1curl --location 'https://qianfan.baidubce.com/v2/responses' \
2--header 'Authorization: Bearer bce-v3/ALTAK-*********/614fb**********'\
3--header 'Content-Type: application/json' \
4--data '{
5    "tools": [
6        {
7            "type": "knowledge_search",
8            "knowledgebase_ids": "f015fff6-05d7-4192-b581-**********"
9        }
10        
11    ],
12    "input": [
13        {
14            "role": "user",
15            "content": "总结智能体客服搭建过程"
16        }
17    ],
18    "model": "deepseek-v3.2"
19}'

1{
2    "id": "rsn-subu0dg30m",
3    "object": "response",
4    "created_at": 1763473098,
5    "status": "completed",
6    "model": "deepseek-v3.2",
7    "tools": [
8        {
9            "type": "knowledge_search",
10            "knowledgebase_ids": "f015fff6-05d7-4192-b581-**********"
11        }
12    ],
13    "output": [
14        {
15            "id": "msg-4npm1gfg0y",
16            "type": "message",
17            "status": "completed",
18            "role": "assistant",
19            "content": [
20                {
21                    "type": "output_text",
22                    "text": "我需要查询知识库来为您总结智能体客服搭建过程。让我搜索相关的文档信息。\n\n"
23                }
24            ]
25        },
26        {
27            "id": "ks-tn2hmi9d6p",
28            "type": "knowledge_search_call",
29            "status": "completed"
30        },
31        {
32            "id": "msg-4zmabgcaqm",
33            "type": "message",
34            "status": "completed",
35            "role": "assistant",
36            "content": [
37                {
38                    "type": "output_text",
39                    "text": "基于知识库内容，智能体客服的搭建过程主要遵循以下步骤：\n\n## 主要搭建流程\n\n### 1. 初始化工作\n- 安装必要的Python库：langgraph、langchain、grandalf、qianfan\n- 进行模型初始化，设置API密钥等必要参数\n\n### 2. 创建智能体\n- 定义客服智能体：作为整体流程的主入口\n- 定义地址更新助手：用于处理地址更新的具体流程\n\n### 3. 定义智能体使用的工具\n- 通过`@tool`装饰器定义客服可以调用的工具或服务\n- 配置系统提示词（System Prompt）来确定智能体的角色和功能……",
40                    "annotations": [
41                        {
42                            "type": "doc_citation",
43                            "doc_id": "ac150673-1602-4e06-be99-6e860fb6c625",
44                            "doc_name": "千帆平台行业场景解决方案p2",
45                            "chunk_id": "8f90f40f-5406-4445-ae6f-3ed0f84225be"
46                        },
47                        ……
48                        ,
49                        {
50                            "type": "doc_citation",
51                            "doc_id": "ac150673-1602-4e06-be99-6e860fb6c625",
52                            "doc_name": "千帆平台行业场景解决方案p2",
53                            "chunk_id": "b005726b-f881-46c1-b9b4-589854082ab7"
54                        }
55                    ]
56                }
57            ]
58        }
59    ],
60    "usage": {
61        "input_tokens": 12787,
62        "output_tokens": 477,
63        "output_tokens_details": {
64            "reasoning_tokens": 0
65        },
66        "total_tokens": 13264
67    }
68}