获取样本列表
更新时间:2025-05-16
功能介绍
用于获取样本列表。
使用说明
本文API支持通过Python SDK、Go SDK、Java SDK 和 Node.js SDK调用,调用流程请参考SDK安装及使用流程。
权限说明
调用本文API,需符合以下权限要求,权限介绍及分配,请查看角色与权限控制列表、账号创建与权限分配。需具有以下任一权限:
- 完全控制千帆大模型平台的权限:QianfanFullControlAccessPolicy
- 只读访问千帆大模型平台的权限:QianfanReadAccessPolicy
- 完全控制千帆大模型平台数据管理(除数据标注外)的权限:QianfanDataFullControlAccessPolicy
- 运维操作千帆大模型平台数据管理(除数据标注外)的权限:QianfanDataOperateAccessPolicy
- 只读访问千帆大模型平台数据管理(除数据标注外)的权限:QianfanDataReadAccessPolicy
SDK调用
调用示例
1import os
2from qianfan import resources
3
4# 通过环境变量初始化认证信息
5# 使用安全认证AK/SK调用,替换下列示例中参数,安全认证Access Key替换your_iam_ak,Secret Key替换your_iam_sk,如何获取请查看https://cloud.baidu.com/doc/Reference/s/9jwvz2egb
6os.environ["QIANFAN_ACCESS_KEY"] = "your_iam_ak"
7os.environ["QIANFAN_SECRET_KEY"] = "your_iam_sk"
8
9
10
11resp = resources.console.utils.call_action(
12 # 调用本文API,该参数值为固定值,无需修改;对应API调用文档-请求结构-请求地址的后缀
13 "/wenxinworkshop/entity/list", "",
14 # 请查看本文请求参数说明,根据实际使用选择参数;对应API调用文档-请求参数-Body参数
15 {
16 "offset": 0,
17 "pageSize": 10,
18 "datasetId": "ds-7pkzh1exthpuy10n",
19 "importTime": [],
20 "annoTime": [],
21 "tabType": 1,
22 "labelId": ""
23 }
24
25)
26
27print(resp.body)
1package main
2import (
3 "context"
4 "fmt"
5 "os"
6 "github.com/baidubce/bce-qianfan-sdk/go/qianfan"
7)
8func main() {
9 // 使用安全认证AK/SK鉴权,通过环境变量初始化;替换下列示例中参数,安全认证Access Key替换your_iam_ak,Secret Key替换your_iam_sk
10 os.Setenv("QIANFAN_ACCESS_KEY", "your_iam_ak")
11 os.Setenv("QIANFAN_SECRET_KEY", "your_iam_sk")
12
13 ca := qianfan.NewConsoleAction()
14
15 res, err := ca.Call(context.TODO(),
16 // 调用本文API,该参数值为固定值,无需修改;对应API调用文档-请求结构-请求地址的后缀
17 "/wenxinworkshop/entity/list", "",
18 // 请查看本文请求参数说明,根据实际使用选择参数;对应API调用文档-请求参数-Body参数
19 map[string]interface{}{
20 "offset": 0,
21 "pageSize": 10,
22 "datasetId": "ds-7pkzh1exthpuy10n",
23 "importTime": []int{},
24 "annoTime": []int{},
25 "tabType": 1,
26 "labelId": "",
27 })
28 if err != nil {
29 panic(err)
30 }
31 fmt.Println(string(res.Body))
32
33}
1import com.baidubce.qianfan.Qianfan;
2import com.baidubce.qianfan.model.console.ConsoleResponse;
3import com.baidubce.qianfan.util.CollUtils;
4import com.baidubce.qianfan.util.Json;
5import java.util.Map;
6
7public class Dome {
8 public static void main(String args[]){
9 // 使用安全认证AK/SK鉴权,替换下列示例中参数,安全认证Access Key替换your_iam_ak,Secret Key替换your_iam_sk
10 Qianfan qianfan = new Qianfan("your_iam_ak", "your_iam_sk");
11
12 ConsoleResponse<Map<String, Object>> response = qianfan.console()
13 // 调用本文API,该参数值为固定值,无需修改;对应API调用文档-请求结构-请求地址的后缀
14 .route("/wenxinworkshop/entity/list")
15 // 需要传入参数的场景,可以自行封装请求类,或者使用Map.of()来构建请求Body
16 // Java 8可以使用SDK提供的CollUtils.mapOf()来替代Map.of()
17 // 请查看本文请求参数说明,根据实际使用选择参数;对应API调用文档-请求参数-Body参数
18 .body(CollUtils.mapOf(
19 "offset", 0,
20 "pageSize", 10,
21 "datasetId", "ds-7pkzh1exthpuy10n",
22 "importTime", new String[]{},
23 "annoTime", new String[]{},
24 "tabType", 1,
25 "labelId", ""
26 ))
27 .execute();
28
29 System.out.println(Json.serialize(response));
30 }
31}
1import {consoleAction, setEnvVariable} from "@baiducloud/qianfan";
2
3// 使用安全认证AK/SK鉴权,通过环境变量初始化;替换下列示例中参数,安全认证Access Key替换your_iam_ak,Secret Key替换your_iam_sk
4setEnvVariable('QIANFAN_ACCESS_KEY','your_iam_ak');
5setEnvVariable('QIANFAN_SECRET_KEY','your_iam_sk');
6
7async function main() {
8 //base_api_route:调用本文API,该参数值为固定值,无需修改;对应API调用文档-请求结构-请求地址的后缀
9 //data:请查看本文请求参数说明,根据实际使用选择参数;对应API调用文档-请求参数-Body参数
10 const res = await consoleAction({base_api_route: '/wenxinworkshop/entity/list', data: {
11 "offset": 0,
12 "pageSize": 10,
13 "datasetId": "ds-7pkzh1exthpuy10n",
14 "importTime": [],
15 "annoTime": [],
16 "tabType": 1,
17 "labelId": ""
18 }
19 });
20
21 console.log(res);
22}
23
24main();
返回示例
1{
2 "log_id": "15jk2d6tkisnidt9",
3 "result": {
4 "totalAll": 138,
5 "total": 102,
6 "items": [
7 {
8 "id": "172383aab601a661be32e89bafccccd17789ba45d5a24cb5db4ec9722fbebe63_1ff9e03fe288419fa1c693b75e38e96e",
9 "name": "",
10 "labels": [
11 {
12 "label_id": "654887c72733b0c09e2d5bc0",
13 "name": "ERNIE_BOT",
14 "color": "#1A73E8"
15 }
16 ],
17 "url": "https://bj.bcebos.com/sdc-default/_system_/dataset/ds-2x3fxhunezkuwu4w/texts/data/raw_172383aab601a661be32e89bafccccd17789ba45d5a24cb5db4ec9722fbebe63_1ff9e03fe288419fa1c693b75e38e96e?authorization=bce-auth-v1%2F50c8bb753dcb4e1d8646bb1ffefd3503%2F2023-11-08T08%3A49%3A27Z%2F7200%2Fhost%2Ff45a5fd525e465f03c21ce3962422f3dbf71d1fd0e9ee8e0b591830845bd333b",
18 "memorySize": 0.01,
19 "isEncrypted": False,
20 "textExtra": {
21 "domainType": "",
22 "taskType": "",
23 "wordNum": 0,
24 "repetitiveCharRatio": 0,
25 "specialCharRatio": 0,
26 "flaggedWordRatio": 0,
27 "langProb": 0,
28 "perplexity": 0
29 }
30 },
31 {
32 "id": "13d48401c36e2442ffb0dba377f63e7706799d96a908d950baddb72c4d61f2f6_a48201bb7a72430288ef090790a59ad6",
33 "name": "",
34 "labels": [
35 {
36 "label_id": "654887c72733b0c09e2d5bc0",
37 "name": "ERNIE_BOT",
38 "color": "#1A73E8"
39 }
40 ],
41 "url": "https://bj.bcebos.com/sdc-default/_system_/dataset/ds-2x3fxhunezkuwu4w/texts/data/raw_13d48401c36e2442ffb0dba377f63e7706799d96a908d950baddb72c4d61f2f6_a48201bb7a72430288ef090790a59ad6?authorization=bce-auth-v1%2F50c8bb753dcb4e1d8646bb1ffefd3503%2F2023-11-08T08%3A49%3A27Z%2F7200%2Fhost%2F9b863c3444f671d8667bc32fe31517f05e372878b13b5b56460946236785b736",
42 "memorySize": 0.01,
43 "isEncrypted": False,
44 "textExtra": {
45 "domainType": "",
46 "taskType": "",
47 "wordNum": 0,
48 "repetitiveCharRatio": 0,
49 "specialCharRatio": 0,
50 "flaggedWordRatio": 0,
51 "langProb": 0,
52 "perplexity": 0
53 }
54 },
55 ]
56 },
57 "status": 200,
58 "success": True
59}
1{
2 "log_id": "15jk2d6tkisnidt9",
3 "result": {
4 "totalAll": 138,
5 "total": 102,
6 "items": [
7 {
8 "id": "172383aab601a661be32e89bafccccd17789ba45d5a24cb5db4ec9722fbebe63_1ff9e03fe288419fa1c693b75e38e96e",
9 "name": "",
10 "labels": [
11 {
12 "label_id": "654887c72733b0c09e2d5bc0",
13 "name": "ERNIE_BOT",
14 "color": "#1A73E8"
15 }
16 ],
17 "url": "https://bj.bcebos.com/sdc-default/_system_/dataset/ds-2x3fxhunezkuwu4w/texts/data/raw_172383aab601a661be32e89bafccccd17789ba45d5a24cb5db4ec9722fbebe63_1ff9e03fe288419fa1c693b75e38e96e?authorization=bce-auth-v1%2F50c8bb753dcb4e1d8646bb1ffefd3503%2F2023-11-08T08%3A49%3A27Z%2F7200%2Fhost%2Ff45a5fd525e465f03c21ce3962422f3dbf71d1fd0e9ee8e0b591830845bd333b",
18 "memorySize": 0.01,
19 "isEncrypted": false,
20 "textExtra": {
21 "domainType": "",
22 "taskType": "",
23 "wordNum": 0,
24 "repetitiveCharRatio": 0,
25 "specialCharRatio": 0,
26 "flaggedWordRatio": 0,
27 "langProb": 0,
28 "perplexity": 0
29 }
30 },
31 {
32 "id": "13d48401c36e2442ffb0dba377f63e7706799d96a908d950baddb72c4d61f2f6_a48201bb7a72430288ef090790a59ad6",
33 "name": "",
34 "labels": [
35 {
36 "label_id": "654887c72733b0c09e2d5bc0",
37 "name": "ERNIE_BOT",
38 "color": "#1A73E8"
39 }
40 ],
41 "url": "https://bj.bcebos.com/sdc-default/_system_/dataset/ds-2x3fxhunezkuwu4w/texts/data/raw_13d48401c36e2442ffb0dba377f63e7706799d96a908d950baddb72c4d61f2f6_a48201bb7a72430288ef090790a59ad6?authorization=bce-auth-v1%2F50c8bb753dcb4e1d8646bb1ffefd3503%2F2023-11-08T08%3A49%3A27Z%2F7200%2Fhost%2F9b863c3444f671d8667bc32fe31517f05e372878b13b5b56460946236785b736",
42 "memorySize": 0.01,
43 "isEncrypted": false,
44 "textExtra": {
45 "domainType": "",
46 "taskType": "",
47 "wordNum": 0,
48 "repetitiveCharRatio": 0,
49 "specialCharRatio": 0,
50 "flaggedWordRatio": 0,
51 "langProb": 0,
52 "perplexity": 0
53 }
54 },
55 ]
56 },
57 "status": 200,
58 "success": true
59}
60错误码
1{
2 log_id: '15jk2d6tkisnidt9',
3 result: {
4 totalAll: 138,
5 total: 102,
6 items: [
7 {
8 id: '172383aab601a661be32e89bafccccd17789ba45d5a24cb5db4ec9722fbebe63_1ff9e03fe288419fa1c693b75e38e96e',
9 name: '',
10 labels: [
11 {
12 label_id: '654887c72733b0c09e2d5bc0',
13 name: 'ERNIE_BOT',
14 color: '#1A73E8'
15 }
16 ],
17 url: 'https://bj.bcebos.com/sdc-default/_system_/dataset/ds-2x3fxhunezkuwu4w/texts/data/raw_172383aab601a661be32e89bafccccd17789ba45d5a24cb5db4ec9722fbebe63_1ff9e03fe288419fa1c693b75e38e96e?authorization=bce-auth-v1/50c8bb753dcb4e1d8646bb1ffefd3503/2023-11-08T08:49:27Z/7200/host/f45a5fd525e465f03c21ce3962422f3dbf71d1fd0e9ee8e0b591830845bd333b',
18 memorySize: 0.01,
19 isEncrypted: false,
20 textExtra: {
21 domainType: '',
22 taskType: '',
23 wordNum: 0,
24 repetitiveCharRatio: 0,
25 specialCharRatio: 0,
26 flaggedWordRatio: 0,
27 langProb: 0,
28 perplexity: 0
29 }
30 },
31 {
32 id: '13d48401c36e2442ffb0dba377f63e7706799d96a908d950baddb72c4d61f2f6_a48201bb7a72430288ef090790a59ad6',
33 name: '',
34 labels: [
35 {
36 label_id: '654887c72733b0c09e2d5bc0',
37 name: 'ERNIE_BOT',
38 color: '#1A73E8'
39 }
40 ],
41 url: 'https://bj.bcebos.com/sdc-default/_system_/dataset/ds-2x3fxhunezkuwu4w/texts/data/raw_13d48401c36e2442ffb0dba377f63e7706799d96a908d950baddb72c4d61f2f6_a48201bb7a72430288ef090790a59ad6?authorization=bce-auth-v1/50c8bb753dcb4e1d8646bb1ffefd3503/2023-11-08T08:49:27Z/7200/host/9b863c3444f671d8667bc32fe31517f05e372878b13b5b56460946236785b736',
42 memorySize: 0.01,
43 isEncrypted: false,
44 textExtra: {
45 domainType: '',
46 taskType: '',
47 wordNum: 0,
48 repetitiveCharRatio: 0,
49 specialCharRatio: 0,
50 flaggedWordRatio: 0,
51 langProb: 0,
52 perplexity: 0
53 }
54 },
55 ]
56 },
57 status: 200,
58 success: true
59}
请求参数
名称 | 类型 | 必填 | 描述 |
---|---|---|---|
datasetId | string | 是 | 数据集版本ID,说明: (1)可以通过以下任一方式获取该字段值: · 方式一,通过调用创建数据集接口,返回的datasetId字段获取 · 方式二,在控制台-数据集管理列表页面,点击详情,在版本信息页查看,如下图所示: ![]() (2)该字段新增支持string类型,如果之前使用的是int类型,建议变更为string类型,后续可能将逐步废弃int类型;例如之前是通过调用创建数据集V1接口,返回的id字段获取,请替换为接口返回的datasetId字段获取 |
offset | int | 否 | 分页偏移,默认0 |
pageSize | int | 否 | 分页大小,说明: · 范围[1,30],超出最大范围按最大范围处理 · 默认20 |
importTime | List<integer> | 否 | 导入日期区间,可以获取该区间数据,说明: 需传入2个日期的时间戳,单位毫秒,分别是开始日期时间戳、结束日期时间戳 |
annoTime | List<integer> | 否 | 标注日期区间,可以获取该区间数据,说明: 需传入2个日期的时间戳,单位毫秒,分别是开始日期时间戳、结束日期时间戳 |
tabType | int | 否 | 可选值如下: · 1:已标注 · 2:未标注 · 0:全部 |
labelId | string | 否 | 标签id,说明: · 多个labelId用英文逗号分开,如1,2 · 仅文生图支持 |
返回参数
说明:返回的部分字段如下,未说明的字段暂无需关注。
名称 | 类型 | 描述 |
---|---|---|
log_id | string | 操作记录id |
result | object | 返回结果 |
status | int | 状态码 |
success | bool | 是否操作成功,说明: · true:成功 · false:失败 |
result说明
名称 | 类型 | 描述 |
---|---|---|
totalAll | int | 总数量 |
total | int | 筛选后的数量 |
items | List<object> | 样本列表 |
items说明
名称 | 类型 | 描述 |
---|---|---|
id | string | 样本ID |
name | string | 样本名称,图片才有 |
labels | List<object> | 标签列表 |
url | string | 存储地址 |
memorySize | int | 样本大小,单位为MB |
isEncrypted | bool | 是否加密 |
textExtra | object | 文档附加说明 |
label说明
名称 | 类型 | 描述 |
---|---|---|
label_id | string | 标签id |
name | string | 标签名称 |
color | string | 标签颜色 |
textExtra说明
名称 | 类型 | 描述 |
---|---|---|
domainType | string | 领域类型 |
taskType | string | 任务类型 |
wordNum | int | 词数目 |
repetitiveCharRatio | int | 重复率 |
specialCharRatio | int | 特殊字符 |
flaggedWordRatio | int | 色暴词率 |
langProb | int | 语言概率 |
perplexity | int | 困惑率 |