Upload 5 files

.env.example

@@ -0,0 +1,243 @@
+# Environment Configuration Template
+# Copy this file to .env and fill in your actual values
+
+# =============================================================================
+# Core Application Settings
+# =============================================================================
+ENVIRONMENT=development
+DEBUG=true
+LOG_LEVEL=INFO
+APP_NAME=Context-Aware Research Assistant
+APP_VERSION=1.0.0
+
+# =============================================================================
+# API Keys (Required)
+# =============================================================================
+
+# Google Gemini API Key (Required)
+# Get your free API key from: https://makersuite.google.com/app/apikey
+GOOGLE_API_KEY=your_gemini_api_key_here
+
+# Google Custom Search API (Required for web search)
+# Get from: https://console.cloud.google.com/
+GOOGLE_CSE_ID=your_custom_search_engine_id_here
+
+# Together AI API Key (Required for Llama models)
+# Sign up at: https://together.ai/
+TOGETHER_API_KEY=your_together_api_key_here
+
+# Tavily Search API Key (Optional but recommended)
+# Sign up at: https://tavily.com/
+TAVILY_API_KEY=your_tavily_api_key_here
+
+# LangSmith (Optional - for monitoring and debugging)
+LANGSMITH_API_KEY=your_langsmith_api_key_here
+LANGCHAIN_TRACING_V2=true
+LANGCHAIN_ENDPOINT=https://api.smith.langchain.com
+LANGCHAIN_PROJECT=context-aware-research-app
+
+# =============================================================================
+# Application Configuration
+# =============================================================================
+
+# Supabase Configuration (Optional - for database features)
+# Sign up at: https://supabase.com/
+SUPABASE_URL=your_supabase_project_url_here
+SUPABASE_KEY=your_supabase_anon_key_here
+SUPABASE_SERVICE_KEY=your_supabase_service_role_key_here
+DATABASE_URL=postgresql://postgres:your_password@db.your-project-ref.supabase.co:5432/postgres
+
+# Server Configuration
+API_HOST=0.0.0.0
+API_PORT=8000
+API_WORKERS=1
+FRONTEND_PORT=8501
+
+# Request Settings
+API_TIMEOUT=60
+MAX_SOURCES=10
+MAX_RETRIES=3
+REQUEST_TIMEOUT=300
+
+# Rate Limiting
+REQUESTS_PER_MINUTE=60
+RATE_LIMIT_PER_MINUTE=30
+BURST_LIMIT=100
+
+# =============================================================================
+# Research Configuration
+# =============================================================================
+
+# Search Settings
+DEFAULT_SEARCH_DEPTH=2
+MAX_SEARCH_RESULTS=20
+CONTENT_FETCH_TIMEOUT=30
+MAX_CONTENT_LENGTH=50000
+
+# Quality Thresholds
+MIN_CONFIDENCE_SCORE=5.0
+MIN_WORD_COUNT=100
+
+# Context Management
+MAX_CONTEXT_HISTORY=5
+CONTEXT_SUMMARY_LENGTH=1000
+
+# =============================================================================
+# LLM Configuration
+# =============================================================================
+
+# Model Selection
+DEFAULT_LLM_PROVIDER=gemini
+GEMINI_MODEL=gemini-1.5-flash
+PRIMARY_MODEL=gemini-1.5-flash
+FALLBACK_MODEL=gemini-1.5-flash
+ANALYSIS_MODEL=gemini-1.5-pro
+
+# Token Limits
+MAX_TOKENS=4096
+MAX_INPUT_TOKENS=30000
+MAX_OUTPUT_TOKENS=8000
+TEMPERATURE=0.1
+
+# =============================================================================
+# Cache and Performance
+# =============================================================================
+
+# Caching
+CACHE_TTL=3600
+ENABLE_CACHE=true
+CACHE_TYPE=memory
+
+# Performance
+PARALLEL_REQUESTS=5
+BATCH_SIZE=10
+ENABLE_STREAMING=true
+
+# =============================================================================
+# Security Settings
+# =============================================================================
+
+# CORS
+CORS_ORIGINS=["http://localhost:8501", "http://127.0.0.1:8501"]
+CORS_METHODS=["GET", "POST", "OPTIONS"]
+CORS_HEADERS=["*"]
+
+# Security Headers
+ENABLE_SECURITY_HEADERS=true
+SECRET_KEY=your_secret_key_here_change_in_production
+
+# =============================================================================
+# Monitoring and Observability
+# =============================================================================
+
+# Logging
+LOG_FILE=logs/app.log
+LOG_ROTATION=daily
+LOG_RETENTION_DAYS=30
+
+# Metrics
+ENABLE_METRICS=true
+METRICS_PORT=9090
+
+# =============================================================================
+# Feature Flags
+# =============================================================================
+
+# Experimental Features
+ENABLE_PDF_EXPORT=false
+ENABLE_WORD_CLOUD=false
+ENABLE_ANALYTICS_DASHBOARD=false
+ENABLE_VOICE_INTERFACE=false
+
+# Data Sources
+ENABLE_ACADEMIC_SEARCH=false
+ENABLE_NEWS_SEARCH=true
+ENABLE_SOCIAL_MEDIA=false
+
+# =============================================================================
+# Development Settings
+# =============================================================================
+
+# Development Only
+RELOAD_ON_CHANGE=true
+ENABLE_DEBUG_TOOLBAR=true
+SHOW_SQL_QUERIES=false
+MOCK_EXTERNAL_APIS=false
+
+# Testing
+ENABLE_TEST_MODE=false
+
+# =============================================================================
+# Production Overrides
+# =============================================================================
+
+# Uncomment these for production deployment
+# ENVIRONMENT=production
+# DEBUG=false
+# LOG_LEVEL=WARNING
+# ENABLE_SECURITY_HEADERS=true
+# ENABLE_RATE_LIMITING=true
+# CACHE_TYPE=redis
+# REDIS_URL=redis://localhost:6379/0
+
+# =============================================================================
+# STREAMLIT CLOUD DEPLOYMENT
+# =============================================================================
+# When deploying to Streamlit Cloud, add these to your app secrets:
+#
+# Required secrets:
+# GOOGLE_API_KEY = "your_gemini_api_key_here"
+# GOOGLE_CSE_ID = "your_custom_search_engine_id_here"
+# TOGETHER_API_KEY = "your_together_api_key_here"
+# TAVILY_API_KEY = "your_tavily_api_key_here"
+# LANGSMITH_API_KEY = "your_langsmith_api_key_here"
+#
+# Optional secrets:
+# SUPABASE_URL = "your_supabase_project_url_here"
+# SUPABASE_KEY = "your_supabase_anon_key_here"
+# SUPABASE_SERVICE_KEY = "your_supabase_service_role_key_here"
+#
+# Configuration secrets:
+# LANGCHAIN_TRACING_V2 = "true"
+# LANGCHAIN_PROJECT = "context-aware-research-app"
+# DEFAULT_LLM_PROVIDER = "gemini"
+# GEMINI_MODEL = "gemini-1.5-flash"
+# MAX_TOKENS = "4096"
+# TEMPERATURE = "0.1"
+#
+# =============================================================================
+# API SETUP INSTRUCTIONS
+# =============================================================================
+# 
+# 1. Google API Setup:
+#    a) Go to: https://console.cloud.google.com/
+#    b) Create new project or select existing
+#    c) Enable "Custom Search API"
+#    d) Go to "Credentials" → "Create Credentials" → "API Key"
+#    e) Copy the API key to GOOGLE_API_KEY
+#    f) Go to: https://cse.google.com/cse/
+#    g) Create a new search engine
+#    h) Copy the Search Engine ID to GOOGLE_CSE_ID
+#
+# 2. Together AI Setup:
+#    a) Sign up at: https://together.ai/
+#    b) Go to "API Keys" section
+#    c) Generate new API key
+#    d) Copy to TOGETHER_API_KEY
+#
+# 3. LangSmith Setup (Optional):
+#    a) Sign up at: https://smith.langchain.com/
+#    b) Go to "Settings" → "API Keys"
+#    c) Generate new API key
+#    d) Copy to LANGSMITH_API_KEY
+#
+# 4. Tavily Setup (Optional):
+#    a) Sign up at: https://tavily.com/
+#    b) Get API key from dashboard
+#    c) Copy to TAVILY_API_KEY
+#
+# 5. Supabase Setup (Optional):
+#    a) Sign up at: https://supabase.com/
+#    b) Create new project
+#    c) Go to "Settings" → "API"
+#    d) Copy URL and keys to respective variables

Dockerfile

@@ -0,0 +1,34 @@
+FROM python:3.11-slim
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONPATH=/app
+
+# Set work directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    software-properties-common \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+COPY requirements.txt .
+RUN pip install --upgrade pip && pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Expose port 7860 (Hugging Face Spaces standard)
+EXPOSE 7860
+
+# Health check for backend
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:7860/health || exit 1
+
+# Run the application via app.py entry point
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,16 @@
+"""
+Entry point for Hugging Face Spaces deployment.
+"""
+import uvicorn
+import os
+from app.main import app
+
+if __name__ == "__main__":
+    port = int(os.getenv("PORT", 7860))  # Hugging Face uses port 7860
+    uvicorn.run(
+        app,
+        host="0.0.0.0",
+        port=port,
+        workers=1,
+        log_level="info"
+    )

docker-compose.yml

@@ -0,0 +1,86 @@
+version: '3.8'
+
+services:
+  # Full-stack service (both backend and frontend)
+  research-app:
+    build: .
+    container_name: research-app-fullstack
+    ports:
+      - "8000:8000"  # FastAPI backend
+      - "8501:8501"  # Streamlit frontend
+    environment:
+      - START_MODE=both
+      - GOOGLE_API_KEY=${GOOGLE_API_KEY}
+      - GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
+      - TOGETHER_API_KEY=${TOGETHER_API_KEY}
+      - LANGSMITH_API_KEY=${LANGSMITH_API_KEY}
+      - TAVILY_API_KEY=${TAVILY_API_KEY}
+      - LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2:-true}
+      - LANGCHAIN_PROJECT=${LANGCHAIN_PROJECT:-context-aware-research-app}
+      - DEFAULT_LLM_PROVIDER=${DEFAULT_LLM_PROVIDER:-gemini}
+      - GEMINI_MODEL=${GEMINI_MODEL:-gemini-1.5-flash}
+      - SUPABASE_URL=${SUPABASE_URL}
+      - SUPABASE_KEY=${SUPABASE_KEY}
+      - SUPABASE_SERVICE_KEY=${SUPABASE_SERVICE_KEY}
+      - DATABASE_URL=${DATABASE_URL}
+    env_file:
+      - .env
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+
+  # Backend-only service
+  backend:
+    build: .
+    container_name: research-app-backend
+    ports:
+      - "8000:8000"
+    environment:
+      - START_MODE=backend
+      - GOOGLE_API_KEY=${GOOGLE_API_KEY}
+      - GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
+      - TOGETHER_API_KEY=${TOGETHER_API_KEY}
+      - LANGSMITH_API_KEY=${LANGSMITH_API_KEY}
+      - TAVILY_API_KEY=${TAVILY_API_KEY}
+      - LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2:-true}
+      - LANGCHAIN_PROJECT=${LANGCHAIN_PROJECT:-context-aware-research-app}
+      - DEFAULT_LLM_PROVIDER=${DEFAULT_LLM_PROVIDER:-gemini}
+      - GEMINI_MODEL=${GEMINI_MODEL:-gemini-1.5-flash}
+      - SUPABASE_URL=${SUPABASE_URL}
+      - SUPABASE_KEY=${SUPABASE_KEY}
+      - SUPABASE_SERVICE_KEY=${SUPABASE_SERVICE_KEY}
+      - DATABASE_URL=${DATABASE_URL}
+    env_file:
+      - .env
+    restart: unless-stopped
+    profiles:
+      - backend-only
+
+  # Frontend-only service (connects to external backend)
+  frontend:
+    build: .
+    container_name: research-app-frontend
+    ports:
+      - "8501:8501"
+    environment:
+      - START_MODE=frontend
+      - API_URL=${API_URL:-http://localhost:8000}
+    restart: unless-stopped
+    profiles:
+      - frontend-only
+    depends_on:
+      - backend
+
+# Networks
+networks:
+  default:
+    name: research-app-network
+
+# Volumes for persistent data (if using local database)
+volumes:
+  app_data:
+    driver: local

requirements.txt

@@ -0,0 +1,34 @@
+# Core LangChain and LangGraph dependencies
+langgraph>=0.2.0
+langchain>=0.2.0
+langchain-core>=0.2.0
+langchain-google-genai>=1.0.0
+langchain-together>=0.1.0
+langsmith>=0.1.0
+
+# API and Web Framework
+fastapi>=0.104.0
+uvicorn[standard]>=0.24.0
+pydantic>=2.5.0
+pydantic-settings>=2.1.0
+
+# HTTP and Web Scraping
+httpx>=0.25.0
+requests>=2.31.0
+beautifulsoup4>=4.12.0
+aiohttp>=3.9.0
+brotli>=1.0.0
+ddgs>=9.5.0
+
+# External APIs for enhanced search
+tavily-python>=0.3.0
+
+# Utilities
+python-dotenv>=1.0.0
+structlog>=23.2.0
+typer>=0.9.0
+rich>=13.7.0
+
+# Data processing
+pandas>=2.1.0
+numpy>=1.24.0