110 lines
3.1 KiB
Python
110 lines
3.1 KiB
Python
#!/usr/bin/env python3
|
|
|
|
"""
|
|
AI Review Service
|
|
|
|
基于 DeepSeek + RAG 的 AI 内容审核微服务。
|
|
接收纯文本字符串，返回结构化审核结果。
|
|
"""
|
|
|
|
from flask import Flask, request, jsonify
|
|
from flask_cors import CORS
|
|
from waitress import serve
|
|
from dotenv import load_dotenv
|
|
import hashlib
|
|
import os
|
|
import sys
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
load_dotenv(os.path.join(os.path.dirname(os.path.abspath(__file__)), ".env"))
|
|
|
|
from agent.review_agent import ReviewAgent
|
|
from security_middleware import apply_security_headers
|
|
|
|
app = Flask(__name__)
|
|
apply_security_headers(app)
|
|
CORS(app)
|
|
|
|
review_agent = ReviewAgent()
|
|
|
|
|
|
@app.route('/review', methods=['POST'])
|
|
def review():
|
|
"""
|
|
审核接口
|
|
Request: {"content": "待审核的字符串"}
|
|
Response: {"invalid": "true"} 或 {"invalid": "false"}
|
|
"""
|
|
data = request.get_json()
|
|
|
|
if not data or 'content' not in data:
|
|
return jsonify({"error": "content is required"}), 400
|
|
|
|
content = data.get('content', '').strip()
|
|
|
|
if not content:
|
|
return jsonify({"error": "content cannot be empty"}), 400
|
|
|
|
result = review_agent.review(content)
|
|
return jsonify(result), 200
|
|
|
|
|
|
@app.route('/rag/feedback', methods=['POST'])
|
|
def rag_feedback():
|
|
"""
|
|
人工纠偏反馈接口 —— AI 审核结果与人工判断不一致时调用。
|
|
|
|
Request: {"content": "被误判的文本", "correct_type": "violation"}
|
|
correct_type: "violation" — AI 漏判了（AI 通过但实际违规）
|
|
"safe" — AI 误杀了（AI 拦截但实际安全）
|
|
|
|
Response: {"added": true, "id": "v_xxx", "md5": "xxx"}
|
|
{"added": false, "reason": "duplicate"}
|
|
"""
|
|
data = request.get_json()
|
|
|
|
if not data or 'content' not in data:
|
|
return jsonify({"error": "content is required"}), 400
|
|
|
|
content = data.get('content', '').strip()
|
|
correct_type = data.get('correct_type', 'violation').strip()
|
|
|
|
if not content:
|
|
return jsonify({"error": "content cannot be empty"}), 400
|
|
|
|
if correct_type not in ("violation", "safe"):
|
|
return jsonify({"error": "correct_type must be 'violation' or 'safe'"}), 400
|
|
|
|
md5_hash = hashlib.md5(content.encode("utf-8")).hexdigest()
|
|
entry_id = f"{correct_type[:1]}_{md5_hash[:12]}"
|
|
category = "human_feedback"
|
|
|
|
added = review_agent.rag.add_example(entry_id, content, correct_type, category)
|
|
|
|
return jsonify({
|
|
"added": added,
|
|
"id": entry_id if added else None,
|
|
"md5": md5_hash,
|
|
"reason": None if added else "duplicate",
|
|
}), 200
|
|
|
|
|
|
@app.route('/health', methods=['GET'])
|
|
def health():
|
|
return jsonify({"status": "ok"}), 200
|
|
|
|
|
|
@app.route('/rag/list', methods=['GET'])
|
|
def rag_list():
|
|
"""返回 RAG 库中所有条目。"""
|
|
entries = review_agent.rag.list_all()
|
|
return jsonify({"total": len(entries), "entries": entries}), 200
|
|
|
|
|
|
ADDR = os.getenv("AI_REVIEW_HOST", "127.0.0.1")
|
|
PORT = int(os.getenv("AI_REVIEW_PORT", "8007"))
|
|
|
|
if __name__ == "__main__":
|
|
print(f'AI Review Service listening at http://{ADDR}:{PORT}')
|
|
serve(app, host=ADDR, port=PORT)
|