同步接口API详情

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),  # 如果您没有配置环境变量，请在此处用您的API Key进行替换
    # 以下为华北2（北京）地域的URL，调用时请将{WorkspaceId}替换为真实的业务空间ID，各地域的URL不同。
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1"
)

completion = client.embeddings.create(
    model="qwen3.7-text-embedding",
    input='衣服的质量杠杠的，很漂亮，不枉我等了这么久啊，喜欢，以后还来这里买',
    dimensions=1024, # 指定向量维度（仅 qwen3.7-text-embedding、text-embedding-v3及 text-embedding-v4支持该参数）
    encoding_format="float"
)

print(completion.model_dump_json())

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.embeddings.CreateEmbeddingResponse;
import com.openai.models.embeddings.EmbeddingCreateParams;

public class Main {
    public static void main(String[] args) {
        // 创建客户端，使用环境变量中的API密钥
        OpenAIClient client = OpenAIOkHttpClient.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // 以下为华北2（北京）地域的URL，调用时请将{WorkspaceId}替换为真实的业务空间ID，各地域的URL不同。
                .baseUrl("https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1")
                .build();

        // 创建向量化请求参数
        EmbeddingCreateParams params = EmbeddingCreateParams.builder()
                .model("qwen3.7-text-embedding")
                .input(EmbeddingCreateParams.Input.ofString("衣服的质量杠杠的，很漂亮，不枉我等了这么久啊，喜欢，以后还来这里买"))
                // 指定向量维度（仅 qwen3.7-text-embedding、text-embedding-v3及 text-embedding-v4支持该参数）
                .dimensions(1024)
                .build();

        try {
            // 发送请求并获取响应
            CreateEmbeddingResponse response = client.embeddings().create(params);
            System.out.println(response);
        } catch (Exception e) {
            System.err.println("请求出错，请查看错误码对照网页：");
            System.err.println("https://help.aliyun.com/zh/model-studio/faq-about-alibaba-cloud-model-studio?spm=a2c4g.11186623.help-menu-2400256.d_0_17_0.18733a66lTrcHv#1c38f58abfcml");
            System.err.println("错误详情：" + e.getMessage());
            e.printStackTrace();
        }
    }
}

curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/embeddings' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3.7-text-embedding",
    "input": "风急天高猿啸哀，渚清沙白鸟飞回，无边落木萧萧下，不尽长江滚滚来",
    "dimensions": 1024,
    "encoding_format": "float"
}'

# 通过 dashscope 命令行调用
export DASHSCOPE_API_KEY="your-api-key"
# 将 {WorkspaceId} 替换为业务空间ID，cn-beijing 替换为对应地域（新加坡: ap-southeast-1, 美东: us-east-1）
export DASHSCOPE_HTTP_BASE_URL="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
dashscope embeddings create -m text-embedding-v3 -i "你好世界"

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),  # 如果您没有配置环境变量，请在此处用您的API Key进行替换
    # 以下为华北2（北京）地域的URL，调用时请将{WorkspaceId}替换为真实的业务空间ID，各地域的URL不同。
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1"
)

completion = client.embeddings.create(
    model="qwen3.7-text-embedding",
    input=['风急天高猿啸哀', '渚清沙白鸟飞回', '无边落木萧萧下', '不尽长江滚滚来'],
    dimensions=1024,# 指定向量维度（仅 qwen3.7-text-embedding、text-embedding-v3及 text-embedding-v4支持该参数）
    encoding_format="float"
)

print(completion.model_dump_json())

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.embeddings.CreateEmbeddingResponse;
import com.openai.models.embeddings.EmbeddingCreateParams;

import java.util.Arrays;
import java.util.List;
import java.util.ArrayList;

public class Main {
    public static void main(String[] args) {
        // 创建客户端，使用环境变量中的API密钥
        OpenAIClient client = OpenAIOkHttpClient.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // 以下为华北2（北京）地域的URL，调用时请将{WorkspaceId}替换为真实的业务空间ID，各地域的URL不同。
                .baseUrl("https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1")
                .build();

        // 创建输入字符串列表
        List<String> inputList = Arrays.asList(
            "风急天高猿啸哀",
            "渚清沙白鸟飞回",
            "无边落木萧萧下",
            "不尽长江滚滚来"
        );

        // 存储所有响应的列表
        List<CreateEmbeddingResponse> responses = new ArrayList<>();

        // 循环处理每个字符串
        for (String text : inputList) {
            try {
                // 创建向量化请求参数
                EmbeddingCreateParams params = EmbeddingCreateParams.builder()
                        .model("qwen3.7-text-embedding")
                        .input(EmbeddingCreateParams.Input.ofString(text))
                        // 指定向量维度（仅 qwen3.7-text-embedding、text-embedding-v3及 text-embedding-v4支持该参数）
                        .dimensions(1024)
                        .build();

                // 发送请求并获取响应
                CreateEmbeddingResponse response = client.embeddings().create(params);
                responses.add(response);
                System.out.println("处理文本: " + text);
                System.out.println("向量化结果: " + response);
                System.out.println("------------------------");
            } catch (Exception e) {
                System.err.println("处理文本时出错: " + text);
                System.err.println("错误详情：" + e.getMessage());
                e.printStackTrace();
            }
        }

        // 打印总结信息
        System.out.println("\n总共处理了 " + responses.size() + " 个文本");
    }
}

curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/embeddings' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3.7-text-embedding",
    "input": [
        "风急天高猿啸哀",
        "渚清沙白鸟飞回",
        "无边落木萧萧下",
        "不尽长江滚滚来"
        ],
    "dimensions": 1024,
    "encoding_format": "float"
}'

import dashscope
from http import HTTPStatus
# 以下为华北2（北京）地域的配置，调用时请将{WorkspaceId}替换为真实的业务空间ID，各地域的配置不同。
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"

resp = dashscope.TextEmbedding.call(
    model="qwen3.7-text-embedding",
    input='衣服的质量杠杠的，很漂亮，不枉我等了这么久啊，喜欢，以后还来这里买',
    dimension=1024,  # 指定向量维度（仅 qwen3.7-text-embedding、text-embedding-v3及 text-embedding-v4支持该参数）
    output_type="dense&sparse"
)

print(resp) if resp.status_code == HTTPStatus.OK else print(resp)

import java.util.Arrays;
import com.alibaba.dashscope.embeddings.TextEmbedding;
import com.alibaba.dashscope.embeddings.TextEmbeddingParam;
import com.alibaba.dashscope.embeddings.TextEmbeddingResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;

/**
 * 千问文本向量模型调用示例
 */
public final class Main {
    public static void main(String[] args) {
        // 以下为华北2（北京）地域的配置，调用时请将{WorkspaceId}替换为真实的业务空间ID，各地域的配置不同。
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";
        try {
            // 构建请求参数
            TextEmbeddingParam param = TextEmbeddingParam
                    .builder()
                    .model("qwen3.7-text-embedding")  // 使用text-embedding-v4模型
                    .texts(Arrays.asList("衣服的质量杠杠的，很漂亮，不枉我等了这么久啊，喜欢，以后还来这里买"))  // 输入文本
                    .parameter("dimension", 1024)  // 指定向量维度（仅 qwen3.7-text-embedding、text-embedding-v3及 text-embedding-v4支持该参数）
                    .build();

            // 创建模型实例并调用
            TextEmbedding textEmbedding = new TextEmbedding();
            TextEmbeddingResult result = textEmbedding.call(param);

            // 输出结果
            System.out.println(result);

        } catch (ApiException | NoApiKeyException e) {
            System.out.println("调用失败：" + e.getMessage());
        }
    }
}

curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3.7-text-embedding",
    "input": {
        "texts": [
        "风急天高猿啸哀，渚清沙白鸟飞回，无边落木萧萧下，不尽长江滚滚来"
        ]
    },
    "parameters": {
        "dimension": 1024,
        "output_type": "dense"
    }
}'

import dashscope
from http import HTTPStatus
# 以下为华北2（北京）地域的配置，调用时请将{WorkspaceId}替换为真实的业务空间ID，各地域的配置不同。
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"

DASHSCOPE_MAX_BATCH_SIZE = 10

inputs = ['风急天高猿啸哀', '渚清沙白鸟飞回', '无边落木萧萧下', '不尽长江滚滚来']

result = None
batch_counter = 0
for i in range(0, len(inputs), DASHSCOPE_MAX_BATCH_SIZE):
    batch = inputs[i:i + DASHSCOPE_MAX_BATCH_SIZE]
    resp = dashscope.TextEmbedding.call(
        model="qwen3.7-text-embedding",
        input=batch,
        dimension=1024  # 指定向量维度（仅 qwen3.7-text-embedding、text-embedding-v3及 text-embedding-v4支持该参数）
    )
    if resp.status_code == HTTPStatus.OK:
        if result is None:
            result = resp
        else:
            for emb in resp.output['embeddings']:
                emb['text_index'] += batch_counter
                result.output['embeddings'].append(emb)
            result.usage['total_tokens'] += resp.usage['total_tokens']
    else:
        print(resp)
    batch_counter += len(batch)

print(result)

import java.util.Arrays;
import java.util.List;
import com.alibaba.dashscope.embeddings.TextEmbedding;
import com.alibaba.dashscope.embeddings.TextEmbeddingParam;
import com.alibaba.dashscope.embeddings.TextEmbeddingResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.embeddings.TextEmbeddingResultItem;
import com.alibaba.dashscope.utils.Constants;

public final class Main {
    private static final int DASHSCOPE_MAX_BATCH_SIZE = 10;

    public static void main(String[] args) {
        // 以下为华北2（北京）地域的配置，调用时请将{WorkspaceId}替换为真实的业务空间ID，各地域的配置不同。
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";
        List<String> inputs = Arrays.asList(
                "风急天高猿啸哀",
                "渚清沙白鸟飞回",
                "无边落木萧萧下",
                "不尽长江滚滚来"
        );

        TextEmbeddingResult result = null;
        int batchCounter = 0;

        for (int i = 0; i < inputs.size(); i += DASHSCOPE_MAX_BATCH_SIZE) {
            List<String> batch = inputs.subList(i, Math.min(i + DASHSCOPE_MAX_BATCH_SIZE, inputs.size()));
            TextEmbeddingParam param = TextEmbeddingParam.builder()
                    .model("qwen3.7-text-embedding")
                    .texts(batch)
                    .parameter("dimension", 1024)  // 指定向量维度（仅 qwen3.7-text-embedding、text-embedding-v3及 text-embedding-v4支持该参数）
                    .build();

            TextEmbedding textEmbedding = new TextEmbedding();
            try {
                TextEmbeddingResult resp = textEmbedding.call(param);
                if (resp != null) {
                    if (result == null) {
                        result = resp;
                    } else {
                        for (var emb : resp.getOutput().getEmbeddings()) {
                            emb.setTextIndex(emb.getTextIndex() + batchCounter);
                            result.getOutput().getEmbeddings().add(emb);
                        }
                        result.getUsage().setTotalTokens(result.getUsage().getTotalTokens() + resp.getUsage().getTotalTokens());
                    }
                } else {
                    System.out.println(resp);
                }
            } catch (ApiException | NoApiKeyException e) {
                e.printStackTrace();
            }
            batchCounter += batch.size();
        }

        System.out.println(result);
    }
}

curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3.7-text-embedding",
    "input": {
        "texts": [
          "风急天高猿啸哀",
          "渚清沙白鸟飞回",
          "无边落木萧萧下",
          "不尽长江滚滚来"
        ]
    },
    "parameters": {
          "dimension": 1024,
          "output_type": "dense"
    }
}'