "intent_detection": 1327.92,
+      "retrieval_router": 637.33,
+      "context_builder": 0.0,
+      "response_generation": 1209.4,
+      "validation": 0.0,
+      "memory_persistence": 1075.38,
+      "tts_generation": 2110.23,
+      "workflow_orchestration": 7009.19
+    },
+    "breakdown_percent": {
+      "sentiment_analysis": 0.0,
+      "entity_extraction": 4.1,
+      "intent_detection": 9.5,
+      "retrieval_router": 4.6,
+      "context_builder": 0.0,
+      "response_generation": 8.7,
+      "validation": 0.0,
+      "memory_persistence": 7.7,
+      "tts_generation": 15.1,
+      "workflow_orchestration": 50.3
+    }
+  },
+  {
+    "timestamp": "2026-06-03T18:32:31.131203",
+    "total_time_ms": 5959.28,
+    "modules": {
+      "sentiment_analysis": 0.0,
+      "entity_extraction": 123.39,
+      "intent_detection": 1338.2,
+      "retrieval_router": 298.56,
+      "context_builder": 0.0,
+      "response_generation": 1028.93,
+      "validation": 1.81,
+      "memory_persistence": 1062.51,
+      "tts_generation": 2081.34,
+      "workflow_orchestration": 5959.28
+    },
+    "breakdown_percent": {
+      "sentiment_analysis": 0.0,
+      "entity_extraction": 1.0,
+      "intent_detection": 11.3,
+      "retrieval_router": 2.5,
+      "context_builder": 0.0,
+      "response_generation": 8.7,
+      "validation": 0.0,
+      "memory_persistence": 8.9,
+      "tts_generation": 17.5,
+      "workflow_orchestration": 50.1
+    }
+  },
+  {
+    "timestamp": "2026-06-03T18:36:02.419370",
+    "total_time_ms": 20168.46,
+    "modules": {
+      "sentiment_analysis": 0.0,
+      "validation": 0.0,
+      "entity_extraction": 840.66,
+      "intent_detection": 1772.81,
+      "response_generation": 2562.12,
+      "retrieval_router": 2732.23,
+      "context_builder": 0.0,
+      "memory_persistence": 1871.22,
+      "tts_generation": 4072.96,
+      "workflow_orchestration": 20168.46
+    },
+    "breakdown_percent": {
+      "sentiment_analysis": 0.0,
+      "validation": 0.0,
+      "entity_extraction": 2.5,
+      "intent_detection": 5.2,
+      "response_generation": 7.5,
+      "retrieval_router": 8.0,
+      "context_builder": 0.0,
+      "memory_persistence": 5.5,
+      "tts_generation": 12.0,
+      "workflow_orchestration": 59.3
+    }
+  },
+  {
+    "timestamp": "2026-06-03T18:40:18.536003",
+    "total_time_ms": 421490.8,
+    "modules": {
+      "sentiment_analysis": 0.0,
+      "entity_extraction": 119.72,
+      "intent_detection": 978.72,
+      "retrieval_router": 307.16,
+      "context_builder": 0.0,
+      "response_generation": 3172.24,
+      "validation": 0.0,
+      "workflow_orchestration": 421487.38
+    },
+    "breakdown_percent": {
+      "sentiment_analysis": 0.0,
+      "entity_extraction": 0.0,
+      "intent_detection": 0.2,
+      "retrieval_router": 0.1,
+      "context_builder": 0.0,
+      "response_generation": 0.7,
+      "validation": 0.0,
+      "workflow_orchestration": 98.9
+    }
   }
 ]

docker-compose.yml

@@ -0,0 +1,81 @@
+version: '3.8'
+
+services:
+  # Qdrant Vector Database
+  qdrant:
+    image: qdrant/qdrant:latest
+    ports:
+      - "6333:6333"
+      - "6334:6334"
+    volumes:
+      - qdrant_storage:/qdrant/storage
+    environment:
+      - QDRANT_API_KEY=${QDRANT_API_KEY:-}
+    networks:
+      - voice-rag-network
+
+  # FastAPI Backend
+  backend:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    environment:
+      - APP_TYPE=backend
+      - GROQ_API_KEY=${GROQ_API_KEY}
+      - GROQ_MODEL=${GROQ_MODEL}
+      - QDRANT_URL=http://qdrant:6333
+      - QDRANT_API_KEY=${QDRANT_API_KEY:-}
+      - KB_COLLECTION=${KB_COLLECTION}
+      - HISTORY_COLLECTION=${HISTORY_COLLECTION}
+      - DEBUG=${DEBUG:-True}
+      - LOG_LEVEL=${LOG_LEVEL:-INFO}
+    ports:
+      - "8000:8000"
+    depends_on:
+      - qdrant
+    networks:
+      - voice-rag-network
+    volumes:
+      - ./data:/app/data
+
+  # Streamlit Frontend
+  frontend:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    environment:
+      - APP_TYPE=frontend
+      - GROQ_API_KEY=${GROQ_API_KEY}
+      - GROQ_MODEL=${GROQ_MODEL}
+      - QDRANT_URL=http://qdrant:6333
+      - QDRANT_API_KEY=${QDRANT_API_KEY:-}
+      - KB_COLLECTION=${KB_COLLECTION}
+      - HISTORY_COLLECTION=${HISTORY_COLLECTION}
+      - DEBUG=${DEBUG:-True}
+      - LOG_LEVEL=${LOG_LEVEL:-INFO}
+    ports:
+      - "8501:8501"
+    depends_on:
+      - backend
+    networks:
+      - voice-rag-network
+    volumes:
+      - ./data:/app/data
+
+  # Redis Cache (Optional)
+  redis:
+    image: redis:7-alpine
+    ports:
+      - "6379:6379"
+    networks:
+      - voice-rag-network
+    volumes:
+      - redis_storage:/data
+
+volumes:
+  qdrant_storage:
+  redis_storage:
+
+networks:
+  voice-rag-network:
+    driver: bridge

export_workflow_diagram.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+"""Export LangGraph workflow diagram"""
+
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+
+from orchestration.langgraph_workflow import get_workflow_graph, compiled_workflow
+
+def save_mermaid_diagram():
+    """Save Mermaid diagram to file"""
+    diagram = get_workflow_graph()
+    
+    output_path = Path("WORKFLOW_DIAGRAM.md")
+    with open(output_path, "w") as f:
+        f.write("# Voice RAG Bot - LangGraph Workflow Diagram\n\n")
+        f.write("```mermaid\n")
+        f.write(diagram)
+        f.write("\n```\n")
+    
+    print(f"✓ Mermaid diagram saved to {output_path}")
+    return diagram
+
+def save_ascii_diagram():
+    """Save ASCII diagram to file"""
+    ascii_graph = compiled_workflow.get_graph().draw_ascii()
+    
+    output_path = Path("WORKFLOW_ASCII.txt")
+    with open(output_path, "w") as f:
+        f.write(ascii_graph)
+    
+    print(f"✓ ASCII diagram saved to {output_path}")
+    return ascii_graph
+
+def save_png_diagram():
+    """Save PNG diagram to file"""
+    try:
+        png_bytes = compiled_workflow.get_graph().draw_mermaid_png()
+        
+        output_path = Path("WORKFLOW_DIAGRAM.png")
+        with open(output_path, "wb") as f:
+            f.write(png_bytes)
+        
+        print(f"✓ PNG diagram saved to {output_path} ({len(png_bytes)} bytes)")
+        return output_path
+    except Exception as e:
+        print(f"⚠ PNG diagram generation failed: {e}")
+        print("  (Requires 'playwright' package: pip install playwright)")
+        return None
+
+if __name__ == "__main__":
+    print("Exporting workflow diagrams...\n")
+    
+    mermaid = save_mermaid_diagram()
+    print("\nMermaid Output:")
+    print("-" * 60)
+    print(mermaid[:500] + "..." if len(mermaid) > 500 else mermaid)
+    
+    try:
+        ascii_diag = save_ascii_diagram()
+        print("\nASCII Output:")
+        print("-" * 60)
+        print(ascii_diag[:500] + "..." if len(ascii_diag) > 500 else ascii_diag)
+    except Exception as e:
+        print(f"\n⚠ ASCII diagram not available: {e}")
+    
+    png_path = save_png_diagram()
+    
+    print("\n✓ Workflow diagrams exported successfully!")

frontend/pages/workflow_diagram.py

@@ -0,0 +1,77 @@
+"""Streamlit page for workflow visualization"""
+
+import streamlit as st
+from pathlib import Path
+import sys
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from orchestration.langgraph_workflow import compiled_workflow
+
+st.set_page_config(page_title="Workflow Diagram", layout="wide")
+
+st.title("🔄 LangGraph Workflow Diagram")
+
+st.markdown("""
+This page displays the 9-node orchestration pipeline for the Voice RAG Bot:
+- **Nodes**: Sentiment Analysis → Entity Extraction → Intent Detection → Retrieval → Context → Response → Validation → Memory → TTS
+- **Parallel Execution**: Sentiment & Entity steps run in parallel
+- **Conditional Logic**: Validation node can retry response generation if quality checks fail
+""")
+
+try:
+    # Generate PNG diagram
+    png_bytes = compiled_workflow.get_graph().draw_mermaid_png()
+    
+    col1, col2 = st.columns([2, 1])
+    
+    with col1:
+        st.image(png_bytes, caption="Voice RAG Bot - 9-Node Workflow", use_column_width=True)
+    
+    with col2:
+        st.subheader("Workflow Details")
+        
+        details = """
+        **9 Nodes:**
+        1. Sentiment Analysis
+        2. Entity Extraction
+        3. Intent Detection
+        4. Retrieval Router
+        5. Context Builder
+        6. Response Generation
+        7. Validation
+        8. Memory Persistence
+        9. TTS Generation
+        
+        **Features:**
+        - Parallel execution
+        - Conditional retries
+        - Latency tracking
+        - Audio generation
+        """
+        st.markdown(details)
+        
+        if st.button("📥 Download Diagram as PNG"):
+            st.download_button(
+                label="Download PNG",
+                data=png_bytes,
+                file_name="workflow_diagram.png",
+                mime="image/png"
+            )
+            st.success("✓ PNG ready for download!")
+    
+except Exception as e:
+    st.error(f"❌ Error generating diagram: {e}")
+    st.info("💡 Make sure playwright is installed: `pip install playwright`")
+
+st.divider()
+
+try:
+    # Display Mermaid text version as fallback
+    mermaid_text = compiled_workflow.get_graph().draw_mermaid()
+    
+    with st.expander("📄 View Mermaid Source"):
+        st.code(mermaid_text, language="mermaid")
+        
+except Exception as e:
+    st.warning(f"Could not generate Mermaid source: {e}")

spaces.yaml

@@ -0,0 +1,10 @@
+title: Voice RAG Bot
+description: Voice-enabled RAG chatbot with sentiment analysis and entity extraction
+app_file: app.py
+sdk: streamlit
+sdk_version: "1.28.0"
+python_version: "3.11"
+cpu: true
+gpu: true
+startup_duration_timeout: 600
+hf_oauth: true