detoxify / app.py
Utiric's picture
Update app.py
4e5636a verified
raw
history blame
30.2 kB
from flask import Flask, request, jsonify, render_template
import os
import uuid
import time
import threading
import tiktoken
from datetime import datetime, timedelta
from collections import defaultdict, deque
from detoxify import Detoxify
import logging
logging.basicConfig(level=logging.INFO)
app = Flask(__name__, static_folder='static', template_folder='templates')
print("Loading Detoxify model... This may take a moment.")
detoxify_model = Detoxify('multilingual')
print("Model loaded successfully.")
API_KEY = os.getenv('API_KEY', 'your-api-key-here')
request_durations = deque(maxlen=100)
request_timestamps = deque(maxlen=1000)
daily_requests = defaultdict(int)
daily_tokens = defaultdict(int)
concurrent_requests = 0
concurrent_requests_lock = threading.Lock()
encoding = tiktoken.get_encoding("cl100k_base")
def count_tokens(text):
return len(encoding.encode(text))
def transform_predictions(prediction_dict):
category_keys = [
"toxicity", "severe_toxicity", "obscene", "threat",
"insult", "identity_attack", "sexual_explicit"
]
scores = {}
for key in category_keys:
scores[key] = float(prediction_dict.get(key, 0.0))
threshold = 0.5
bool_categories = {key: (scores[key] > threshold) for key in category_keys}
flagged = any(bool_categories.values())
return flagged, bool_categories, scores
def track_request_metrics(start_time, tokens_count):
end_time = time.time()
duration = end_time - start_time
app.logger.info(f"Server-side processing for moderation request took {duration * 1000:.2f} ms.")
request_durations.append(duration)
request_timestamps.append(datetime.now())
today = datetime.now().strftime("%Y-%m-%d")
daily_requests[today] += 1
daily_tokens[today] += tokens_count
def get_performance_metrics():
global concurrent_requests
with concurrent_requests_lock:
current_concurrent = concurrent_requests
if not request_durations:
avg_request_time = 0
peak_request_time = 0
else:
avg_request_time = sum(request_durations) / len(request_durations)
peak_request_time = max(request_durations)
now = datetime.now()
one_minute_ago = now - timedelta(seconds=60)
requests_last_minute = sum(1 for ts in request_timestamps if ts > one_minute_ago)
today = now.strftime("%Y-%m-%d")
today_requests = daily_requests.get(today, 0)
today_tokens = daily_tokens.get(today, 0)
last_7_days = []
for i in range(7):
date = (now - timedelta(days=i)).strftime("%Y-%m-%d")
last_7_days.append({
"date": date,
"requests": daily_requests.get(date, 0),
"tokens": daily_tokens.get(date, 0)
})
return {
"avg_request_time_ms": avg_request_time * 1000,
"peak_request_time_ms": peak_request_time * 1000,
"requests_per_minute": requests_last_minute,
"concurrent_requests": current_concurrent,
"today_requests": today_requests,
"today_tokens": today_tokens,
"last_7_days": last_7_days
}
@app.route('/')
def home():
return render_template('index.html')
@app.route('/v1/moderations', methods=['POST'])
def moderations():
global concurrent_requests
with concurrent_requests_lock:
concurrent_requests += 1
start_time = time.time()
total_tokens = 0
response = None
try:
auth_header = request.headers.get('Authorization')
if not auth_header or not auth_header.startswith("Bearer "):
response = jsonify({"error": "Unauthorized"}), 401
return response
provided_api_key = auth_header.split(" ")[1]
if provided_api_key != API_KEY:
response = jsonify({"error": "Unauthorized"}), 401
return response
data = request.get_json()
raw_input = data.get('input')
if raw_input is None:
response = jsonify({"error": "Invalid input, 'input' field is required"}), 400
return response
if isinstance(raw_input, str):
texts = [raw_input]
elif isinstance(raw_input, list):
texts = raw_input
else:
response = jsonify({"error": "Invalid input format, expected string or list of strings"}), 400
return response
if not texts:
response = jsonify({"error": "Input list cannot be empty"}), 400
return response
if len(texts) > 10:
response = jsonify({"error": "Too many input items. Maximum 10 allowed."}), 400
return response
for text in texts:
if not isinstance(text, str) or len(text.encode('utf-8')) > 300000:
response = jsonify({"error": "Each input item must be a string with a maximum of 300k bytes."}), 400
return response
total_tokens += count_tokens(text)
predictions = detoxify_model.predict(texts)
results = []
for i in range(len(texts)):
single_prediction = {key: value[i] for key, value in predictions.items()}
flagged, bool_categories, scores = transform_predictions(single_prediction)
results.append({
"flagged": flagged,
"categories": bool_categories,
"category_scores": scores,
})
response_data = {
"id": "modr-" + uuid.uuid4().hex[:24],
"model": "text-moderation-detoxify-multilingual",
"results": results
}
response = jsonify(response_data)
return response
except Exception as e:
app.logger.error(f"An error occurred: {e}", exc_info=True)
response = jsonify({"error": "An internal server error occurred."}), 500
return response
finally:
if response and response.status_code < 400:
track_request_metrics(start_time, total_tokens)
with concurrent_requests_lock:
concurrent_requests -= 1
@app.route('/v1/metrics', methods=['GET'])
def metrics():
auth_header = request.headers.get('Authorization')
if not auth_header or not auth_header.startswith("Bearer "):
return jsonify({"error": "Unauthorized"}), 401
provided_api_key = auth_header.split(" ")[1]
if provided_api_key != API_KEY:
return jsonify({"error": "Unauthorized"}), 401
return jsonify(get_performance_metrics())
def create_directories_and_files():
os.makedirs('templates', exist_ok=True)
os.makedirs('static', exist_ok=True)
index_path = os.path.join('templates', 'index.html')
if not os.path.exists(index_path):
with open(index_path, 'w', encoding='utf-8') as f:
f.write('''<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Text Moderation API</title>
<script src="https://cdn.tailwindcss.com"></script>
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
<script>
tailwind.config = {
darkMode: 'class',
theme: {
extend: {
colors: {
primary: {
50: '#eff6ff', 100: '#dbeafe', 200: '#bfdbfe', 300: '#93c5fd', 400: '#60a5fa',
500: '#3b82f6', 600: '#2563eb', 700: '#1d4ed8', 800: '#1e40af', 900: '#1e3a8a',
}
}
}
}
}
</script>
<style>
.gradient-bg { background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); }
.dark .gradient-bg { background: linear-gradient(135deg, #1e3a8a 0%, #4c1d95 100%); }
.glass-effect {
background: rgba(255, 255, 255, 0.1); backdrop-filter: blur(10px);
border: 1px solid rgba(255, 255, 255, 0.2);
}
.dark .glass-effect { background: rgba(30, 41, 59, 0.5); border: 1px solid rgba(100, 116, 139, 0.3); }
.category-card { transition: all 0.3s ease; }
.category-card:hover { transform: translateY(-5px); }
.loading-spinner { border-top-color: #3b82f6; animation: spinner 1.5s linear infinite; }
@keyframes spinner { 0% { transform: rotate(0deg); } 100% { transform: rotate(360deg); } }
</style>
</head>
<body class="bg-gray-50 dark:bg-gray-900 text-gray-900 dark:text-gray-100 min-h-screen font-sans">
<header class="gradient-bg text-white shadow-lg">
<div class="container mx-auto px-4 py-6 flex justify-between items-center">
<div class="flex items-center space-x-3">
<div class="w-10 h-10 rounded-full bg-white flex items-center justify-center">
<i class="fas fa-shield-alt text-primary-600 text-xl"></i>
</div>
<h1 class="text-2xl font-bold">Text Moderation API</h1>
</div>
<div class="flex items-center space-x-4">
<button id="refreshMetrics" class="glass-effect px-4 py-2 rounded-lg hover:bg-white/20 transition">
<i class="fas fa-sync-alt mr-2"></i>Refresh Metrics
</button>
<button id="darkModeToggle" class="glass-effect p-2 rounded-lg hover:bg-white/20 transition">
<i class="fas fa-moon dark:hidden"></i>
<i class="fas fa-sun hidden dark:inline"></i>
</button>
</div>
</div>
</header>
<main class="container mx-auto px-4 py-8">
<section class="mb-12">
<h2 class="text-2xl font-bold mb-6 flex items-center">
<i class="fas fa-chart-line mr-3 text-primary-600"></i>
Performance Metrics
</h2>
<div class="grid grid-cols-1 md:grid-cols-2 lg:grid-cols-4 gap-6 mb-8">
<div class="bg-white dark:bg-gray-800 rounded-xl shadow-lg p-6">
<div class="flex items-center justify-between">
<div>
<p class="text-gray-500 dark:text-gray-400 text-sm">Avg. Response (last 100)</p>
<p class="text-2xl font-bold" id="avgResponseTime">0ms</p>
</div>
<div class="w-12 h-12 rounded-full bg-primary-100 dark:bg-primary-900/30 flex items-center justify-center">
<i class="fas fa-clock text-primary-600 dark:text-primary-400"></i>
</div>
</div>
</div>
<div class="bg-white dark:bg-gray-800 rounded-xl shadow-lg p-6">
<div class="flex items-center justify-between">
<div>
<p class="text-gray-500 dark:text-gray-400 text-sm">Requests / Minute</p>
<p class="text-2xl font-bold" id="requestsPerMinute">0</p>
</div>
<div class="w-12 h-12 rounded-full bg-green-100 dark:bg-green-900/30 flex items-center justify-center">
<i class="fas fa-tachometer-alt text-green-600 dark:text-green-400"></i>
</div>
</div>
</div>
<div class="bg-white dark:bg-gray-800 rounded-xl shadow-lg p-6">
<div class="flex items-center justify-between">
<div>
<p class="text-gray-500 dark:text-gray-400 text-sm">Peak Response (last 100)</p>
<p class="text-2xl font-bold" id="peakResponseTime">0ms</p>
</div>
<div class="w-12 h-12 rounded-full bg-red-100 dark:bg-red-900/30 flex items-center justify-center">
<i class="fas fa-exclamation-triangle text-red-600 dark:text-red-400"></i>
</div>
</div>
</div>
<div class="bg-white dark:bg-gray-800 rounded-xl shadow-lg p-6">
<div class="flex items-center justify-between">
<div>
<p class="text-gray-500 dark:text-gray-400 text-sm">Today's Requests</p>
<p class="text-2xl font-bold" id="todayRequests">0</p>
</div>
<div class="w-12 h-12 rounded-full bg-yellow-100 dark:bg-yellow-900/30 flex items-center justify-center">
<i class="fas fa-list-ol text-yellow-600 dark:text-yellow-400"></i>
</div>
</div>
</div>
</div>
<div class="bg-white dark:bg-gray-800 rounded-xl shadow-lg p-6">
<h3 class="text-lg font-semibold mb-4">Last 7 Days Activity</h3>
<div class="h-64">
<canvas id="activityChart"></canvas>
</div>
</div>
</section>
<section class="mb-12">
<h2 class="text-2xl font-bold mb-6 flex items-center">
<i class="fas fa-code mr-3 text-primary-600"></i>
API Tester
</h2>
<div class="bg-white dark:bg-gray-800 rounded-xl shadow-lg p-6">
<form id="apiTestForm">
<div class="mb-6">
<label class="block text-sm font-medium mb-2" for="apiKey">API Key</label>
<input type="password" id="apiKey" class="w-full px-4 py-2 rounded-lg border border-gray-300 dark:border-gray-600 bg-white dark:bg-gray-700 focus:outline-none focus:ring-2 focus:ring-primary-500" placeholder="Enter your API key">
</div>
<div class="mb-6">
<label class="block text-sm font-medium mb-2">Text Inputs</label>
<div id="textInputsContainer">
<div class="text-input-group mb-4">
<textarea class="w-full px-4 py-2 rounded-lg border border-gray-300 dark:border-gray-600 bg-white dark:bg-gray-700 focus:outline-none focus:ring-2 focus:ring-primary-500" rows="3" placeholder="Enter text to moderate..."></textarea>
<button type="button" class="remove-input mt-2 text-red-500 hover:text-red-700 hidden">
<i class="fas fa-trash-alt mr-1"></i> Remove
</button>
</div>
</div>
<button type="button" id="addTextInput" class="mt-2 text-primary-600 hover:text-primary-800 dark:text-primary-400 dark:hover:text-primary-300">
<i class="fas fa-plus-circle mr-1"></i> Add another text input
</button>
</div>
<div class="flex justify-between items-center">
<div>
<button type="submit" id="analyzeBtn" class="bg-primary-600 hover:bg-primary-700 text-white font-medium py-2 px-6 rounded-lg transition">
<i class="fas fa-search mr-2"></i> Analyze Text
</button>
<button type="button" id="clearBtn" class="ml-2 bg-gray-300 hover:bg-gray-400 dark:bg-gray-600 dark:hover:bg-gray-700 text-gray-800 dark:text-gray-200 font-medium py-2 px-6 rounded-lg transition">
<i class="fas fa-eraser mr-2"></i> Clear
</button>
</div>
<div class="text-sm text-gray-500 dark:text-gray-400">
<i class="fas fa-info-circle mr-1"></i> Maximum 10 text inputs allowed
</div>
</div>
</form>
</div>
</section>
<section id="resultsSection" class="hidden">
<h2 class="text-2xl font-bold mb-6 flex items-center">
<i class="fas fa-clipboard-check mr-3 text-primary-600"></i>
Analysis Results
</h2>
<div class="bg-white dark:bg-gray-800 rounded-xl shadow-lg p-6 mb-6">
<div class="flex justify-between items-center mb-4">
<h3 class="text-lg font-semibold">Summary</h3>
<div class="text-sm text-gray-500 dark:text-gray-400">
<i class="fas fa-stopwatch mr-1"></i> Round-trip time: <span id="responseTime">0ms</span>
</div>
</div>
<div id="resultsContainer" class="space-y-6">
</div>
</div>
</section>
<section>
<h2 class="text-2xl font-bold mb-6 flex items-center">
<i class="fas fa-book mr-3 text-primary-600"></i>
API Documentation
</h2>
<div class="bg-white dark:bg-gray-800 rounded-xl shadow-lg p-6">
<h3 class="text-lg font-semibold mb-4">Endpoint</h3>
<div class="bg-gray-100 dark:bg-gray-700 p-4 rounded-lg mb-6 font-mono text-sm">POST /v1/moderations</div>
<h3 class="text-lg font-semibold mb-4">Request Body</h3>
<div class="bg-gray-100 dark:bg-gray-700 p-4 rounded-lg mb-6 overflow-x-auto">
<pre class="text-sm"><code>{
"input": "Text to moderate"
}</code></pre>
</div>
<h3 class="text-lg font-semibold mb-4">Response</h3>
<div class="bg-gray-100 dark:bg-gray-700 p-4 rounded-lg overflow-x-auto">
<pre class="text-sm"><code>{
"id": "modr-1234567890abcdef",
"model": "text-moderation-detoxify-multilingual",
"results": [
{
"flagged": true,
"categories": {
"toxicity": true,
"severe_toxicity": false,
/* ... other categories */
},
"category_scores": {
"toxicity": 0.95,
"severe_toxicity": 0.1,
/* ... other scores */
}
}
]
}</code></pre>
</div>
</div>
</section>
</main>
<footer class="bg-gray-100 dark:bg-gray-800 border-t border-gray-200 dark:border-gray-700 mt-12">
<div class="container mx-auto px-4 py-6 text-center text-gray-600 dark:text-gray-400">
© 2025 Text Moderation API. All rights reserved.
</div>
</footer>
<script>
const darkModeToggle = document.getElementById('darkModeToggle');
const html = document.documentElement;
if (localStorage.getItem('theme') === 'dark' || (!('theme' in localStorage) && window.matchMedia('(prefers-color-scheme: dark)').matches)) {
html.classList.add('dark');
}
darkModeToggle.addEventListener('click', () => {
html.classList.toggle('dark');
localStorage.setItem('theme', html.classList.contains('dark') ? 'dark' : 'light');
});
let activityChart;
function initActivityChart() {
if (activityChart) { activityChart.destroy(); }
const ctx = document.getElementById('activityChart').getContext('2d');
const isDarkMode = document.documentElement.classList.contains('dark');
const gridColor = isDarkMode ? 'rgba(255, 255, 255, 0.1)' : 'rgba(0, 0, 0, 0.1)';
const textColor = isDarkMode ? '#e5e7eb' : '#374151';
activityChart = new Chart(ctx, {
type: 'bar',
data: { labels: [], datasets: [
{ label: 'Requests', data: [], backgroundColor: 'rgba(59, 130, 246, 0.6)', borderColor: 'rgba(59, 130, 246, 1)', borderWidth: 1 },
{ label: 'Tokens', data: [], backgroundColor: 'rgba(16, 185, 129, 0.6)', borderColor: 'rgba(16, 185, 129, 1)', borderWidth: 1, yAxisID: 'y1' }
]},
options: {
responsive: true, maintainAspectRatio: false,
scales: {
y: { beginAtZero: true, position: 'left', title: { display: true, text: 'Requests', color: textColor }, ticks: { color: textColor }, grid: { color: gridColor } },
y1: { beginAtZero: true, position: 'right', title: { display: true, text: 'Tokens', color: textColor }, ticks: { color: textColor }, grid: { drawOnChartArea: false } }
},
plugins: { legend: { labels: { color: textColor } } }
}
});
}
async function fetchMetrics() {
const apiKey = document.getElementById('apiKey').value || 'temp-key-for-metrics';
try {
const response = await fetch('/v1/metrics', {
headers: { 'Authorization': 'Bearer ' + apiKey }
});
if (!response.ok) {
const error = await response.json();
console.error('Failed to fetch metrics:', error.error);
if(response.status === 401) {
}
return;
}
const data = await response.json();
updateMetricsDisplay(data);
} catch (error) {
console.error('Error fetching metrics:', error);
}
}
function updateMetricsDisplay(data) {
document.getElementById('avgResponseTime').textContent = data.avg_request_time_ms.toFixed(0) + 'ms';
document.getElementById('peakResponseTime').textContent = data.peak_request_time_ms.toFixed(0) + 'ms';
document.getElementById('requestsPerMinute').textContent = data.requests_per_minute;
document.getElementById('todayRequests').textContent = data.today_requests.toLocaleString();
if (activityChart) {
const labels = data.last_7_days.map(d => new Date(d.date).toLocaleDateString('en-US', { month: 'short', day: 'numeric' })).reverse();
const requests = data.last_7_days.map(d => d.requests).reverse();
const tokens = data.last_7_days.map(d => d.tokens).reverse();
activityChart.data.labels = labels;
activityChart.data.datasets[0].data = requests;
activityChart.data.datasets[1].data = tokens;
activityChart.update();
}
}
document.getElementById('addTextInput').addEventListener('click', () => {
const container = document.getElementById('textInputsContainer');
if (container.children.length >= 10) {
alert('Maximum 10 text inputs allowed');
return;
}
const newGroup = container.firstElementChild.cloneNode(true);
newGroup.querySelector('textarea').value = '';
newGroup.querySelector('.remove-input').classList.remove('hidden');
container.appendChild(newGroup);
updateRemoveButtons();
});
document.getElementById('textInputsContainer').addEventListener('click', function(e) {
if (e.target.closest('.remove-input')) {
e.target.closest('.text-input-group').remove();
updateRemoveButtons();
}
});
function updateRemoveButtons() {
const groups = document.querySelectorAll('.text-input-group');
groups.forEach(group => {
group.querySelector('.remove-input').classList.toggle('hidden', groups.length <= 1);
});
}
document.getElementById('clearBtn').addEventListener('click', () => {
document.getElementById('apiTestForm').reset();
const container = document.getElementById('textInputsContainer');
container.innerHTML = container.firstElementChild.outerHTML;
container.querySelector('textarea').value = '';
updateRemoveButtons();
document.getElementById('resultsSection').classList.add('hidden');
});
document.getElementById('apiTestForm').addEventListener('submit', async (e) => {
e.preventDefault();
const apiKey = document.getElementById('apiKey').value;
if (!apiKey) { alert('Please enter your API key'); return; }
const texts = Array.from(document.querySelectorAll('#textInputsContainer textarea'))
.map(t => t.value.trim()).filter(Boolean);
if (texts.length === 0) { alert('Please enter at least one text to analyze'); return; }
const analyzeBtn = document.getElementById('analyzeBtn');
const originalBtnContent = analyzeBtn.innerHTML;
analyzeBtn.innerHTML = '<div class="loading-spinner inline-block w-4 h-4 border-2 border-white border-t-transparent rounded-full mr-2"></div> Analyzing...';
analyzeBtn.disabled = true;
const startTime = Date.now();
try {
const response = await fetch('/v1/moderations', {
method: 'POST',
headers: { 'Content-Type': 'application/json', 'Authorization': 'Bearer ' + apiKey },
body: JSON.stringify({ input: texts.length === 1 ? texts[0] : texts })
});
const responseTime = Date.now() - startTime;
const data = await response.json();
if (!response.ok) throw new Error(data.error || 'Failed to analyze text');
displayResults(data, responseTime, texts);
fetchMetrics();
} catch (error) {
alert('Error: ' + error.message);
} finally {
analyzeBtn.innerHTML = originalBtnContent;
analyzeBtn.disabled = false;
}
});
function displayResults(data, responseTime, texts) {
const resultsSection = document.getElementById('resultsSection');
const resultsContainer = document.getElementById('resultsContainer');
document.getElementById('responseTime').textContent = responseTime + 'ms';
resultsContainer.innerHTML = '';
data.results.forEach((result, index) => {
const resultCard = document.createElement('div');
resultCard.className = 'border border-gray-200 dark:border-gray-700 rounded-lg p-4';
const flaggedBadge = result.flagged
? '<span class="inline-flex items-center px-2.5 py-0.5 rounded-full text-xs font-medium bg-red-100 text-red-800 dark:bg-red-900 dark:text-red-100"><i class="fas fa-exclamation-triangle mr-1"></i> Flagged</span>'
: '<span class="inline-flex items-center px-2.5 py-0.5 rounded-full text-xs font-medium bg-green-100 text-green-800 dark:bg-green-900 dark:text-green-100"><i class="fas fa-check-circle mr-1"></i> Safe</span>';
let categoriesHtml = Object.entries(result.category_scores).map(([category, score]) => {
const isFlagged = result.categories[category];
const categoryClass = isFlagged ? 'text-red-600 dark:text-red-400' : 'text-green-600 dark:text-green-400';
const scoreClass = score > 0.7 ? 'text-red-600 dark:text-red-400' : score > 0.4 ? 'text-yellow-600 dark:text-yellow-400' : 'text-green-600 dark:text-green-400';
return `
<div class="flex justify-between items-center py-2 border-b border-gray-100 dark:border-gray-700 last:border-b-0">
<span class="font-medium capitalize">${category.replace(/_/g, ' ')}</span>
<div class="flex items-center">
<span class="text-sm ${scoreClass} font-mono">${score.toFixed(4)}</span>
</div>
</div>
`;
}).join('');
resultCard.innerHTML = `
<div class="flex justify-between items-start mb-3">
<h4 class="text-lg font-semibold">Input ${index + 1}</h4>
${flaggedBadge}
</div>
<blockquote class="mb-4 p-3 bg-gray-50 dark:bg-gray-700 rounded-lg text-sm border-l-4 border-gray-300 dark:border-gray-500">${texts[index]}</blockquote>
<div class="category-card">
<h5 class="font-medium mb-2">Category Scores</h5>
<div class="bg-white dark:bg-gray-800/50 rounded-lg p-2">
${categoriesHtml}
</div>
</div>
`;
resultsContainer.appendChild(resultCard);
});
resultsSection.classList.remove('hidden');
resultsSection.scrollIntoView({ behavior: 'smooth', block: 'start' });
}
document.addEventListener('DOMContentLoaded', () => {
initActivityChart();
document.getElementById('refreshMetrics').addEventListener('click', fetchMetrics);
fetchMetrics();
setInterval(fetchMetrics, 15000);
});
</script>
</body>
</html>''')
if __name__ == '__main__':
create_directories_and_files()
port = int(os.getenv('PORT', 7860))
app.run(host='0.0.0.0', port=port, debug=True, use_reloader=False)