Skip to content

文件搜索工具

POST  v1/responses

请求参数

Authorization

在 Header 添加参数 Authorization,其值为在 Bearer 之后拼接 Token。

Authorization: Bearer ******************

Body 参数

Content-Type: application/json

参数名类型必填说明
modelstring必需要使用的模型 ID。
toolsarray[object]必需工具
inputarray [object]必需输入消息列表。包含 role (可选), content (可选) 等字段。
includearray[string]可选指定要在模型响应中包含的附加输出数据。
instructionsstring可选作为系统消息插入到模型上下文的最前面。注意:当使用 previous_response_id 时,之前的指令不会自动带入,方便切换指令。
max_output_tokensinteger可选响应生成的最大 token 数(包含可见输出和推理 token)。
metadataobject可选最多包含 16 个键值对的元数据对象,用于存储额外信息。键最长 64 字符,值最长 512 字符。
parallel_tool_callsboolean可选是否在工具调用期间启用并行执行。
previous_response_idstring可选前一次响应的唯一 ID,用于创建多轮对话。
reasoningobject可选仅适用于 o 系列模型。配置模型的推理行为。
service_tierstring可选指定处理请求的延迟层级(如 auto, default, flex)。未设置时默认为 auto
storeboolean可选是否将此请求的输出存储用于模型蒸馏或评估。
streamboolean可选如果为 true,将通过服务器发送事件流式返回响应。
temperaturenumber可选采样温度 (0-2)。值越高输出越随机,值越低越确定。建议只调整此参数或 top_p 其中之一。
textobject可选文本响应的配置。可配置 { "type": "json_schema" } 以启用结构化输出。
tool_choicearray[string]可选模型可调用的工具列表(目前仅支持函数)。最多支持 128 个函数。
top_pnumber可选核采样参数 (0-1)。例如 0.1 意味着只考虑概率质量前 10% 的 token。
truncationstring可选用于模型响应的截断策略。
userstring可选最终用户的唯一标识符,有助于 OpenAI 监控和检测滥用行为。

请求示例 (JSON)

{
    "model": "gpt-4.1",
    "tools": [
        {
            "type": "file_search",
            "vector_store_ids": [
                "vs_1234567890"
            ],
            "max_num_results": 20
        }
    ],
    "input": "古代棕龙有哪些特性和属性?"
}

返回响应

200 成功

Content-Type: application/json

响应参数

字段名类型必填说明
idstring必需响应的唯一标识符。
objectstring必需对象类型。
created_atinteger必需创建时间的 Unix 时间戳。
statusstring必需响应的当前状态。
backgroundboolean必需是否在后台运行。
modelstring必需使用的模型名称。
parallel_tool_callsboolean必需是否启用了并行工具调用。
service_tierstring必需服务层级(如 default, flex 等)。
storeboolean必需是否存储了输出用于训练/评估。
temperatureinteger必需采样温度。
tool_choicestring必需工具选择策略。
toolsarray[string]必需可用的工具列表。
top_logprobsinteger必需返回的对数概率数量。
top_pinteger必需核采样概率阈值。
truncationstring必需截断策略。
usernull必需用户标识(此处显示为 null,通常用于审计)。
metadataobject必需用户自定义的元数据。
createdinteger必需另一个时间戳字段(可能是兼容旧版字段)。

响应示例

{
    "id": "resp_67ccf4c55fc48190b71bd0463ad3306d09504fb6872380d7",
    "object": "response",
    "created_at": 1741485253,
    "status": "completed",
    "error": null,
    "incomplete_details": null,
    "instructions": null,
    "max_output_tokens": null,
    "model": "gpt-4.1",
    "output": [
        {
            "type": "file_search_call",
            "id": "fs_67ccf4c63cd08190887ef6464ba5681609504fb6872380d7",
            "status": "completed",
            "queries": [
                "古代棕龙的特性和属性"
            ],
            "results": null
        },
        {
            "type": "message",
            "id": "msg_67ccf4c93e5c81909d595b369351a9d309504fb6872380d7",
            "status": "completed",
            "role": "assistant",
            "content": [
                {
                    "type": "output_text",
                    "text": "根据资料,古代棕龙具有以下特性和属性:\n\n1. 物理特征:古代棕龙体型庞大,体长可达25-30米,翼展约35米。它们的鳞片呈深棕色至铜色,随着年龄增长会变得更加暗沉。头部有特征性的双角和脊刺,下颚强壮,适合撕裂猎物。\n\n2. 能力:它们能喷吐强力的酸液,对目标造成严重腐蚀伤害。古代棕龙还拥有出色的掘地能力,常在沙漠或山地挖掘复杂的巢穴系统。\n\n3. 智力:被认为是龙族中最为狡猾和有耐心的品种,智力极高,精通多种语言,并具有复杂的战术思维。\n\n4. 栖息地:主要栖息在干旱的山地和沙漠地区,喜欢炎热干燥的环境。\n\n5. 宝藏:古代棕龙以其庞大的宝藏闻名,特别喜爱收集铜币、红宝石和火焰魔法物品。\n\n6. 寿命:是所有龙种中寿命最长的之一,可活2000-2500年,随着年龄增长其力量和魔法能力也会增强。\n\n7. 性格:极度领地意识强,性格暴躁易怒,对侵入者毫不留情,但也以其罕见的耐心著称,能为复仇等待几个世纪。",
                    "annotations": [
                        {
                            "type": "file_citation",
                            "index": 80,
                            "file_id": "file-4wDz5b167pAf72nx1h9eiN",
                            "filename": "dragons.pdf"
                        },
                        {
                            "type": "file_citation",
                            "index": 233,
                            "file_id": "file-4wDz5b167pAf72nx1h9eiN",
                            "filename": "dragons.pdf"
                        },
                        {
                            "type": "file_citation",
                            "index": 345,
                            "file_id": "file-4wDz5b167pAf72nx1h9eiN",
                            "filename": "dragons.pdf"
                        },
                        {
                            "type": "file_citation",
                            "index": 420,
                            "file_id": "file-4wDz5b167pAf72nx1h9eiN",
                            "filename": "dragons.pdf"
                        },
                        {
                            "type": "file_citation",
                            "index": 520,
                            "file_id": "file-4wDz5b167pAf72nx1h9eiN",
                            "filename": "dragons.pdf"
                        },
                        {
                            "type": "file_citation",
                            "index": 580,
                            "file_id": "file-4wDz5b167pAf72nx1h9eiN",
                            "filename": "dragons.pdf"
                        },
                        {
                            "type": "file_citation",
                            "index": 655,
                            "file_id": "file-4wDz5b167pAf72nx1h9eiN",
                            "filename": "dragons.pdf"
                        },
                        {
                            "type": "file_citation",
                            "index": 781,
                            "file_id": "file-4wDz5b167pAf72nx1h9eiN",
                            "filename": "dragons.pdf"
                        }
                    ]
                }
            ]
        }
    ],
    "parallel_tool_calls": true,
    "previous_response_id": null,
    "reasoning": {
        "effort": null,
        "summary": null
    },
    "store": true,
    "temperature": 1,
    "text": {
        "format": {
            "type": "text"
        }
    },
    "tool_choice": "auto",
    "tools": [
        {
            "type": "file_search",
            "filters": null,
            "max_num_results": 20,
            "ranking_options": {
                "ranker": "auto",
                "score_threshold": 0
            },
            "vector_store_ids": [
                "vs_1234567890"
            ]
        }
    ],
    "top_p": 1,
    "truncation": "disabled",
    "usage": {
        "input_tokens": 18307,
        "input_tokens_details": {
            "cached_tokens": 0
        },
        "output_tokens": 348,
        "output_tokens_details": {
            "reasoning_tokens": 0
        },
        "total_tokens": 18655
    },
    "user": null,
    "metadata": {}
}

示例代码

python
import http.client
import json

conn = http.client.HTTPSConnection("nxaiapp.com")
payload = json.dumps({
   "model": "gpt-4.1",
   "tools": [
      {
         "type": "file_search",
         "vector_store_ids": [
            "vs_1234567890"
         ],
         "max_num_results": 20
      }
   ],
   "input": "古代棕龙有哪些特性和属性?"
})
headers = {
   'Authorization': 'Bearer <token>',
   'Content-Type': 'application/json'
}
conn.request("POST", "/v1//responses", payload, headers)
res = conn.getresponse()
data = res.read()
print(data.decode("utf-8"))