请求体 | 文本输入Python请求示例 import dashscope
import os
messages = [
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': '你是谁？'}
]
response = dashscope.Generation.call(
api_key=os.getenv('DASHSCOPE_API_KEY'),
model="qwen-turbo",
messages=messages,
result_format='message'
)
print(response)
响应示例 {
"status_code": 200,
"request_id": "902fee3b-f7f0-9a8c-96a1-6b4ea25af114",
"code": "",
"message": "",
"output": {
"text": null,
"finish_reason": null,
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "我是阿里云开发的一款超大规模语言模型，我叫通义千问。"
}
}
]
},
"usage": {
"input_tokens": 22,
"output_tokens": 17,
"total_tokens": 39
}
}
Java请求示例 // 建议dashscope SDK的版本 >= 2.12.0
import java.util.Arrays;
import java.lang.System;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;
public class Main {
public static GenerationResult callWithMessage() throws ApiException, NoApiKeyException, InputRequiredException {
Generation gen = new Generation();
Message systemMsg = Message.builder()
.role(Role.SYSTEM.getValue())
.content("You are a helpful assistant.")
.build();
Message userMsg = Message.builder()
.role(Role.USER.getValue())
.content("你是谁？")
.build();
GenerationParam param = GenerationParam.builder()
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("qwen-turbo")
.messages(Arrays.asList(systemMsg, userMsg))
.resultFormat(GenerationParam.ResultFormat.MESSAGE)
.build();
return gen.call(param);
}
public static void main(String[] args) {
try {
GenerationResult result = callWithMessage();
System.out.println(JsonUtils.toJson(result));
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
// 使用日志框架记录异常信息
System.err.println("An error occurred while calling the generation service: " + e.getMessage());
}
System.exit(0);
}
}
响应示例 {
"requestId": "86dd52a9-23ec-9804-8f82-85f4c7fd5114",
"usage": {
"input_tokens": 22,
"output_tokens": 17,
"total_tokens": 39
},
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "我是阿里云开发的一款超大规模语言模型，我叫通义千问。"
}
}
]
}
}
curl请求示例 curl --location "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "qwen-turbo",
"input":{
"messages":[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "你是谁？"
}
]
},
"parameters": {
"result_format": "message"
}
}'
响应示例 {
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "我是通义千问，由阿里云开发的AI助手。我被设计用来回答各种问题、提供信息和与用户进行对话。有什么我可以帮助你的吗？"
}
}
]
},
"usage": {
"total_tokens": 58,
"output_tokens": 36,
"input_tokens": 22
},
"request_id": "39377fd7-26dd-99f5-b539-5fd004b6ecb5"
}
图像输入Python请求示例 import dashscope
import os
messages = [
{
"role": "user",
"content": [
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"},
{"text": "这些是什么?"}
]
}
]
response = dashscope.MultiModalConversation.call(
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen-vl-max-0809',
messages=messages
)
print(response)
响应示例 {
"status_code": 200,
"request_id": "3a031529-707f-9b7d-968c-172e7533debc",
"code": "",
"message": "",
"output": {
"text": null,
"finish_reason": null,
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": [
{
"text": "图1中是一名女子和狗在沙滩上玩耍。\n图2是孟加拉虎的插画，它正向镜头走来。\n图3里是一只可爱的小白兔。"
}
]
}
}
]
},
"usage": {
"input_tokens": 3743,
"output_tokens": 41,
"image_tokens": 3697
}
}
Java请求示例 // Copyright (c) Alibaba, Inc. and its affiliates.
import java.util.Arrays;
import java.util.Collections;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
public class Main {
public static void simpleMultiModalConversationCall()
throws ApiException, NoApiKeyException, UploadFileException {
MultiModalConversation conv = new MultiModalConversation();
MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
.content(Arrays.asList(
Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"),
Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"),
Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"),
Collections.singletonMap("text", "这些是什么?"))).build();
MultiModalConversationParam param = MultiModalConversationParam.builder()
.model("qwen-vl-plus")
.message(userMessage)
.build();
MultiModalConversationResult result = conv.call(param);
System.out.println(JsonUtils.toJson(result));
}
public static void main(String[] args) {
try {
simpleMultiModalConversationCall();
} catch (ApiException | NoApiKeyException | UploadFileException e) {
System.out.println(e.getMessage());
}
System.exit(0);
}
}
响应示例 {
"requestId": "dcb38a0f-fd69-9071-bcde-c4530f9a7559",
"usage": {
"input_tokens": 3740,
"output_tokens": 48
},
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": [
{
"text": "图1中是一名女子和一只大金毛在沙滩上玩耍。\n图2是孟加拉虎的写实照片，老虎正向镜头走来。\n图3是一幅插画，主要展示了一只兔子。"
}
]
}
}
]
}
}
curl请求示例 curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen-vl-plus",
"input":{
"messages":[
{
"role": "user",
"content": [
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"},
{"text": "这些是什么?"}
]
}
]
}
}'
响应示例 {
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": [
{
"text": "图1中是一名女子和一只大金毛在沙滩上玩耍。\n图2是孟加拉虎的写实照片，老虎正向镜头走来。\n图3是一幅插画，主要展示了一只兔子。"
}
]
}
}
]
},
"usage": {
"output_tokens": 48,
"input_tokens": 3740,
"image_tokens": 3697
},
"request_id": "eb6204ea-4cba-91b1-95ab-e7836b7355d6"
}
视频输入请求示例 响应示例 {
"status_code": 200,
"request_id": "157fab7e-b9ed-912c-8a8b-72495fbc3938",
"code": "",
"message": "",
"output": {
"text": null,
"finish_reason": null,
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": [
{
"text": "视频的内容是演示如何使用阿里云的模型体验平台。"
}
]
}
}
]
},
"usage": {
"input_tokens": 3725,
"output_tokens": 14,
"video_tokens": 3700
}
}
音频输入Python请求示例 import dashscope
import os
messages = [
{
"role": "user",
"content": [
{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"},
{"text": "这段音频在说什么?"}
]
}
]
response = dashscope.MultiModalConversation.call(
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen2-audio-instruct',
messages=messages
)
print(response)
响应示例 {
"status_code": 200,
"request_id": "cd6a86c7-ff55-9f3c-a379-d434e5af8079",
"code": "",
"message": "",
"output": {
"text": null,
"finish_reason": null,
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": [
{
"text": "这段音频说的是:'欢迎使用阿里云'"
}
]
}
}
]
},
"usage": {
"input_tokens": 33,
"output_tokens": 10,
"audio_tokens": 85
}
}
Java请求示例 import java.util.Arrays;
import java.util.Collections;
import java.lang.System;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
public class Main {
public static void simpleMultiModalConversationCall()
throws ApiException, NoApiKeyException, UploadFileException {
MultiModalConversation conv = new MultiModalConversation();
MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
.content(Arrays.asList(Collections.singletonMap("audio", "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"),
Collections.singletonMap("text", "这段音频在说什么?"))).build();
MultiModalConversationParam param = MultiModalConversationParam.builder()
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("qwen2-audio-instruct")
.message(userMessage)
.build();
MultiModalConversationResult result = conv.call(param);
System.out.println(JsonUtils.toJson(result));
}
public static void main(String[] args) {
try {
simpleMultiModalConversationCall();
} catch (ApiException | NoApiKeyException | UploadFileException e) {
System.out.println(e.getMessage());
}
System.exit(0);
}
}
响应示例 {
"requestId": "e701e39b-4dfa-9dde-805a-f83782b3394a",
"usage": {
"input_tokens": 33,
"output_tokens": 10
},
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": [
{
"text": "这段音频说的是:'欢迎使用阿里云'"
}
]
}
}
]
}
}
curl请求示例 curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen2-audio-instruct",
"input":{
"messages":[
{
"role": "system",
"content": [
{"text": "You are a helpful assistant."}
]
},
{
"role": "user",
"content": [
{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"},
{"text": "这段音频在说什么?"}
]
}
]
}
}'
响应示例 {
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": [
{
"text": "这段音频说的是:'欢迎使用阿里云'"
}
]
}
}
]
},
"usage": {
"audio_tokens": 85,
"output_tokens": 10,
"input_tokens": 33
},
"request_id": "db617e5b-d706-9143-b011-8b0f05fe8fa3"
}
流式输出Python请求示例 import dashscope
import os
messages = [
{'role':'system','content':'you are a helpful assistant'},
{'role': 'user','content': '你是谁？'}
]
responses = dashscope.Generation.call(
api_key=os.getenv('DASHSCOPE_API_KEY'),
model="qwen-turbo",
messages=messages,
result_format='message',
stream=True,
incremental_output=True
)
for response in responses:
print(response)
响应示例 {"status_code": 200, "request_id": "xxx", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "我是"}}]}, "usage": {"input_tokens": 21, "output_tokens": 1, "total_tokens": 22}}
{"status_code": 200, "request_id": "xxx", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "通"}}]}, "usage": {"input_tokens": 21, "output_tokens": 2, "total_tokens": 23}}
{"status_code": 200, "request_id": "xxx", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "义"}}]}, "usage": {"input_tokens": 21, "output_tokens": 3, "total_tokens": 24}}
{"status_code": 200, "request_id": "xxx", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "千问，由阿里"}}]}, "usage": {"input_tokens": 21, "output_tokens": 8, "total_tokens": 29}}
{"status_code": 200, "request_id": "xxx", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "云开发的AI助手。我被"}}]}, "usage": {"input_tokens": 21, "output_tokens": 16, "total_tokens": 37}}
{"status_code": 200, "request_id": "xxx", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "设计用来回答各种问题、提供信息"}}]}, "usage": {"input_tokens": 21, "output_tokens": 24, "total_tokens": 45}}
{"status_code": 200, "request_id": "xxx", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "和与用户进行对话。有什么我可以"}}]}, "usage": {"input_tokens": 21, "output_tokens": 32, "total_tokens": 53}}
{"status_code": 200, "request_id": "xxx", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "stop", "message": {"role": "assistant", "content": "帮助你的吗？"}}]}, "usage": {"input_tokens": 21, "output_tokens": 36, "total_tokens": 57}}
Java请求示例 import java.util.Arrays;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;
import io.reactivex.Flowable;
import java.lang.System;
public class Main {
private static final Logger logger = LoggerFactory.getLogger(Main.class);
private static void handleGenerationResult(GenerationResult message) {
System.out.println(JsonUtils.toJson(message));
}
public static void streamCallWithMessage(Generation gen, Message userMsg)
throws NoApiKeyException, ApiException, InputRequiredException {
GenerationParam param = buildGenerationParam(userMsg);
Flowable<GenerationResult> result = gen.streamCall(param);
result.blockingForEach(message -> handleGenerationResult(message));
}
private static GenerationParam buildGenerationParam(Message userMsg) {
return GenerationParam.builder()
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("qwen-turbo")
.messages(Arrays.asList(userMsg))
.resultFormat(GenerationParam.ResultFormat.MESSAGE)
.incrementalOutput(true)
.build();
}
public static void main(String[] args) {
try {
Generation gen = new Generation();
Message userMsg = Message.builder().role(Role.USER.getValue()).content("你是谁？").build();
streamCallWithMessage(gen, userMsg);
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
logger.error("An exception occurred: {}", e.getMessage());
}
System.exit(0);
}
}
响应示例 {"requestId":"xxx","usage":{"input_tokens":11,"output_tokens":1,"total_tokens":12},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":"我是"}}]}}
{"requestId":"xxx","usage":{"input_tokens":11,"output_tokens":2,"total_tokens":13},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":"通"}}]}}
{"requestId":"xxx","usage":{"input_tokens":11,"output_tokens":3,"total_tokens":14},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":"义"}}]}}
{"requestId":"xxx","usage":{"input_tokens":11,"output_tokens":8,"total_tokens":19},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":"千问，由阿里"}}]}}
{"requestId":"xxx","usage":{"input_tokens":11,"output_tokens":16,"total_tokens":27},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":"云开发的AI助手。我被"}}]}}
{"requestId":"xxx","usage":{"input_tokens":11,"output_tokens":24,"total_tokens":35},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":"设计用来回答各种问题、提供信息"}}]}}
{"requestId":"xxx","usage":{"input_tokens":11,"output_tokens":32,"total_tokens":43},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":"和与用户进行对话。有什么我可以"}}]}}
{"requestId":"xxx","usage":{"input_tokens":11,"output_tokens":36,"total_tokens":47},"output":{"choices":[{"finish_reason":"stop","message":{"role":"assistant","content":"帮助你的吗？"}}]}}
curl请求示例 curl --location "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--header "X-DashScope-SSE: enable" \
--data '{
"model": "qwen-turbo",
"input":{
"messages":[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "你是谁？"
}
]
},
"parameters": {
"result_format": "message",
"incremental_output":true
}
}'
响应示例 id:1
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"我是","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":23,"input_tokens":22,"output_tokens":1},"request_id":"xxx"}
id:2
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"通","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":24,"input_tokens":22,"output_tokens":2},"request_id":"xxx"}
id:3
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"义","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":25,"input_tokens":22,"output_tokens":3},"request_id":"xxx"}
id:4
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"千问，由阿里","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":30,"input_tokens":22,"output_tokens":8},"request_id":"xxx"}
id:5
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"云开发的AI助手。我被","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":38,"input_tokens":22,"output_tokens":16},"request_id":"xxx"}
id:6
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"设计用来回答各种问题、提供信息","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":46,"input_tokens":22,"output_tokens":24},"request_id":"xxx"}
id:7
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"和与用户进行对话。有什么我可以","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":54,"input_tokens":22,"output_tokens":32},"request_id":"xxx"}
id:8
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"帮助你的吗？","role":"assistant"},"finish_reason":"stop"}]},"usage":{"total_tokens":58,"input_tokens":22,"output_tokens":36},"request_id":"xxx"}
联网搜索Python请求示例 import dashscope
import os
messages = [
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': '杭州明天天气是什么？'}
]
response = dashscope.Generation.call(
api_key=os.getenv('DASHSCOPE_API_KEY'),
model="qwen-turbo",
messages=messages,
enable_search=True,
result_format='message'
)
print(response)
响应示例 {
"status_code": 200,
"request_id": "c264df1f-0ef3-9323-a55b-83adc5ee48e6",
"code": "",
"message": "",
"output": {
"text": null,
"finish_reason": null,
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "根据提供的信息，杭州明天的天气预报如下：\n\n- 明天白天天气晴朗，东风，风力4级。\n- 明天夜间天气多云，东北风，风力4级。\n\n请注意，这是一则历史预报信息，具体实际天气可能会有所变化。建议您在出行前再次查看最新的天气预报以获取最准确的信息。"
}
}
]
},
"usage": {
"input_tokens": 885,
"output_tokens": 76,
"plugins": {
"search": {
"count": 1
}
},
"total_tokens": 961
}
}
Java请求示例 // 建议dashscope SDK的版本 >= 2.12.0
import java.util.Arrays;
import java.lang.System;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;
public class Main {
public static GenerationResult callWithMessage() throws ApiException, NoApiKeyException, InputRequiredException {
Generation gen = new Generation();
Message systemMsg = Message.builder()
.role(Role.SYSTEM.getValue())
.content("You are a helpful assistant.")
.build();
Message userMsg = Message.builder()
.role(Role.USER.getValue())
.content("明天杭州什么天气？")
.build();
GenerationParam param = GenerationParam.builder()
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("qwen-turbo")
.messages(Arrays.asList(systemMsg, userMsg))
.resultFormat(GenerationParam.ResultFormat.MESSAGE)
.enableSearch(true)
.build();
return gen.call(param);
}
public static void main(String[] args) {
try {
GenerationResult result = callWithMessage();
System.out.println(JsonUtils.toJson(result));
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
// 使用日志框架记录异常信息
System.err.println("An error occurred while calling the generation service: " + e.getMessage());
}
System.exit(0);
}
}
响应示例 {
"requestId": "4e0a961c-77bc-92a3-a65c-b1319fedc6bf",
"usage": {
"input_tokens": 901,
"output_tokens": 73,
"total_tokens": 974
},
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "明天，即2024年9月14日，杭州的天气预报显示为多云，有东北风，风力预计为4级。最低温度预计为26摄氏度，最高温度预计为32摄氏度。请注意，天气预报可能会有所变动，建议在出行前再次查看最新的天气预报信息。"
}
}
]
}
}
curl请求示例 curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-turbo",
"input":{
"messages":[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "明天杭州天气如何？"
}
]
},
"parameters": {
"enable_search": true,
"result_format": "message"
}
}'
响应示例 {
"output": {
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "根据提供的信息，明天即2024年9月14日，杭州的天气预报显示如下：\n\n- 夜间天气：多云\n- 白天天气：多云\n- 风向：东北风\n- 风力：4级\n- 湿度：80%\n- 最低温度：26.0摄氏度\n- 最高温度：32.0摄氏度\n\n请注意，天气预报可能会有变化，建议在出行前再次查看最新的天气预报信息。"
}
}
]
},
"usage": {
"plugins": {
"search": {
"count": 1
}
},
"total_tokens": 1029,
"output_tokens": 114,
"input_tokens": 915
},
"request_id": "2e840007-683a-93c1-bd2d-84003ee6346e"
}
工具调用Python请求示例 import dashscope
import os
tools = [
{
"type": "function",
"function": {
"name": "get_current_time",
"description": "当你想知道现在的时间时非常有用。",
"parameters": {}
}
},
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "当你想查询指定城市的天气时非常有用。",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "城市或县区，比如北京市、杭州市、余杭区等。"
}
}
},
"required": [
"location"
]
}
}
]
messages = [{"role": "user", "content": "杭州天气怎么样"}]
response = dashscope.Generation.call(
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen-max',
messages=messages,
tools=tools,
result_format='message'
)
print(response)
响应示例 {
"status_code": 200,
"request_id": "28d9b918-6287-95d1-9876-a67a9257c0c6",
"code": "",
"message": "",
"output": {
"text": null,
"finish_reason": null,
"choices": [
{
"finish_reason": "tool_calls",
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "get_current_weather",
"arguments": "{\"location\": \"杭州市\"}"
},
"index": 0,
"id": "call_e63b80aab9df4950b391d0",
"type": "function"
}
]
}
}
]
},
"usage": {
"input_tokens": 218,
"output_tokens": 18,
"total_tokens": 236
}
}
Java请求示例 import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import com.alibaba.dashscope.aigc.conversation.ConversationParam.ResultFormat;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.tools.FunctionDefinition;
import com.alibaba.dashscope.tools.ToolFunction;
import com.alibaba.dashscope.utils.JsonUtils;
import com.fasterxml.jackson.databind.node.ObjectNode;
import com.github.victools.jsonschema.generator.Option;
import com.github.victools.jsonschema.generator.OptionPreset;
import com.github.victools.jsonschema.generator.SchemaGenerator;
import com.github.victools.jsonschema.generator.SchemaGeneratorConfig;
import com.github.victools.jsonschema.generator.SchemaGeneratorConfigBuilder;
import com.github.victools.jsonschema.generator.SchemaVersion;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
public class Main {
public class GetWeatherTool {
private String location;
public GetWeatherTool(String location) {
this.location = location;
}
public String call() {
return location+"今天是晴天";
}
}
public class GetTimeTool {
public GetTimeTool() {
}
public String call() {
LocalDateTime now = LocalDateTime.now();
DateTimeFormatter formatter = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
String currentTime = "当前时间：" + now.format(formatter) + "。";
return currentTime;
}
}
public static void SelectTool()
throws NoApiKeyException, ApiException, InputRequiredException {
SchemaGeneratorConfigBuilder configBuilder =
new SchemaGeneratorConfigBuilder(SchemaVersion.DRAFT_2020_12, OptionPreset.PLAIN_JSON);
SchemaGeneratorConfig config = configBuilder.with(Option.EXTRA_OPEN_API_FORMAT_VALUES)
.without(Option.FLATTENED_ENUMS_FROM_TOSTRING).build();
SchemaGenerator generator = new SchemaGenerator(config);
ObjectNode jsonSchema_weather = generator.generateSchema(GetWeatherTool.class);
ObjectNode jsonSchema_time = generator.generateSchema(GetTimeTool.class);
FunctionDefinition fdWeather = FunctionDefinition.builder().name("get_current_weather").description("获取指定地区的天气")
.parameters(JsonUtils.parseString(jsonSchema_weather.toString()).getAsJsonObject()).build();
FunctionDefinition fdTime = FunctionDefinition.builder().name("get_current_time").description("获取当前时刻的时间")
.parameters(JsonUtils.parseString(jsonSchema_time.toString()).getAsJsonObject()).build();
Message systemMsg = Message.builder().role(Role.SYSTEM.getValue())
.content("You are a helpful assistant. When asked a question, use tools wherever possible.")
.build();
Message userMsg = Message.builder().role(Role.USER.getValue()).content("杭州天气").build();
List<Message> messages = new ArrayList<>();
messages.addAll(Arrays.asList(systemMsg, userMsg));
GenerationParam param = GenerationParam.builder()
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("qwen-max")
.messages(messages)
.resultFormat(ResultFormat.MESSAGE)
.tools(Arrays.asList(
ToolFunction.builder().function(fdWeather).build(),
ToolFunction.builder().function(fdTime).build()))
.build();
Generation gen = new Generation();
GenerationResult result = gen.call(param);
System.out.println(JsonUtils.toJson(result));
}
public static void main(String[] args) {
try {
SelectTool();
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
System.out.println(String.format("Exception %s", e.getMessage()));
}
System.exit(0);
}
}
响应示例 {
"requestId": "4d81dc3d-6570-9e33-9e7d-199b20bf568f",
"usage": {
"input_tokens": 245,
"output_tokens": 18,
"total_tokens": 263
},
"output": {
"choices": [
{
"finish_reason": "tool_calls",
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"type": "function",
"id": "call_26a878c36995449195e7f6",
"function": {
"name": "get_current_weather",
"arguments": "{\"location\": \"杭州\"}"
}
}
]
}
}
]
}
}
异步调用请求示例 # 您的Dashscope Python SDK版本需要不低于 1.19.0。
import asyncio
import platform
from dashscope.aigc.generation import AioGeneration
async def main():
response = await AioGeneration.call(
model="qwen-turbo",
messages=[{"role": "user", "content": "你是谁"}],
result_format="message",
)
print(response)
if platform.system() == "Windows":
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
asyncio.run(main())
响应示例 {
"status_code": 200,
"request_id": "124ca191-68a5-90b8-84bd-5ef944883a94",
"code": "",
"message": "",
"output": {
"text": null,
"finish_reason": null,
"choices": [
{
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "我是阿里云开发的一款超大规模语言模型，我叫通义千问。作为一个语言模型，我的目标是生成与给定词语相关的高质量文本，帮助用户获得准确、有用的信息，解决他们的问题和困惑。无论是工作上的需求，如撰写邮件、制作报告、代码编写，还是生活中的问题，如情感交流、日常生活建议，亦或是学习上的辅助，如历史知识、地理信息、数学计算等，我都会尽我所能提供帮助。请随时向我提问或寻求帮助，我会尽力满足您的需求。"
}
}
]
},
"usage": {
"input_tokens": 10,
"output_tokens": 114,
"total_tokens": 124
}
}
|