像 Perplexity 和 ChatGPT Search 这样的人工智能搜索引擎有时会将伪造或过时的信息作为事实呈现。本教程构建了一个验证管道，该管道采用人工智能生成的答案，提取其事实声明，并根据新的 SERP 结果交叉检查每个声明。该管道会标记未经验证的声明并分配信任分数。成本：每次验证 1-3 次搜索，费用为 0.005-0.015 美元。
前置条件
- 已安装 Python 3.9+
- 请求已安装库
- 来自 scavio.dev 的 Scavio API 密钥
操作指南
步骤 1: 从人工智能生成的文本中提取事实主张
解析人工智能答案以识别可验证的具体事实主张。重点关注数字、日期、名称和具体断言。
Python
import re
def extract_claims(text: str) -> list:
"""Extract verifiable claims from AI-generated text."""
claims = []
sentences = re.split(r'[.!?]\s+', text)
for sentence in sentences:
sentence = sentence.strip()
if not sentence or len(sentence) < 20:
continue
# Claims with numbers/dates are verifiable
has_number = bool(re.search(r'\d+', sentence))
# Claims with proper nouns
has_proper = bool(re.search(r'[A-Z][a-z]+(?:\s[A-Z][a-z]+)*', sentence))
# Claims with comparison words
has_comparison = any(w in sentence.lower() for w in
['fastest', 'largest', 'best', 'most', 'first', 'only', 'latest'])
if has_number or has_comparison:
claims.append({'text': sentence, 'type': 'numeric' if has_number else 'comparative'})
elif has_proper:
claims.append({'text': sentence, 'type': 'factual'})
return claims
# Example AI answer to verify
ai_answer = """Python 3.14 was released in October 2025 with a new JIT compiler.
It is 2x faster than Python 3.12 for numeric workloads.
Guido van Rossum announced the change at PyCon 2025."""
claims = extract_claims(ai_answer)
for c in claims:
print(f' [{c["type"]}] {c["text"]}')步骤 2: 根据实时搜索结果交叉检查声明
对于每项主张，请在网络上搜索并检查 SERP 结果是否支持或矛盾。
Python
import requests, os
SCAVIO_KEY = os.environ['SCAVIO_API_KEY']
def verify_claim(claim: str) -> dict:
# Build a verification query from the claim
query = claim[:100] # truncate long claims
resp = requests.post('https://api.scavio.dev/api/v1/search',
headers={'x-api-key': SCAVIO_KEY, 'Content-Type': 'application/json'},
json={'query': query, 'country_code': 'us', 'num_results': 5})
results = resp.json().get('organic_results', [])
if not results:
return {'claim': claim, 'status': 'unverified', 'confidence': 0, 'sources': []}
# Check if results support the claim
claim_lower = claim.lower()
claim_keywords = set(re.findall(r'\b\w{4,}\b', claim_lower))
support_count = 0
sources = []
for r in results:
text = (r.get('title', '') + ' ' + r.get('snippet', '')).lower()
result_words = set(re.findall(r'\b\w{4,}\b', text))
overlap = len(claim_keywords & result_words) / max(len(claim_keywords), 1)
if overlap > 0.3:
support_count += 1
sources.append({'title': r['title'][:50], 'url': r['link']})
confidence = min(support_count / 3 * 100, 100)
status = 'verified' if confidence >= 50 else 'disputed' if confidence >= 20 else 'unverified'
return {'claim': claim[:60], 'status': status,
'confidence': round(confidence), 'sources': sources[:2]}步骤 3: 运行完整的验证管道并计算信任分数
验证 AI 答案中的所有声明并计算该响应的总体信任评分。
Python
import time
def verify_answer(ai_text: str) -> dict:
claims = extract_claims(ai_text)
if not claims:
return {'trust_score': 0, 'claims': [], 'note': 'No verifiable claims found'}
verified_claims = []
for claim in claims:
result = verify_claim(claim['text'])
result['type'] = claim['type']
verified_claims.append(result)
time.sleep(0.3)
# Compute trust score
verified = len([c for c in verified_claims if c['status'] == 'verified'])
disputed = len([c for c in verified_claims if c['status'] == 'disputed'])
total = len(verified_claims)
trust_score = round(verified / total * 100) if total > 0 else 0
cost = total * 0.005
print(f'Trust Score: {trust_score}/100')
print(f'Claims: {total} total, {verified} verified, {disputed} disputed')
print(f'Verification cost: ${cost:.3f}\n')
for c in verified_claims:
icon = 'PASS' if c['status'] == 'verified' else 'WARN' if c['status'] == 'disputed' else 'FAIL'
print(f' [{icon}] {c["claim"]}')
if c['sources']:
print(f' Source: {c["sources"][0]["title"]}')
return {'trust_score': trust_score, 'claims': verified_claims, 'cost': cost}
result = verify_answer(ai_answer)Python 示例
Python
import requests, os, re, time
SCAVIO_KEY = os.environ['SCAVIO_API_KEY']
def verify(claim):
resp = requests.post('https://api.scavio.dev/api/v1/search',
headers={'x-api-key': SCAVIO_KEY, 'Content-Type': 'application/json'},
json={'query': claim[:100], 'country_code': 'us', 'num_results': 5})
results = resp.json().get('organic_results', [])
keywords = set(re.findall(r'\b\w{4,}\b', claim.lower()))
support = sum(1 for r in results
if len(keywords & set(re.findall(r'\b\w{4,}\b', (r.get('snippet','')).lower()))) > len(keywords)*0.3)
return 'verified' if support >= 2 else 'unverified'
claims = ['Python 3.14 released October 2025', 'Guido van Rossum at PyCon 2025']
for c in claims:
print(f'{verify(c)}: {c}')
time.sleep(0.3)JavaScript 示例
JavaScript
const SCAVIO_KEY = process.env.SCAVIO_API_KEY;
async function verify(claim) {
const resp = await fetch('https://api.scavio.dev/api/v1/search', {
method: 'POST',
headers: { 'x-api-key': SCAVIO_KEY, 'Content-Type': 'application/json' },
body: JSON.stringify({ query: claim.slice(0, 100), country_code: 'us', num_results: 5 })
});
const results = (await resp.json()).organic_results || [];
const keywords = new Set(claim.toLowerCase().match(/\b\w{4,}/g) || []);
const support = results.filter(r => {
const words = new Set((r.snippet || '').toLowerCase().match(/\b\w{4,}/g) || []);
return [...keywords].filter(k => words.has(k)).length > keywords.size * 0.3;
}).length;
return support >= 2 ? 'verified' : 'unverified';
}
verify('Python 3.14 released October 2025').then(r => console.log(r));预期输出
JSON
[numeric] Python 3.14 was released in October 2025 with a new JIT compiler
[numeric] It is 2x faster than Python 3.12 for numeric workloads
[factual] Guido van Rossum announced the change at PyCon 2025
Trust Score: 67/100
Claims: 3 total, 2 verified, 1 disputed
Verification cost: $0.015
[PASS] Python 3.14 was released in October 2025 with a new JI
Source: Python 3.14 Release Notes - docs.python.org
[WARN] It is 2x faster than Python 3.12 for numeric workloads
[PASS] Guido van Rossum announced the change at PyCon 2025
Source: PyCon 2025 Keynote - Guido van Rossum