remove sensitive logs

.dockerignore

@@ -0,0 +1,53 @@
+# Git
+.git
+.gitignore
+
+# Python
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+*.so
+*.egg
+*.egg-info
+dist
+build
+.pytest_cache
+.coverage
+htmlcov
+.mypy_cache
+.dmypy.json
+dmypy.json
+
+# Virtual environments
+venv
+env
+ENV
+.venv
+
+# IDE
+.vscode
+.idea
+*.swp
+*.swo
+*~
+
+# Environment files
+.env
+.env.local
+.env.*.local
+
+# Documentation
+README.md
+*.md
+
+# Lock files (not needed for pip install)
+uv.lock
+
+# Vercel
+vercel.json
+
+# Distribution files
+*.tar.gz
+*.zip

.env.dist

@@ -1 +1,13 @@
+# Google Cloud Authentication - Choose ONE of the following methods:
+
+# Option 1: Local development - Path to JSON credentials file
 GOOGLE_APPLICATION_CREDENTIALS=credentials.json
+
+# Option 2: Production - JSON content as string (useful for serverless platforms like Vercel)
+# Paste the entire JSON content of your service account key here
+# GOOGLE_CREDENTIALS_JSON={"type":"service_account","project_id":"..."}
+
+PORT=8000
+HOST=0.0.0.0
+BASIC_AUTH_USERNAME=admin
+BASIC_AUTH_PASSWORD=admin

.gitignore

@@ -11,3 +11,4 @@ wheels/
 
 credentials.json
 .env
+.vercel

.python-version

@@ -1 +0,0 @@
-3.13

DOCKER.md

@@ -0,0 +1,215 @@
+# Docker Setup Guide
+
+This document explains how to build and run the Akern-Genai application using Docker.
+
+## Overview
+
+The Docker configuration includes:
+
+- **Multi-stage build** for smaller image size
+- **Entrypoint script** with proper signal handling and exit status management
+- **Configurable port** via environment variables
+- **Health checks** for monitoring
+- **Non-root user** for security
+- **Optimized build** with `.dockerignore`
+
+## Files
+
+- [`Dockerfile`](Dockerfile) - Multi-stage Docker build configuration
+- [`entrypoint.sh`](entrypoint.sh) - Entrypoint script with signal handling
+- [`docker-compose.yml`](docker-compose.yml) - Docker Compose configuration
+- [`.dockerignore`](.dockerignore) - Files excluded from Docker build context
+
+## Environment Variables
+
+The following environment variables can be configured:
+
+| Variable    | Default   | Description                                           |
+| ----------- | --------- | ----------------------------------------------------- |
+| `PORT`      | `8000`    | Port on which the application listens                 |
+| `HOST`      | `0.0.0.0` | Host address to bind to                               |
+| `WORKERS`   | `1`       | Number of uvicorn worker processes                    |
+| `LOG_LEVEL` | `info`    | Logging level (debug, info, warning, error, critical) |
+
+## Building the Image
+
+### Using Docker directly:
+
+```bash
+docker build -t akern-genai:latest .
+```
+
+### Using Docker Compose:
+
+```bash
+docker-compose build
+```
+
+## Running the Container
+
+### Using Docker directly:
+
+```bash
+# Run with default configuration (port 8000)
+docker run -p 8000:8000 akern-genai:latest
+
+# Run with custom port
+docker run -p 3000:3000 -e PORT=3000 akern-genai:latest
+
+# Run with multiple workers
+docker run -p 8000:8000 -e WORKERS=4 akern-genai:latest
+
+# Run with custom log level
+docker run -p 8000:8000 -e LOG_LEVEL=debug akern-genai:latest
+```
+
+### Using Docker Compose:
+
+```bash
+# Run with default configuration
+docker-compose up
+
+# Run with custom port
+PORT=3000 docker-compose up
+
+# Run in detached mode
+docker-compose up -d
+
+# Stop the container
+docker-compose down
+```
+
+### Using environment file:
+
+Create a `.env` file in the project root:
+
+```env
+PORT=8000
+HOST=0.0.0.0
+WORKERS=1
+LOG_LEVEL=info
+```
+
+Then run:
+
+```bash
+docker-compose up
+```
+
+## Signal Handling
+
+The entrypoint script properly handles termination signals:
+
+- **SIGTERM** - Graceful shutdown (sent by `docker stop`)
+- **SIGINT** - Interrupt signal (Ctrl+C)
+
+The script will:
+
+1. Forward the signal to uvicorn
+2. Wait up to 30 seconds for graceful shutdown
+3. Force kill if shutdown doesn't complete in time
+4. Exit with the same status code as uvicorn
+
+## Health Check
+
+The container includes a health check that monitors the application:
+
+- **Interval**: 30 seconds
+- **Timeout**: 10 seconds
+- **Start period**: 5 seconds
+- **Retries**: 3
+
+Check container health:
+
+```bash
+docker ps
+docker inspect <container_id> | grep -A 10 Health
+```
+
+## Multi-Stage Build
+
+The Dockerfile uses a two-stage build:
+
+### Stage 1: Builder
+
+- Installs build dependencies (gcc, musl-dev, etc.)
+- Creates a virtual environment
+- Installs Python dependencies
+
+### Stage 2: Runtime
+
+- Uses minimal Alpine Linux
+- Only includes runtime dependencies
+- Copies the virtual environment from builder
+- Runs as non-root user
+
+This results in a significantly smaller final image.
+
+## Security Features
+
+- **Non-root user**: Application runs as `appuser` (UID 1000)
+- **Minimal base image**: Alpine Linux with only necessary packages
+- **No build tools in runtime**: Compiler and build tools are not included in final image
+
+## Troubleshooting
+
+### Container exits immediately
+
+Check logs:
+
+```bash
+docker logs <container_id>
+```
+
+### Port already in use
+
+Change the port:
+
+```bash
+docker run -p 3000:3000 -e PORT=3000 akern-genai:latest
+```
+
+### Health check failing
+
+Verify the application is running:
+
+```bash
+docker exec -it <container_id> wget -O- http://localhost:8000/
+```
+
+### View real-time logs
+
+```bash
+docker logs -f <container_id>
+```
+
+## Image Size Comparison
+
+- **Before**: ~200-300 MB (single stage with build tools)
+- **After**: ~100-150 MB (multi-stage, minimal runtime)
+
+## Production Considerations
+
+For production deployment:
+
+1. **Use specific image tags** instead of `latest`
+2. **Set appropriate worker count** based on CPU cores
+3. **Configure resource limits** in docker-compose.yml or Kubernetes
+4. **Use a reverse proxy** (nginx, traefik) for SSL termination
+5. **Set up logging aggregation** (ELK, Loki, etc.)
+6. **Configure monitoring** (Prometheus, Grafana)
+
+Example docker-compose.yml with resource limits:
+
+```yaml
+services:
+  app:
+    deploy:
+      resources:
+        limits:
+          cpus: "2"
+          memory: 1G
+        reservations:
+          cpus: "0.5"
+          memory: 512M
+```

Dockerfile

@@ -0,0 +1,85 @@
+# ============================================
+# Stage 1: Builder
+# ============================================
+FROM python:3.13-alpine AS builder
+
+# Install build dependencies
+RUN apk add --no-cache \
+    gcc \
+    musl-dev \
+    libffi-dev \
+    openssl-dev \
+    cargo
+
+# Create virtual environment
+RUN python -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Set working directory
+WORKDIR /build
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+
+# Install dependencies
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
+
+# ============================================
+# Stage 2: Runtime
+# ============================================
+FROM python:3.13-alpine AS runtime
+
+# Install runtime dependencies only
+RUN apk add --no-cache \
+    libstdc++ \
+    ca-certificates
+
+# Create non-root user for security
+RUN addgroup -g 1000 appuser && \
+    adduser -D -u 1000 -G appuser appuser
+
+# Copy virtual environment from builder
+COPY --from=builder /opt/venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Create application directory
+RUN mkdir /app && \
+    chown -R appuser:appuser /app
+
+WORKDIR /app
+
+# Copy application files
+COPY --chown=appuser:appuser app.py .
+COPY --chown=appuser:appuser llm_config.py .
+COPY --chown=appuser:appuser lib.py .
+
+RUN echo $CREDENTIALS > credentials.json
+COPY --chown=appuser:appuser static ./static
+
+# Copy and setup entrypoint script
+COPY entrypoint.sh /usr/local/bin/entrypoint.sh
+RUN chmod +x /usr/local/bin/entrypoint.sh
+
+# Switch to non-root user
+USER appuser
+
+# Expose default port (can be overridden via PORT env var)
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD wget --no-verbose --tries=1 --spider http://localhost:${PORT:-8000}/ || exit 1
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PORT=8000 \
+    HOST=0.0.0.0 \
+    WORKERS=1 \
+    LOG_LEVEL=info
+
+# Use entrypoint script
+ENTRYPOINT ["/usr/local/bin/entrypoint.sh"]
+
+

app.py

@@ -1,10 +1,29 @@
+"""FastAPI application for Akern-Genai project.
+
+This module provides the web application with WebSocket support
+for streaming responses from the Gemini model.
+"""
+
 import os
 import logging
-from fastapi import FastAPI, Request, WebSocket
+from typing import Annotated
+
+from fastapi import (
+    FastAPI,
+    Request,
+    WebSocket,
+    WebSocketDisconnect,
+    Depends,
+    HTTPException,
+    status,
+)
+from fastapi.security import HTTPBasic, HTTPBasicCredentials
 from fastapi.templating import Jinja2Templates
 from fastapi.staticfiles import StaticFiles
-from main import generate
 
+from lib import generate
+
+# Configure logging format and level
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
@@ -13,11 +32,42 @@ logging.basicConfig(
 
 logger = logging.getLogger(__name__)
 
+# Static files configuration
+STATIC_DIR: str = "static"
+TEMPLATES_DIR: str = "templates"
 
-STATIC_DIR = "static"
-TEMPLATES_DIR = "templates"
+# Security configuration
+security = HTTPBasic()
 
 
+def verify_credentials(credentials: HTTPBasicCredentials = Depends(security)) -> str:
+    """Verify HTTP Basic credentials against environment variables.
+
+    Args:
+        credentials: HTTP Basic authentication credentials.
+
+    Returns:
+        str: The authenticated username.
+
+    Raises:
+        HTTPException: If credentials are invalid.
+    """
+    correct_username = os.getenv("BASIC_AUTH_USERNAME")
+    correct_password = os.getenv("BASIC_AUTH_PASSWORD")
+
+    if not (
+        credentials.username == correct_username
+        and credentials.password == correct_password
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail="Incorrect username or password",
+            headers={"WWW-Authenticate": "Basic"},
+        )
+    return credentials.username
+
+
+# Initialize FastAPI application
 app = FastAPI()
 app.mount(f"/{STATIC_DIR}", StaticFiles(directory=STATIC_DIR), name="static")
 
@@ -25,19 +75,34 @@ templates = Jinja2Templates(directory=os.path.join(STATIC_DIR, TEMPLATES_DIR))
 
 
 @app.get("/")
-async def home(request: Request):
+def home(request: Request, username: Annotated[str, Depends(verify_credentials)]):
+    """Render the main index page.
+
+    Args:
+        request: The incoming request object.
+        username: The authenticated username from HTTP Basic auth.
+
+    Returns:
+        TemplateResponse: The rendered HTML template.
+    """
     return templates.TemplateResponse("index.html", {"request": request})
 
 
 @app.websocket("/ws")
 async def websocket_endpoint(websocket: WebSocket):
+    """Handle WebSocket connections for streaming responses.
+
+    Args:
+        websocket: The WebSocket connection.
+    """
     await websocket.accept()
-    while True:
-        data = await websocket.receive_text()
+    try:
+        while True:
+            data = await websocket.receive_text()
 
-        logger.info(data)
+            async for chunk in generate(data):
+                await websocket.send_text(chunk)
 
-        for chunk in generate(data):
-            await websocket.send_text(chunk)
-
-        await websocket.send_text("<<END>>")
+            await websocket.send_text("<<END>>")
+    except WebSocketDisconnect:
+        logger.info("Client disconnected")

docker-compose.yml

@@ -0,0 +1,32 @@
+services:
+  app:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: akern-genai-app
+    ports:
+      - "${PORT:-8000}:8000"
+    environment:
+      # Application configuration
+      - PORT=${PORT:-8000}
+      - HOST=${HOST:-0.0.0.0}
+      - WORKERS=${WORKERS:-1}
+      - LOG_LEVEL=${LOG_LEVEL:-info}
+
+      # Google GenAI configuration (load from .env file)
+      - GOOGLE_APPLICATION_CREDENTIALS=${GOOGLE_APPLICATION_CREDENTIALS}
+    restart: unless-stopped
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "wget",
+          "--no-verbose",
+          "--tries=1",
+          "--spider",
+          "http://${HOST:-127.0.0.1}:${PORT:-8000}/",
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 5s

entrypoint.sh

@@ -0,0 +1,55 @@
+#!/bin/sh
+set -e
+
+# Default values
+PORT="${PORT:-8000}"
+HOST="${HOST:-0.0.0.0}"
+WORKERS="${WORKERS:-1}"
+LOG_LEVEL="${LOG_LEVEL:-info}"
+
+# Display configuration
+echo "=========================================="
+echo "Starting FastAPI application"
+echo "=========================================="
+echo "Host: ${HOST}"
+echo "Port: ${PORT}"
+echo "Workers: ${WORKERS}"
+echo "Log Level: ${LOG_LEVEL}"
+echo "=========================================="
+
+# Trap signals for graceful shutdown
+cleanup() {
+    echo "Received termination signal, shutting down gracefully..."
+    # Send SIGTERM to uvicorn process group
+    if [ -n "$UVICORN_PID" ]; then
+        kill -TERM "$UVICORN_PID" 2>/dev/null || true
+        # Wait for uvicorn to exit, but with a timeout
+        timeout 30 sh -c "while kill -0 $UVICORN_PID 2>/dev/null; do sleep 1; done" || {
+            echo "Uvicorn did not shut down gracefully, forcing exit..."
+            kill -KILL "$UVICORN_PID" 2>/dev/null || true
+        }
+    fi
+    exit 0
+}
+
+# Register signal handlers
+trap cleanup SIGTERM SIGINT
+
+# Start uvicorn in the background to capture PID
+uvicorn app:app \
+    --host "${HOST}" \
+    --port "${PORT}" \
+    --workers "${WORKERS}" \
+    --log-level "${LOG_LEVEL}" \
+    --access-log \
+    &
+
+UVICORN_PID=$!
+
+# Wait for uvicorn process
+wait $UVICORN_PID
+EXIT_STATUS=$?
+
+# Exit with the same status as uvicorn
+echo "Uvicorn exited with status: ${EXIT_STATUS}"
+exit ${EXIT_STATUS}

lib.py

@@ -0,0 +1,145 @@
+"""Google Gemini API integration for Akern-Genai project.
+
+This module provides functionality to generate content using Google's Gemini model
+with Vertex AI RAG (Retrieval-Augmented Generation) support.
+"""
+
+from llm_config import generate_content_config
+import logging
+import asyncio
+import json
+import os
+import threading
+from google import genai
+from google.genai import types
+from google.oauth2 import service_account
+from dotenv import load_dotenv
+
+logger = logging.getLogger(__name__)
+
+
+# Load environment variables from .env file
+load_dotenv()
+
+
+def get_credentials():
+    """Get Google Cloud credentials and project ID from environment.
+
+    Supports two methods:
+    1. GOOGLE_CREDENTIALS_JSON: Direct JSON content as string (production)
+    2. GOOGLE_APPLICATION_CREDENTIALS: Path to JSON file (local development)
+
+    Returns:
+        tuple: (credentials, project_id) where credentials is a
+        service_account.Credentials object and project_id is the Google Cloud project
+    """
+    # OAuth scopes required for Vertex AI API
+    SCOPES = ["https://www.googleapis.com/auth/cloud-platform"]
+
+    # Try to load credentials from JSON content directly
+    credentials_json = os.getenv("GOOGLE_CREDENTIALS_JSON")
+
+    if credentials_json:
+        try:
+            credentials_info = json.loads(credentials_json)
+            project_id = credentials_info.get("project_id")
+
+            credentials = service_account.Credentials.from_service_account_info(
+                credentials_info, scopes=SCOPES
+            )
+            return credentials, project_id
+        except json.JSONDecodeError as e:
+            raise ValueError(f"Invalid JSON in GOOGLE_CREDENTIALS_JSON: {e}")
+
+    # Fall back to file-based credentials (standard behavior)
+    credentials_path = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")
+
+    if credentials_path and os.path.exists(credentials_path):
+        with open(credentials_path) as f:
+            credentials_info = json.load(f)
+        project_id = credentials_info.get("project_id")
+
+        credentials = service_account.Credentials.from_service_account_file(
+            credentials_path, scopes=SCOPES
+        )
+        return credentials, project_id
+
+    # If neither is provided, return None to let the client use default credentials
+    # (useful when running on Google Cloud with service account attached)
+    return None, None
+
+
+# Gemini model name
+GEMINI_MODEL: str = "gemini-3-pro-preview"
+
+
+async def generate(prompt: str):
+    """Generate content using Gemini model with RAG retrieval.
+
+    This function creates a streaming response from the Gemini model,
+    augmented with content from the configured RAG corpus.
+
+    The blocking API call is run in a thread pool to allow concurrent
+    processing of multiple WebSocket connections.
+
+    Args:
+        prompt: The user's input prompt to generate content for.
+
+    Yields:
+        str: Text chunks from the generated response.
+    """
+    # Create a queue for streaming chunks
+    chunk_queue: asyncio.Queue[str] = asyncio.Queue()
+    loop = asyncio.get_event_loop()
+
+    def run_streaming():
+        """Run the synchronous streaming in a separate thread."""
+        try:
+            credentials, project_id = get_credentials()
+
+            client = genai.Client(
+                vertexai=True,
+                credentials=credentials,
+                project=project_id
+            )
+
+            contents = [
+                types.Content(role="user", parts=[
+                              types.Part.from_text(text=prompt)]),
+            ]
+
+            for chunk in client.models.generate_content_stream(
+                model=GEMINI_MODEL,
+                contents=contents,
+                config=generate_content_config,
+            ):
+                if (
+                    chunk.candidates
+                    and chunk.candidates[0].content
+                    and chunk.candidates[0].content.parts
+                ):
+                    # Schedule the put operation in the event loop
+                    future = asyncio.run_coroutine_threadsafe(
+                        chunk_queue.put(chunk.text),
+                        loop,
+                    )
+                    # Wait for the put to complete (quick operation)
+                    future.result(timeout=1)
+        except Exception as e:
+            print(f"[ERROR] Streaming error: {e}")
+        finally:
+            asyncio.run_coroutine_threadsafe(
+                chunk_queue.put("<<END>>"),
+                loop,
+            )
+
+    # Start the streaming in a daemon thread
+    stream_thread = threading.Thread(target=run_streaming, daemon=True)
+    stream_thread.start()
+
+    # Yield chunks as they become available
+    while True:
+        chunk = await chunk_queue.get()
+        if chunk == "<<END>>":
+            break
+        yield chunk

llm_config.py

@@ -0,0 +1,39 @@
+from google.genai import types
+
+# Vertex AI RAG Corpus resource path
+CORPUS: str = (
+    "projects/520464122471/locations/europe-west3/ragCorpora/2305843009213693952"
+)
+
+tools = [
+    types.Tool(
+        retrieval=types.Retrieval(
+            vertex_rag_store=types.VertexRagStore(
+                rag_resources=[
+                    types.VertexRagStoreRagResource(rag_corpus=CORPUS)],
+            )
+        )
+    )
+]
+
+generate_content_config = types.GenerateContentConfig(
+    temperature=1,
+    top_p=0.95,
+    max_output_tokens=65535,
+    safety_settings=[
+        types.SafetySetting(
+            category="HARM_CATEGORY_HATE_SPEECH", threshold="OFF"),
+        types.SafetySetting(
+            category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="OFF"
+        ),
+        types.SafetySetting(
+            category="HARM_CATEGORY_SEXUALLY_EXPLICIT", threshold="OFF"
+        ),
+        types.SafetySetting(
+            category="HARM_CATEGORY_HARASSMENT", threshold="OFF"),
+    ],
+    tools=tools,
+    thinking_config=types.ThinkingConfig(
+        thinking_level="HIGH",
+    ),
+)

main.py

@@ -1,67 +0,0 @@
-from google import genai
-from google.genai import types
-from dotenv import load_dotenv
-
-
-load_dotenv()
-
-CORPUS = "projects/520464122471/locations/europe-west3/ragCorpora/2305843009213693952"
-
-
-def generate(prompt: str):
-    client = genai.Client(
-        vertexai=True,
-    )
-
-    model = "gemini-3-pro-preview"
-    contents = [
-        types.Content(role="user", parts=[types.Part.from_text(text=prompt)]),
-    ]
-    tools = [
-        types.Tool(
-            retrieval=types.Retrieval(
-                vertex_rag_store=types.VertexRagStore(
-                    rag_resources=[types.VertexRagStoreRagResource(rag_corpus=CORPUS)],
-                )
-            )
-        )
-    ]
-
-    generate_content_config = types.GenerateContentConfig(
-        temperature=1,
-        top_p=0.95,
-        max_output_tokens=65535,
-        safety_settings=[
-            types.SafetySetting(category="HARM_CATEGORY_HATE_SPEECH", threshold="OFF"),
-            types.SafetySetting(
-                category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="OFF"
-            ),
-            types.SafetySetting(
-                category="HARM_CATEGORY_SEXUALLY_EXPLICIT", threshold="OFF"
-            ),
-            types.SafetySetting(category="HARM_CATEGORY_HARASSMENT", threshold="OFF"),
-        ],
-        tools=tools,
-        thinking_config=types.ThinkingConfig(
-            thinking_level="HIGH",
-        ),
-    )
-
-    for chunk in client.models.generate_content_stream(
-        model=model,
-        contents=contents,
-        config=generate_content_config,
-    ):
-        if (
-            not chunk.candidates
-            or not chunk.candidates[0].content
-            or not chunk.candidates[0].content.parts
-        ):
-            continue
-
-        yield chunk.text
-
-
-if __name__ == "__main__":
-    for chunk in generate("Come si calcola il rapporto sodio potassio?"):
-        print(chunk, end="")

pyproject.toml

@@ -5,6 +5,7 @@ description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.13"
 dependencies = [
+    "asyncio>=4.0.0",
     "fastapi>=0.128.0",
     "fastapi-sse>=1.1.1",
     "google-genai>=1.59.0",

requirements.txt

@@ -0,0 +1,33 @@
+annotated-doc==0.0.4
+annotated-types==0.7.0
+anyio==4.12.1
+asyncio==4.0.0
+certifi==2026.1.4
+charset-normalizer==3.4.4
+click==8.3.1
+distro==1.9.0
+fastapi==0.128.0
+fastapi-sse==1.1.1
+google-auth==2.47.0
+google-genai==1.59.0
+h11==0.16.0
+httpcore==1.0.9
+httpx==0.28.1
+idna==3.11
+jinja2==3.1.6
+markupsafe==3.0.3
+pyasn1==0.6.2
+pyasn1-modules==0.4.2
+pydantic==2.12.5
+pydantic-core==2.41.5
+python-dotenv==1.2.1
+requests==2.32.5
+rsa==4.9.1
+sniffio==1.3.1
+starlette==0.50.0
+tenacity==9.1.2
+typing-extensions==4.15.0
+typing-inspection==0.4.2
+urllib3==2.6.3
+uvicorn==0.40.0
+websockets==15.0.1

static/css/main.css

@@ -1,37 +1,425 @@
-textarea {
-    width: 100%;
-    height: 80px;
+/* ===== CSS Variables ===== */
+:root {
+  --accent-color: rgb(38, 186, 216);
+  --accent-hover: rgb(25, 150, 180);
+  --accent-light: rgb(80, 205, 235);
+  --background-gradient: linear-gradient(
+    135deg,
+    var(--accent-hover) 0%,
+    var(--accent-color) 100%
+  );
+  --glass-bg: rgba(255, 255, 255, 0.95);
+  --glass-border: rgba(255, 255, 255, 0.2);
+  --text-primary: #1f2937;
+  --text-secondary: #6b7280;
+  --text-light: #9ca3af;
+  --shadow-sm: 0 1px 2px 0 rgba(0, 0, 0, 0.05);
+  --shadow-md:
+    0 4px 6px -1px rgba(0, 0, 0, 0.1), 0 2px 4px -1px rgba(0, 0, 0, 0.06);
+  --shadow-lg:
+    0 10px 15px -3px rgba(0, 0, 0, 0.1), 0 4px 6px -2px rgba(0, 0, 0, 0.05);
+  --shadow-xl:
+    0 20px 25px -5px rgba(0, 0, 0, 0.1), 0 10px 10px -5px rgba(0, 0, 0, 0.04);
+  --border-radius-sm: 8px;
+  --border-radius-md: 12px;
+  --border-radius-lg: 16px;
+  --border-radius-xl: 24px;
+  --transition-fast: 0.15s ease;
+  --transition-normal: 0.3s ease;
+  --transition-slow: 0.5s ease;
 }
 
-#messages {
-    display: flex;
-    flex-direction: column;
-    gap: 10px;
-    padding: 20px;
+/* ===== Font Face Declarations ===== */
+@font-face {
+  font-family: "Intelo";
+  src: url("../fonts/intelo-regular.woff2") format("woff2");
+  font-weight: 400;
+  font-style: normal;
+  font-display: swap;
 }
 
+@font-face {
+  font-family: "Intelo";
+  src: url("../fonts/intelo-light.woff2") format("woff2");
+  font-weight: 300;
+  font-style: normal;
+  font-display: swap;
+}
+
+@font-face {
+  font-family: "Intelo";
+  src: url("../fonts/intelo-bold.woff2") format("woff2");
+  font-weight: 700;
+  font-style: normal;
+  font-display: swap;
+}
+
+/* ===== Reset & Base Styles ===== */
+* {
+  margin: 0;
+  padding: 0;
+  box-sizing: border-box;
+}
+
+body {
+  font-family:
+    "Intelo",
+    -apple-system,
+    BlinkMacSystemFont,
+    "Segoe UI",
+    Roboto,
+    "Helvetica Neue",
+    Arial,
+    sans-serif;
+  background: var(--background-gradient);
+  min-height: 100vh;
+  display: flex;
+  justify-content: center;
+  align-items: center;
+  padding: 20px;
+  color: var(--text-primary);
+  line-height: 1.6;
+}
+
+/* ===== App Container ===== */
+.app-container {
+  width: 100%;
+  max-width: 900px;
+  height: 90vh;
+  max-height: 800px;
+  background: var(--glass-bg);
+  backdrop-filter: blur(20px);
+  border-radius: var(--border-radius-xl);
+  box-shadow: var(--shadow-xl);
+  display: flex;
+  flex-direction: column;
+  overflow: hidden;
+  border: 1px solid var(--glass-border);
+  animation: fadeInUp 0.6s ease-out;
+}
+
+@keyframes fadeInUp {
+  from {
+    opacity: 0;
+    transform: translateY(30px);
+  }
+
+  to {
+    opacity: 1;
+    transform: translateY(0);
+  }
+}
+
+/* ===== Header ===== */
+.chat-header {
+  background: linear-gradient(
+    135deg,
+    var(--accent-hover) 0%,
+    var(--accent-color) 100%
+  );
+  padding: 20px 24px;
+  display: flex;
+  justify-content: center;
+  align-items: center;
+  box-shadow: var(--shadow-md);
+  z-index: 10;
+}
+
+.header-content img {
+  width: 200px;
+}
+
+/* ===== Main Content ===== */
+.chat-main {
+  flex: 1;
+  display: flex;
+  flex-direction: column;
+  overflow-y: auto;
+  background: linear-gradient(180deg, #f8fafc 0%, #f1f5f9 100%);
+  scroll-behavior: smooth;
+}
+
+.chat-main::-webkit-scrollbar {
+  width: 6px;
+}
+
+.chat-main::-webkit-scrollbar-track {
+  background: transparent;
+}
+
+.chat-main::-webkit-scrollbar-thumb {
+  background: var(--text-light);
+  border-radius: 3px;
+}
+
+.chat-main::-webkit-scrollbar-thumb:hover {
+  background: var(--text-secondary);
+}
+
+/* ===== Messages Container ===== */
+.messages-container {
+  display: flex;
+  flex-direction: column;
+  gap: 16px;
+  padding: 24px;
+  flex-shrink: 0;
+}
+
+/* ===== Message Styles ===== */
 .message {
-    max-width: 70%;
-    padding: 10px 15px;
-    border-radius: 15px;
-    font-family: sans-serif;
-    line-height: 1.4;
+  max-width: 75%;
+  padding: 14px 20px 6px 20px;
+  border-radius: var(--border-radius-lg);
+  font-size: 0.95rem;
+  line-height: 1.6;
+  animation: messageSlide 0.3s ease-out;
+  word-wrap: break-word;
+}
+
+@keyframes messageSlide {
+  from {
+    opacity: 0;
+    transform: translateY(10px);
+  }
+
+  to {
+    opacity: 1;
+    transform: translateY(0);
+  }
 }
 
 .sent {
-    max-width: 70%;
-    background-color: lightgreen;
-    padding: 10px 15px;
-    border-radius: 15px;
-    font-family: sans-serif;
-    line-height: 1.4;
-    align-self: flex-end;
-    border-bottom-right-radius: 2px;
+  align-self: flex-end;
+  background: linear-gradient(
+    135deg,
+    var(--accent-hover) 0%,
+    var(--accent-color) 100%
+  );
+  color: white;
+  border-bottom-right-radius: 4px;
+  box-shadow: var(--shadow-md);
+}
+
+.sent a {
+  color: white;
+  text-decoration: underline;
 }
 
 .received {
-    align-self: flex-start;
-    background-color: #e5e5ea;
-    color: black;
-    border-bottom-left-radius: 2px;
+  align-self: flex-start;
+  background: white;
+  color: var(--text-primary);
+  border-bottom-left-radius: 4px;
+  box-shadow: var(--shadow-sm);
+  border: 1px solid rgba(0, 0, 0, 0.05);
+}
+
+.received a {
+  color: var(--accent-color);
+  text-decoration: none;
+}
+
+.received a:hover {
+  text-decoration: underline;
+}
+
+/* ===== Message Content Lists ===== */
+.message ul,
+.message ol {
+  margin: 0 0 8px 0;
+  padding-left: 20px;
+}
+
+.message p {
+  margin: 0 0 8px 0;
+}
+
+.message ul {
+  list-style-type: disc;
+}
+
+.message ol {
+  list-style-type: decimal;
+}
+
+.message li {
+  margin: 4px 0;
+  line-height: 1.6;
+}
+
+.message li::marker {
+  color: var(--accent-color);
+}
+
+/* Nested lists */
+.message ul ul,
+.message ol ol,
+.message ul ol,
+.message ol ul {
+  margin: 4px 0;
+}
+
+/* ===== Footer ===== */
+.chat-footer {
+  background: white;
+  padding: 20px 24px;
+  border-top: 1px solid rgba(0, 0, 0, 0.05);
+  box-shadow: 0 -4px 6px -1px rgba(0, 0, 0, 0.05);
+}
+
+.input-wrapper {
+  display: flex;
+  gap: 12px;
+  align-items: flex-end;
+  background: var(--background-gradient);
+  padding: 6px;
+  border-radius: var(--border-radius-lg);
+  box-shadow: var(--shadow-md);
+  transition: box-shadow var(--transition-normal);
+}
+
+.input-wrapper:focus-within {
+  box-shadow: var(--shadow-lg);
+}
+
+.message-input {
+  flex: 1;
+  background: white;
+  border: none;
+  border-radius: var(--border-radius-md);
+  padding: 14px 16px;
+  font-size: 1rem;
+  font-family: inherit;
+  color: var(--text-primary);
+  resize: none;
+  outline: none;
+  min-height: 50px;
+  max-height: 150px;
+  field-sizing: content;
+  transition: box-shadow var(--transition-fast);
+}
+
+.message-input::placeholder {
+  color: var(--text-light);
+}
+
+.message-input:focus {
+  box-shadow: 0 0 0 3px rgba(38, 186, 216, 0.2);
+}
+
+.message-input:disabled {
+  opacity: 0.6;
+  cursor: not-allowed;
+  background: #f3f4f6;
+}
+
+.send-button {
+  width: 50px;
+  height: 50px;
+  background: linear-gradient(
+    135deg,
+    var(--accent-hover) 0%,
+    var(--accent-color) 100%
+  );
+  border: none;
+  border-radius: var(--border-radius-md);
+  color: white;
+  cursor: pointer;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  transition: all var(--transition-normal);
+  box-shadow: var(--shadow-md);
+  flex-shrink: 0;
+}
+
+.send-button:hover {
+  transform: scale(1.05);
+  box-shadow: var(--shadow-lg);
+}
+
+.send-button:active {
+  transform: scale(0.95);
+}
+
+.send-button:disabled {
+  opacity: 0.5;
+  cursor: not-allowed;
+  transform: none;
+}
+
+.footer-hint {
+  text-align: center;
+  font-size: 0.75rem;
+  color: var(--text-light);
+  margin-top: 12px;
+}
+
+/* ===== Responsive Design ===== */
+@media (max-width: 768px) {
+  body {
+    padding: 10px;
+  }
+
+  .app-container {
+    height: 95vh;
+    max-height: none;
+    border-radius: var(--border-radius-lg);
+  }
+
+  .chat-header {
+    padding: 16px 20px;
+  }
+
+  .chat-main {
+    padding: 0;
+  }
+
+  .messages-container {
+    padding: 16px;
+    gap: 12px;
+  }
+
+  .message {
+    max-width: 85%;
+    padding: 12px 14px;
+    font-size: 0.9rem;
+  }
+
+  .chat-footer {
+    padding: 16px 20px;
+  }
+
+  .message-input {
+    padding: 12px 14px;
+    font-size: 0.95rem;
+  }
+
+  .send-button {
+    width: 46px;
+    height: 46px;
+  }
+}
+
+@media (max-width: 480px) {
+  .message {
+    max-width: 90%;
+  }
+}
+
+/* ===== Loading Animation ===== */
+@keyframes shimmer {
+  0% {
+    background-position: -200% 0;
+  }
+
+  100% {
+    background-position: 200% 0;
+  }
+}
+
+.loading-message {
+  background: linear-gradient(90deg, #f0f0f0 25%, #e0e0e0 50%, #f0f0f0 75%);
+  background-size: 200% 100%;
+  animation: shimmer 1.5s infinite;
 }

static/js/main.js

@@ -1,34 +1,61 @@
 (($) => {
-    var ws = new WebSocket("ws://localhost:8000/ws");
-    const input = $("#message");
-    const messages = $('#messages');
-    var lastMessage;
+  const isSecure = location.protocol === "https:";
+  var ws = new WebSocket(
+    `ws${isSecure ? "s" : ""}://${location.host}/ws`,
+  );
+  const input = $("#message");
+  const button = $("#button");
+  const messages = $("#messages");
+  const chatMain = $(".chat-main");
+  var lastMessage;
 
-    $('#button').on('click', () => {
-        const message = input.val();
+  // Function to scroll to bottom of chat
+  const scrollToBottom = () => {
+    chatMain.scrollTop(chatMain[0].scrollHeight);
+  };
 
-        if (message) {
-            ws.send(message);
-            lastMessage = $('<div class="message received"><p>Loading...</p></div>')
-            messages.append(`<div class="message sent"><p>${message}</p></div>`)
-            messages.append(lastMessage);
+  $("#button").on("click", () => {
+    const message = input.val();
 
-            input.val("");
-        }
-    });
+    if (message) {
+      // Disable input and button while waiting for response
+      input.prop("disabled", true);
+      button.prop("disabled", true);
 
-    ws.onmessage = (event) => {
-        if (lastMessage.text() === "Loading...") {
-            lastMessage.empty();
-        }
+      ws.send(message);
+      lastMessage = $('<div class="message received"><p>Loading...</p></div>');
+      messages.append(`<div class="message sent"><p>${message}</p></div>`);
+      messages.append(lastMessage);
 
-        var content = document.createTextNode(event.data);
+      input.val("");
+      scrollToBottom();
+    }
+  });
 
-        if (content.textContent === "<<END>>") {
-            lastMessage.html(marked.parse(lastMessage.text()));
-        }
-        else {
-            lastMessage.append(content);
-        }
-    };
+  input.on("keydown", (e) => {
+    if (e.key === "Enter" && !e.shiftKey) {
+      e.preventDefault();
+      $("#button").click();
+    }
+  });
+
+  ws.onmessage = (event) => {
+    if (lastMessage.text() === "Loading...") {
+      lastMessage.empty();
+    }
+
+    var content = document.createTextNode(event.data);
+
+    if (content.textContent === "<<END>>") {
+      lastMessage.html(marked.parse(lastMessage.text()));
+      // Re-enable input and button when response is complete
+      input.prop("disabled", false);
+      button.prop("disabled", false);
+      input.focus();
+      scrollToBottom();
+    } else {
+      lastMessage.append(content);
+      scrollToBottom();
+    }
+  };
 })(jQuery);

static/templates/index.html

@@ -1,24 +1,57 @@
-<!DOCTYPE html>
+<!doctype html>
 <html lang="en">
-<head>
-    <meta charset="UTF-8">
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <link rel="stylesheet" href="/static/css/main.css">
-    <title>Document</title>
-</head>
-<body>
-    <h1>Chat</h1>
-    <p>Come si calcola la massa magra? dammi una spiegazione dettagliata</p>
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <link rel="stylesheet" href="/static/css/main.css" />
+    <title>AKERN Assistant</title>
+  </head>
+  <body>
+    <div class="app-container">
+      <header class="chat-header">
+        <div class="header-content">
+          <img
+            src="https://www.akern.com/wp-content/themes/zaki_new/resources/img/icon/logo@2x.png"
+            alt=""
+          />
+        </div>
+      </header>
 
-    <div>
-        <textarea name="" id="message"></textarea>
-        <input id="button" type="button" value="Send">
+      <main class="chat-main">
+        <div id="messages" class="messages-container"></div>
+      </main>
+
+      <footer class="chat-footer">
+        <div class="input-wrapper">
+          <textarea
+            id="message"
+            class="message-input"
+            placeholder="Scrivi qui il tuo messaggio..."
+            rows="1"
+          ></textarea>
+          <button id="button" class="send-button">
+            <svg
+              width="24"
+              height="24"
+              viewBox="0 0 24 24"
+              fill="none"
+              xmlns="http://www.w3.org/2000/svg"
+            >
+              <path
+                d="M2.01 21L23 12 2.01 3 2 10l15 2-15 2z"
+                fill="currentColor"
+              />
+            </svg>
+          </button>
+        </div>
+        <p class="footer-hint">
+          Premi Invio per inviare, Shift+Invio per una nuova riga
+        </p>
+      </footer>
     </div>
 
-    <div id="messages"></div>
-
     <script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.7.1/jquery.min.js"></script>
     <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
     <script src="/static/js/main.js"></script>
-</body>
+  </body>
 </html>

uv.lock

@@ -32,6 +32,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/38/0e/27be9fdef66e72d64c0cdc3cc2823101b80585f8119b5c112c2e8f5f7dab/anyio-4.12.1-py3-none-any.whl", hash = "sha256:d405828884fc140aa80a3c667b8beed277f1dfedec42ba031bd6ac3db606ab6c", size = 113592, upload-time = "2026-01-06T11:45:19.497Z" },
 ]
 
+[[package]]
+name = "asyncio"
+version = "4.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/71/ea/26c489a11f7ca862d5705db67683a7361ce11c23a7b98fc6c2deaeccede2/asyncio-4.0.0.tar.gz", hash = "sha256:570cd9e50db83bc1629152d4d0b7558d6451bb1bfd5dfc2e935d96fc2f40329b", size = 5371, upload-time = "2025-08-05T02:51:46.605Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/57/64/eff2564783bd650ca25e15938d1c5b459cda997574a510f7de69688cb0b4/asyncio-4.0.0-py3-none-any.whl", hash = "sha256:c1eddb0659231837046809e68103969b2bef8b0400d59cfa6363f6b5ed8cc88b", size = 5555, upload-time = "2025-08-05T02:51:45.767Z" },
+]
+
 [[package]]
 name = "certifi"
 version = "2026.1.4"
@@ -144,6 +153,7 @@ name = "genai"
 version = "0.1.0"
 source = { virtual = "." }
 dependencies = [
+    { name = "asyncio" },
     { name = "fastapi" },
     { name = "fastapi-sse" },
     { name = "google-genai" },
@@ -155,6 +165,7 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
+    { name = "asyncio", specifier = ">=4.0.0" },
     { name = "fastapi", specifier = ">=0.128.0" },
     { name = "fastapi-sse", specifier = ">=1.1.1" },
     { name = "google-genai", specifier = ">=1.59.0" },

vercel.json

@@ -0,0 +1,4 @@
+{
+  "builds": [{ "src": "app.py", "use": "@vercel/python" }],
+  "routes": [{ "src": "/(.*)", "dest": "app.py" }]
+}