ai审核模块

2026-07-24 11:00:40 +08:00
1 parent 3089093476
commit 2423f19fcd
@@ -0,0 +1,166 @@
+"""
+AI Review 测试页面
+
+启动方式: streamlit run ai_review/test_app.py
+"""
+
+import streamlit as st
+import requests
+
+API = "http://127.0.0.1:8007"
+
+st.set_page_config(page_title="AI Review 测试", layout="wide")
+st.title("AI Review 审核测试")
+
+# ── 左侧：审核区 ──
+left, right = st.columns([2, 1])
+
+with left:
+    st.subheader("内容审核")
+
+    content = st.text_area("输入待审核文本", height=150,
+                            value=st.session_state.get("input_text", ""),
+                            key="content")
+
+    if st.button("提交审核", type="primary", use_container_width=True):
+        if not content.strip():
+            st.warning("请输入内容")
+        else:
+            resp = requests.post(f"{API}/review", json={"content": content})
+            if resp.ok:
+                data = resp.json()
+                st.session_state["last_result"] = data
+                st.session_state["last_content"] = content
+            else:
+                st.error(f"请求失败: {resp.text}")
+
+    # 显示审核结果
+    if "last_result" in st.session_state:
+        result = st.session_state["last_result"]
+        invalid = result.get("invalid") in (True, "true")
+
+        st.divider()
+        if invalid:
+            st.error(f"审核结果: 违规")
+        else:
+            st.success(f"审核结果: 通过")
+
+        with st.expander("原始响应"):
+            st.json(result)
+
+        # 人工纠偏
+        st.divider()
+        st.subheader("人工纠偏")
+
+        if invalid:
+            st.caption("AI 判违规但人工认为正常？点击下方按钮纠正。")
+            if st.button("人工纠正为正常", type="secondary"):
+                correct = st.session_state["last_content"]
+                resp = requests.post(
+                    f"{API}/rag/feedback",
+                    json={"content": correct, "correct_type": "safe"},
+                )
+                if resp.ok:
+                    fb = resp.json()
+                    if fb["added"]:
+                        st.toast("已写入 RAG 库")
+                    else:
+                        st.toast("已存在，跳过")
+        else:
+            st.caption("AI 放行了但人工发现违规？点击下方按钮纠正。")
+            if st.button("人工纠正为违规", type="secondary"):
+                correct = st.session_state["last_content"]
+                resp = requests.post(
+                    f"{API}/rag/feedback",
+                    json={"content": correct, "correct_type": "violation"},
+                )
+                if resp.ok:
+                    fb = resp.json()
+                    if fb["added"]:
+                        st.toast("已写入 RAG 库")
+                    else:
+                        st.toast("已存在，跳过")
+
+# ── 右侧：快捷用例 ──
+with right:
+    st.subheader("快捷用例")
+
+    test_cases = {
+        "违规-色情服务": "加我微信xxxxx，裸聊视频一对一服务，学生妹上门",
+        "违规-赌博": "真人百家乐在线投注，包赢不赔，注册送彩金",
+        "违规-假证": "专业办理身份证驾驶证，高仿毕业证，货到付款",
+        "违规-药品": "迷奸水听话水货到付款，保密发货",
+        "安全-日常": "今天天气真好，适合出门散步",
+        "安全-技术": "Python的装饰器本质上是一个高阶函数",
+        "安全-娱乐": "请问最近有什么好看的电影推荐吗",
+        "安全-学习": "机器学习入门需要先掌握线性代数和概率论",
+    }
+
+    for label, text in test_cases.items():
+        if st.button(label, use_container_width=True):
+            st.session_state["input_text"] = text
+            st.rerun()
+
+    st.divider()
+    st.subheader("服务状态")
+    try:
+        resp = requests.get(f"{API}/health")
+        if resp.ok:
+            st.success("服务在线")
+        else:
+            st.error("服务异常")
+    except Exception:
+        st.error("无法连接服务")
+
+# ── 底部：RAG 知识库 ──
+st.divider()
+st.subheader("RAG 知识库")
+
+if st.button("刷新知识库", type="secondary"):
+    st.rerun()
+
+try:
+    resp = requests.get(f"{API}/rag/list")
+    if resp.ok:
+        data = resp.json()
+        entries = data.get("entries", [])
+        total = data.get("total", 0)
+
+        if total == 0:
+            st.info("知识库为空")
+        else:
+            violation_count = sum(1 for e in entries if e["type"] == "violation")
+            safe_count = sum(1 for e in entries if e["type"] == "safe")
+
+            col1, col2, col3 = st.columns(3)
+            col1.metric("总条目", total)
+            col2.metric("违规样本", violation_count)
+            col3.metric("安全样本", safe_count)
+
+            rows = []
+            for e in entries:
+                src = "预设" if e["category"] != "human_feedback" else "人工反馈"
+                tag = "违规" if e["type"] == "violation" else "安全"
+                rows.append({
+                    "标签": tag,
+                    "来源": src,
+                    "分类": e["category"],
+                    "ID": e["id"],
+                    "内容": e["text"][:80] + ("..." if len(e["text"]) > 80 else ""),
+                })
+
+            st.dataframe(
+                rows,
+                use_container_width=True,
+                column_config={
+                    "标签": st.column_config.Column(width="small"),
+                    "来源": st.column_config.Column(width="small"),
+                    "分类": st.column_config.Column(width="medium"),
+                    "ID": st.column_config.Column(width="small"),
+                    "内容": st.column_config.Column(width="large"),
+                },
+            )
+    else:
+        st.error("无法获取知识库数据")
+except Exception as e:
+    st.error(f"请求失败: {e}")