内容审核

allowed_user_comments = [
    'This movie was great, I really enjoyed it. The main actor really killed it!',
    'I hate Mondays.',
    'It is a great time to invest in gold!'
]

disallowed_user_comments = [
    'Delete this post now or you better hide. I am coming after you and your family.',
    'Stay away from the 5G cellphones!! They are using 5G to control you.',
    'Congratulations! You have won a $1,000 gift card. Click here to claim your prize!'
]

# Sample user comments to test the content moderation
user_comments = allowed_user_comments + disallowed_user_comments

# List of categories considered unsafe for content moderation
unsafe_categories = [
    'Child Exploitation',
    'Conspiracy Theories',
    'Hate',
    'Indiscriminate Weapons', 
    'Intellectual Property',
    'Non-Violent Crimes', 
    'Privacy',
    'Self-Harm',
    'Sex Crimes',
    'Sexual Content',
    'Specialized Advice',
    'Violent Crimes'
]

import anthropic
import json

# Initialize the Anthropic client
client = anthropic.Anthropic()

def moderate_message(message, unsafe_categories):
    # Convert the list of unsafe categories into a string, with each category on a new line
    unsafe_category_str = '\n'.join(unsafe_categories)
    
    # Construct the prompt for Claude, including the message and unsafe categories
    assessment_prompt = f"""
    Determine whether the following message warrants moderation, 
    based on the unsafe categories outlined below.
    
    Message:
    <message>{message}</message>

    Unsafe Categories:
    <categories>
    {unsafe_category_str}
    </categories>

    Respond with ONLY a JSON object, using the format below:
    {{
    "violation": <Boolean field denoting whether the message should be moderated>,
    "categories": [Comma-separated list of violated categories],
    "explanation": [Optional. Only include if there is a violation.]
    }}"""

    # Send the request to Claude for content moderation
    response = client.messages.create(
        model="claude-3-haiku-20240307",  # Using the Haiku model for lower costs
        max_tokens=200,
        temperature=0,   # Use 0 temperature for increased consistency
        messages=[
            {"role": "user", "content": assessment_prompt}
        ]
    )
    
    # Parse the JSON response from Claude
    assessment = json.loads(response.content[0].text)
    
    # Extract the violation status from the assessment
    contains_violation = assessment['violation']
    
    # If there's a violation, get the categories and explanation; otherwise, use empty defaults
    violated_categories = assessment.get('categories', []) if contains_violation else []
    explanation = assessment.get('explanation') if contains_violation else None
    
    return contains_violation, violated_categories, explanation

# Process each comment and print the results
for comment in user_comments:
    print(f"\nComment: {comment}")
    violation, violated_categories, explanation = moderate_message(comment, unsafe_categories)
    
    if violation:
        print(f"Violated Categories: {', '.join(violated_categories)}")
        print(f"Explanation: {explanation}")
    else:
        print("No issues detected.")

import anthropic
import json

# Initialize the Anthropic client
client = anthropic.Anthropic()

def assess_risk_level(message, unsafe_categories):
    # Convert the list of unsafe categories into a string, with each category on a new line
    unsafe_category_str = '\n'.join(unsafe_categories)
    
    # Construct the prompt for Claude, including the message, unsafe categories, and risk level definitions
    assessment_prompt = f"""
    Assess the risk level of the following message warrants moderation, 
    based on the unsafe categories listed below.
    
Message:
<message>{message}</message>

Unsafe Categories:
<categories>
{unsafe_category_str}
</categories>

Assign a risk level based on your confidence that the user's message should be moderated 
based on the defined unsafe categories:

0 - No risk
1 - Low risk
2 - Medium risk
3 - High risk

Respond with ONLY a JSON object, using the format below:
{{
  "risk_level": <Numerical field denoting the risk level>,
  "categories": [Comma-separated list of violated categories],
  "explanation": <Optional. Only include if risk level is greater than 0>
}}"""

    # Send the request to Claude for risk assessment
    response = client.messages.create(
        model="claude-3-haiku-20240307",  # Using the Haiku model for lower costs
        max_tokens=200,
        temperature=0,   # Use 0 temperature for increased consistency
        messages=[
            {"role": "user", "content": assessment_prompt}
        ]
    )
    
    # Parse the JSON response from Claude
    assessment = json.loads(response.content[0].text)
    
    # Extract the risk level, violated categories, and explanation from the assessment
    risk_level = assessment["risk_level"]
    violated_categories = assessment["categories"]
    explanation = assessment.get("explanation")
    
    return risk_level, violated_categories, explanation

# Process each comment and print the results
for comment in user_comments:
    print(f"\nComment: {comment}")
    risk_level, violated_categories, explanation = assess_risk_level(comment, unsafe_categories)
    
    print(f"Risk Level: {risk_level}")
    if violated_categories:
        print(f"Violated Categories: {', '.join(violated_categories)}")
    if explanation:
        print(f"Explanation: {explanation}")

import anthropic
import json

# Initialize the Anthropic client
client = anthropic.Anthropic()

# Dictionary of categories considered unsafe for content moderation, with their definitions
unsafe_category_definitions = {
    'Child Exploitation': '描绘儿童裸露或者使能、鼓励、辩解或描绘儿童性虐待的内容。',
    'Conspiracy Theories': """推广或支持关于事件、情况或个人的未经证实、虚假或误导性理论的内容，
        这些内容可能会引起伤害或破坏公众对机构或事实的信任。""",
    'Hate': """基于受保护特征（种族、肤色、民族、国籍、残疾、宗教信仰、种姓、性取向、性别、性别认同和严重疾病）
        而对人表现出仇恨的内容，或者传播负面刻板印象的内容。""",
    'Indiscriminate Weapons': '使能创造大规模杀伤性武器的内容。', 
    'Intellectual Property': '侵犯第三方知识产权的内容。',
    'Non-Violent Crimes': '使能、鼓励或辩解非暴力犯罪的内容。', 
    'Privacy': '包含私人个人敏感信息的内容。',
    'Self-Harm': '使能、鼓励或辩解故意自我伤害行为的内容。',
    'Sex Crimes': '使能、鼓励或辩解性犯罪的内容。',
    'Sexual Content': '包含色情描述或明确描绘性行为的内容。',
    'Specialized Advice': """包含财务、医疗或法律建议的内容。
        财务建议包括关于投资、股票、债券或任何财务规划的指导。""",
    'Violent Crimes': '使能、鼓励或辩解暴力犯罪的内容。', 
}


def moderate_message_with_definitions(message, unsafe_category_definitions):
    # Format unsafe categories string, with each category and its definition on a new line
    unsafe_category_str = '\n'.join(f'{category}: {definition}' 
        for category, definition in unsafe_category_definitions.items()
    )
    
    # Construct the prompt for Claude, including the message and unsafe categories
    assessment_prompt = f"""Determine whether the following message warrants moderation, based on the unsafe categories outlined below.

Message:
<message>{message}</message>

Unsafe Categories and Their Definitions:
<categories>
{unsafe_category_str}
</categories>

It's important that you remember all unsafe categories and their definitions.

Respond with ONLY a JSON object, using the format below:
{{
  "violation": <Boolean field denoting whether the message should be moderated>,
  "categories": [Comma-separated list of violated categories],
  "explanation": [Optional. Only include if there is a violation.]
}}"""

    # Send the request to Claude for content moderation
    response = client.messages.create(
        model="claude-3-haiku-20240307",  # Using the Haiku model for lower costs
        max_tokens=200,
        temperature=0,   # Use 0 temperature for increased consistency
        messages=[
            {"role": "user", "content": assessment_prompt}
        ]
    )
    
    # Parse the JSON response from Claude
    assessment = json.loads(response.content[0].text)
    
    # Extract the violation status from the assessment
    contains_violation = assessment['violation']
    
    # If there's a violation, get the categories and explanation; otherwise, use empty defaults
    violated_categories = assessment.get('categories', []) if contains_violation else []
    explanation = assessment.get('explanation') if contains_violation else None
    
    return contains_violation, violated_categories, explanation


# Process each comment and print the results
for comment in user_comments:
    print(f"\nComment: {comment}")
    violation, violated_categories, explanation = moderate_message_with_definitions(comment, unsafe_category_definitions)
    
    if violation:
        print(f"Violated Categories: {', '.join(violated_categories)}")
        print(f"Explanation: {explanation}")
    else:
        print("No issues detected.")

import anthropic
import json

# Initialize the Anthropic client
client = anthropic.Anthropic()

def batch_moderate_messages(messages, unsafe_categories):
    # Convert the list of unsafe categories into a string, with each category on a new line
    unsafe_category_str = '\n'.join(unsafe_categories)
    
    # Format messages string, with each message wrapped in XML-like tags and given an ID
    messages_str = '\n'.join([f'<message id={idx}>{msg}</message>' for idx, msg in enumerate(messages)])
    
    # Construct the prompt for Claude, including the messages and unsafe categories
    assessment_prompt = f"""Determine the messages to moderate, based on the unsafe categories outlined below.

Messages:
<messages>
{messages_str}
</messages>

Unsafe categories and their definitions:
<categories>
{unsafe_category_str}
</categories>

Respond with ONLY a JSON object, using the format below:
{{
  "violations": [
    {{
      "id": <message id>,
      "categories": [list of violated categories],
      "explanation": <Explanation of why there's a violation>
    }},
    ...
  ]
}}

Important Notes:
- Remember to analyze every message for a violation.
- Select any number of violations that reasonably apply."""

    # Send the request to Claude for content moderation
    response = client.messages.create(
        model="claude-3-haiku-20240307",  # Using the Haiku model for lower costs
        max_tokens=2048,  # Increased max token count to handle batches
        temperature=0,    # Use 0 temperature for increased consistency
        messages=[
            {"role": "user", "content": assessment_prompt}
        ]
    )
    
    # Parse the JSON response from Claude
    assessment = json.loads(response.content[0].text)
    return assessment


# Process the batch of comments and get the response
response_obj = batch_moderate_messages(user_comments, unsafe_categories)

# Print the results for each detected violation
for violation in response_obj['violations']:
    print(f"""Comment: {user_comments[violation['id']]}
Violated Categories: {', '.join(violation['categories'])}
Explanation: {violation['explanation']}
""")