Content Moderation

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-laozhang-api-key",
    base_url="https://api2.laozhang.ai/v1"
)

response = client.moderations.create(
    input="Text content to be reviewed"
)

result = response.results[0]
print(f"Contains harmful content: {result.flagged}")
print(f"Category scores: {result.category_scores}")

texts = ["Text 1", "Text 2", "Text 3"]

response = client.moderations.create(input=texts)

for i, result in enumerate(response.results):
    status = '⚠️ Flagged' if result.flagged else '✅ Safe'
    print(f"Text {i+1}: {status}")

def check_content(text):
    """Check if content is safe"""
    response = client.moderations.create(input=text)
    result = response.results[0]
    
    if result.flagged:
        violations = [
            cat for cat, flagged in result.categories.model_dump().items()
            if flagged
        ]
        return False, violations
    
    return True, []

# Usage
is_safe, violations = check_content(user_input)
if not is_safe:
    print(f"⚠️ Violation categories: {violations}")

def safe_chat(user_message):
    """Chat with safety checks"""
    # Check user input
    if client.moderations.create(input=user_message).results[0].flagged:
        return "Sorry, your message contains inappropriate content."
    
    # Process after safety check
    response = client.chat.completions.create(
        model="gpt-4.1",
        messages=[{"role": "user", "content": user_message}]
    )
    
    ai_reply = response.choices[0].message.content
    
    # Check AI response
    if client.moderations.create(input=ai_reply).results[0].flagged:
        return "Sorry, unable to generate appropriate response."
    
    return ai_reply

def check_with_threshold(text, threshold=0.5):
    """Check with custom threshold"""
    response = client.moderations.create(input=text)
    result = response.results[0]
    
    scores = result.category_scores.model_dump()
    high_risk = {
        cat: score for cat, score in scores.items()
        if score > threshold
    }
    
    return len(high_risk) == 0, high_risk

def process_with_safety(user_input):
    # 1. Check user input
    if not is_safe(user_input):
        return "Input content violates guidelines"
    
    # 2. Process
    result = process(user_input)
    
    # 3. Check output
    if not is_safe(result):
        return "Unable to generate appropriate content"
    
    return result