Qwen-Coder adalah model bahasa yang dirancang untuk tugas-tugas pemrograman. Anda dapat menggunakan API-nya untuk menghasilkan kode, melengkapi kode, serta memanggil tool guna berinteraksi dengan sistem eksternal.
Kami menyarankan menggunakan model tujuan umum terbaru alih-alih model Qwen-Coder. Untuk informasi lebih lanjut, lihat Pembuatan teks guna memilih model yang sesuai dengan skenario Anda.
Mulai
Sebelum memulai, dapatkan Kunci API dan konfigurasikan sebagai Variabel lingkungan. Jika Anda menggunakan kit pengembangan perangkat lunak (SDK), Anda harus menginstal SDK OpenAI atau DashScope. Contoh berikut menunjukkan cara memanggil modelqwen3-coder-next untuk menulis fungsi Python yang mencari bilangan prima.
- OpenAI compatible-Chat Completions API
- DashScope
- Python
- Node.js
- curl
Contoh permintaanResponse
Copy
import os
from openai import OpenAI
client = OpenAI(
# Kunci API bervariasi berdasarkan Wilayah. Untuk mendapatkan Kunci API, kunjungi: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Alibaba Cloud Model Studio Anda: api_key="sk-xxx",
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
model="qwen3-coder-next",
messages=[
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': 'Write a Python function named find_prime_numbers that takes an integer n as a parameter and returns a list of all prime numbers less than n. Do not output non-code content or Markdown code blocks.'}],
)
print(completion.choices[0].message.content)
Copy
def find_prime_numbers(n):
if n <= 2:
return []
primes = []
for num in range(2, n):
is_prime = True
for i in range(2, int(num ** 0.5) + 1):
if num % i == 0:
is_prime = False
break
if is_prime:
primes.append(num)
return primes
Contoh permintaanResponse
Copy
import OpenAI from "openai";
const client = new OpenAI(
{
// Kunci API bervariasi berdasarkan Wilayah. Untuk mendapatkan Kunci API, kunjungi: https://www.alibabacloud.com/help/en/model-studio/get-api-key
// Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Model Studio Anda: apiKey: "sk-xxx",
apiKey: process.env.DASHSCOPE_API_KEY,
// URL berikut untuk wilayah Singapura. Saat melakukan panggilan, ganti {WorkspaceId} dengan ID ruang kerja aktual Anda. URL bervariasi berdasarkan wilayah.
baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
}
);
async function main() {
const completion = await client.chat.completions.create({
model: "qwen3-coder-next",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Write a Python function named find_prime_numbers that takes an integer n as a parameter and returns a list of all prime numbers less than n. Do not output non-code content or Markdown code blocks." }
],
});
console.log(completion.choices[0].message.content);
}
main();
Copy
def find_prime_numbers(n):
if n <= 2:
return []
primes = []
for num in range(2, n):
is_prime = True
for i in range(2, int(num ** 0.5) + 1):
if num % i == 0:
is_prime = False
break
if is_prime:
primes.append(num)
return primes
Contoh permintaanURL bervariasi berdasarkan wilayah.Response
Copy
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-coder-next",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Write a Python function named find_prime_numbers that takes an integer n as a parameter and returns a list of all prime numbers less than n. Do not output non-code content or Markdown code blocks."
}
]
}'
Copy
{
"model": "qwen3-coder-next",
"id": "chatcmpl-3123d5cb-01b8-9a90-98cc-5bffbb369xxx",
"choices": [
{
"message": {
"content": "def find_prime_numbers(n):\n if n <= 2:\n return []\n \n primes = []\n for num in range(2, n):\n is_prime = True\n for i in range(2, int(num ** 0.5) + 1):\n if num % i == 0:\n is_prime = False\n break\n if is_prime:\n primes.append(num)\n \n return primes",
"role": "assistant"
},
"index": 0,
"finish_reason": "stop"
}
],
"created": 1770108104,
"object": "chat.completion",
"usage": {
"total_tokens": 155,
"completion_tokens": 89,
"prompt_tokens": 66
}
}
- Python
- Java
- curl
Contoh permintaanResponse
Copy
import dashscope
import os
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'
messages = [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Write a Python function named find_prime_numbers that takes an integer n as a parameter and returns a list of all prime numbers less than n. Do not output non-code content or Markdown code blocks."
}
]
response = dashscope.Generation.call(
# Kunci API bervariasi berdasarkan Wilayah. Untuk mendapatkan Kunci API, kunjungi: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Alibaba Cloud Model Studio Anda: api_key = "sk-xxx",
api_key=os.getenv("DASHSCOPE_API_KEY"),
model="qwen3-coder-next",
messages=messages,
result_format="message"
)
if response.status_code == 200:
print(response.output.choices[0].message.content)
else:
print(f"Kode respons HTTP: {response.status_code}")
print(f"Kode error: {response.code}")
print(f"Pesan error: {response.message}")
Copy
def find_prime_numbers(n):
if n <= 2:
return []
primes = []
for num in range(2, n):
is_prime = True
for i in range(2, int(num ** 0.5) + 1):
if num % i == 0:
is_prime = False
break
if is_prime:
primes.append(num)
return primes
Contoh permintaanResponse
Copy
import java.util.Arrays;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
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.protocol.Protocol;
public class Main {
public static GenerationResult callWithMessage()
throws NoApiKeyException, ApiException, InputRequiredException {
String apiKey = System.getenv("DASHSCOPE_API_KEY");
Generation gen = new Generation(Protocol.HTTP.getValue(), "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1");
Message sysMsg = Message.builder()
.role(Role.SYSTEM.getValue())
.content("You are a helpful assistant.").build();
Message userMsg = Message.builder()
.role(Role.USER.getValue())
.content("Write a Python function named find_prime_numbers that takes an integer n as a parameter and returns a list of all prime numbers less than n. Do not output non-code content or Markdown code blocks.").build();
GenerationParam param = GenerationParam.builder()
.apiKey(apiKey)
.model("qwen3-coder-next")
.messages(Arrays.asList(sysMsg, userMsg))
.resultFormat(GenerationParam.ResultFormat.MESSAGE)
.build();
return gen.call(param);
}
public static void main(String[] args){
try {
GenerationResult result = callWithMessage();
System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent());
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
System.err.println("Exception permintaan: " + e.getMessage());
e.printStackTrace();
}
}
}
Copy
def find_prime_numbers(n):
if n <= 2:
return []
primes = []
for num in range(2, n):
is_prime = True
for i in range(2, int(num ** 0.5) + 1):
if num % i == 0:
is_prime = False
break
if is_prime:
primes.append(num)
return primes
Contoh permintaanURL bervariasi berdasarkan wilayah.Response
Copy
curl -X POST "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-coder-next",
"input":{
"messages":[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Write a Python function named find_prime_numbers that takes an integer n as a parameter and returns a list of all prime numbers less than n. Do not output non-code content or Markdown code blocks."
}
]
},
"parameters": {
"result_format": "message"
}
}'
Copy
{
"output": {
"choices": [
{
"message": {
"content": "def find_prime_numbers(n):\n if n <= 2:\n return []\n \n primes = []\n for num in range(2, n):\n is_prime = True\n for i in range(2, int(num ** 0.5) + 1):\n if num % i == 0:\n is_prime = False\n break\n if is_prime:\n primes.append(num)\n \n return primes",
"role": "assistant"
},
"finish_reason": "stop"
}
]
},
"usage": {
"total_tokens": 155,
"input_tokens": 66,
"output_tokens": 89
},
"request_id": "dd78b1cf-8029-46bb-9bea-b794ded7bxxx"
}
Kemampuan inti
Pemanggilan tool
Berikan model sekumpulan tool untuk berinteraksi dengan lingkungan eksternal, seperti membaca dan menulis file, memanggil API, atau mengoperasikan database. Model menentukan apakah dan bagaimana memanggil tool ini berdasarkan instruksi Anda. Untuk informasi lebih lanjut, lihat Function Calling. Alur lengkap pemanggilan tool mencakup:- Definisikan tool dan kirim permintaan: Definisikan daftar tool dalam permintaan dan instruksikan model untuk menyelesaikan tugas yang memerlukan tool tersebut.
- Jalankan tool: Urai
tool_callsyang dikembalikan oleh model dan panggil fungsi tool lokal yang sesuai untuk menjalankan tugas. - Kembalikan hasil eksekusi: Bungkus hasil eksekusi tool ke dalam format tertentu dan kirim kembali ke model. Model menggunakan hasil ini untuk menyelesaikan tugas akhir.
write_file untuk menyimpannya ke file lokal.
- OpenAI compatible-Chat Completions API
- DashScope
- Python
- Node.js
- curl
Copy
import os
import json
from openai import OpenAI
client = OpenAI(
# Kunci API bervariasi berdasarkan Wilayah. Untuk mendapatkan Kunci API, kunjungi: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Alibaba Cloud Model Studio Anda: api_key="sk-xxx",
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
tools = [
{
"type": "function",
"function": {
"name": "write_file",
"description": "Writes content to a specified file. Creates the file if it does not exist.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "The relative or absolute path of the object file."
},
"content": {
"type": "string",
"description": "The string content to write to the file."
}
},
"required": ["path", "content"]
}
}
}
]
# Implementasikan fungsi tool
def write_file(path: str, content: str) -> str:
"""Menulis konten ke file."""
try:
# Pastikan direktori ada
os.makedirs(os.path.dirname(path),
exist_ok=True) if os.path.dirname(path) else None
with open(path, 'w', encoding='utf-8') as f:
f.write(content)
return f"Success: The file '{path}' has been written."
except Exception as e:
return f"Error: An exception occurred while writing the file - {str(e)}"
messages = [{"role": "user", "content": "Write a Python quicksort algorithm and name the file quick_sort.py."}]
completion = client.chat.completions.create(
model="qwen3-coder-next",
messages=messages,
tools=tools
)
assistant_output = completion.choices[0].message
if assistant_output.content is None:
assistant_output.content = ""
messages.append(assistant_output)
# Jika tidak diperlukan pemanggilan tool, cetak langsung kontennya
if assistant_output.tool_calls is None:
print(f"Tidak diperlukan pemanggilan tool. Respons langsung: {assistant_output.content}")
else:
# Masuk ke loop pemanggilan tool
while assistant_output.tool_calls is not None:
for tool_call in assistant_output.tool_calls:
tool_call_id = tool_call.id
func_name = tool_call.function.name
arguments = json.loads(tool_call.function.arguments)
print(f"Memanggil tool [{func_name}] dengan argumen: {arguments}")
# Jalankan tool
tool_result = write_file(**arguments)
# Buat pesan balasan tool
tool_message = {
"role": "tool",
"tool_call_id": tool_call_id,
"content": tool_result,
}
print(f"Tool mengembalikan: {tool_message['content']}")
messages.append(tool_message)
# Panggil model lagi untuk mendapatkan respons bahasa alami yang dirangkum
response = client.chat.completions.create(
model="qwen3-coder-next",
messages=messages,
tools=tools
)
assistant_output = response.choices[0].message
if assistant_output.content is None:
assistant_output.content = ""
messages.append(assistant_output)
print(f"Respons akhir model: {assistant_output.content}")
Copy
Calling tool [write_file] with arguments: {'content': 'def quick_sort(arr):\\n if len(arr) <= 1:\\n return arr\\n pivot = arr[len(arr) // 2]\\n left = [x for x in arr if x < pivot]\\n middle = [x for x in arr if x == pivot]\\n right = [x for x in arr if x > pivot]\\n return quick_sort(left) + middle + quick_sort(right)\\n\\nif __name__ == \\"__main__\\":\\n example_list = [3, 6, 8, 10, 1, 2, 1]\\n print(\\"Original list:\\", example_list)\\n sorted_list = quick_sort(example_list)\\n print(\\"Sorted list:\\", sorted_list)', 'path': 'quick_sort.py'}
Tool returned: Success: The file 'quick_sort.py' has been written.
Final model response: I have created a file named `quick_sort.py` for you, which contains the Python implementation of the quicksort algorithm. You can run this file to see the example output. Let me know if you need any further modifications or explanations!
Copy
import OpenAI from "openai";
import fs from "fs/promises";
import path from "path";
const client = new OpenAI({
// Kunci API bervariasi berdasarkan Wilayah. Untuk mendapatkan Kunci API, kunjungi: https://www.alibabacloud.com/help/en/model-studio/get-api-key
// Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Model Studio Anda: apiKey: "sk-xxx",
apiKey: process.env.DASHSCOPE_API_KEY,
baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});
const tools = [
{
"type": "function",
"function": {
"name": "write_file",
"description": "Writes content to a specified file. Creates the file if it does not exist.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "The relative or absolute path of the object file."
},
"content": {
"type": "string",
"description": "The string content to write to the file."
}
},
"required": ["path", "content"]
}
}
}
];
// Implementasikan fungsi tool
async function write_file(filePath, content) {
try:
// Untuk alasan keamanan, fitur penulisan file dinonaktifkan secara default. Untuk menggunakannya, hapus komentar pada baris berikut dan pastikan jalurnya aman.
// const dir = path.dirname(filePath);
// if (dir) {
// await fs.mkdir(dir, { recursive: true });
// }
// await fs.writeFile(filePath, content, "utf-8");
return `Success: The file '${filePath}' has been written.`;
} catch (error) {
return `Error: An exception occurred while writing the file - ${error.message}`;
}
}
const messages = [{"role": "user", "content": "Write a Python quicksort algorithm and name the file quick_sort.py."}];
async function main() {
const completion = await client.chat.completions.create({
model: "qwen3-coder-next",
messages: messages,
tools: tools
});
let assistant_output = completion.choices[0].message;
// Pastikan konten tidak null
if (!assistant_output.content) assistant_output.content = "";
messages.push(assistant_output);
// Jika tidak diperlukan pemanggilan tool, cetak langsung kontennya
if (!assistant_output.tool_calls) {
console.log(`Tidak diperlukan pemanggilan tool. Respons langsung: ${assistant_output.content}`);
} else {
// Masuk ke loop pemanggilan tool
while (assistant_output.tool_calls) {
for (const tool_call of assistant_output.tool_calls) {
const tool_call_id = tool_call.id;
const func_name = tool_call.function.name;
const args = JSON.parse(tool_call.function.arguments);
console.log(`Memanggil tool [${func_name}] dengan argumen:`, args);
// Jalankan tool
const tool_result = await write_file(args.path, args.content);
// Buat pesan balasan tool
const tool_message = {
"role": "tool",
"tool_call_id": tool_call_id,
"content": tool_result
};
console.log(`Tool mengembalikan: ${tool_message.content}`);
messages.push(tool_message);
}
// Panggil model lagi untuk mendapatkan respons bahasa alami yang dirangkum
const response = await client.chat.completions.create({
model: "qwen3-coder-next",
messages: messages,
tools: tools
});
assistant_output = response.choices[0].message;
if (!assistant_output.content) assistant_output.content = "";
messages.push(assistant_output);
}
console.log(`Respons akhir model: ${assistant_output.content}`);
}
}
main();
Copy
Calling tool [write_file] with arguments: {
content: 'def quick_sort(arr):\\n if len(arr) <= 1:\\n return arr\\n pivot = arr[len(arr) // 2]\\n left = [x for x in arr if x < pivot]\\n middle = [x for x in arr if x == pivot]\\n right = [x for x in arr if x > pivot]\\n return quick_sort(left) + middle + quick_sort(right)\\n\\nif __name__ == \\"__main__\\":\\n example_list = [3, 6, 8, 10, 1, 2, 1]\\n print(\\"Original list:\\", example_list)\\n sorted_list = quick_sort(example_list)\\n print(\\"Sorted list:\\", sorted_list)',
path: 'quick_sort.py'
}
Tool returned: Success: The file 'quick_sort.py' has been written.
Final model response: The `quick_sort.py` file has been successfully created with the Python implementation of the quicksort algorithm. You can run this file to see the sorting result for the example list. Let me know if you need any further modifications or explanations!
Contoh ini menunjukkan langkah pertama proses pemanggilan tool: mengirim permintaan dan mengambil maksud model untuk memanggil tool.URL bervariasi berdasarkan wilayah.Response
Copy
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-coder-next",
"messages": [
{
"role": "user",
"content": "Write a Python quicksort algorithm and name the file quick_sort.py."
}
],
"tools": [
{
"type": "function",
"function": {
"name": "write_file",
"description": "Writes content to a specified file. Creates the file if it does not exist.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "The relative or absolute path of the object file."
},
"content": {
"type": "string",
"description": "The string content to write to the file."
}
},
"required": ["path", "content"]
}
}
}
]
}'
Copy
{
"choices": [
{
"message": {
"content": "",
"role": "assistant",
"tool_calls": [
{
"index": 0,
"id": "call_0ca7505bb6e44471a40511e5",
"type": "function",
"function": {
"name": "write_file",
"arguments": "{\"content\": \"def quick_sort(arr):\\\\n if len(arr) <= 1:\\\\n return arr\\\\n pivot = arr[len(arr) // 2]\\\\n left = [x for x in arr if x < pivot]\\\\n middle = [x for x in arr if x == pivot]\\\\n right = [x for x in arr if x > pivot]\\\\n return quick_sort(left) + middle + quick_sort(right)\\\\n\\\\nif __name__ == \\\\\\\"__main__\\\\\\\":\\\\n example_list = [3, 6, 8, 10, 1, 2, 1]\\\\n print(\\\\\\\"Original list:\\\\\\\", example_list)\\\\n sorted_list = quick_sort(example_list)\\\\n print(\\\\\\\"Sorted list:\\\\\\\", sorted_list)\", \"path\": \"quick_sort.py\"}"
}
}
]
},
"finish_reason": "tool_calls",
"index": 0,
"logprobs": null
}
],
"object": "chat.completion",
"usage": {
"prompt_tokens": 494,
"completion_tokens": 193,
"total_tokens": 687,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"created": 1761620025,
"system_fingerprint": null,
"model": "qwen3-coder-next",
"id": "chatcmpl-20e96159-beea-451f-b3a4-d13b218112b5"
}
- Python
- Java
- curl
Copy
import os
import json
import dashscope
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'
tools = [
{
"type": "function",
"function": {
"name": "write_file",
"description": "Writes content to a specified file. Creates the file if it does not exist.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "The relative or absolute path of the object file."
},
"content": {
"type": "string",
"description": "The string content to write to the file."
}
},
"required": ["path", "content"]
}
}
}
]
# Implementasikan fungsi tool
def write_file(path: str, content: str) -> str:
"""Menulis konten ke file."""
try:
# Untuk alasan keamanan, fitur penulisan file dinonaktifkan secara default. Untuk menggunakannya, hapus komentar pada baris berikut dan pastikan jalurnya aman.
# os.makedirs(os.path.dirname(path),exist_ok=True) if os.path.dirname(path) else None
# with open(path, 'w', encoding='utf-8') as f:
# f.write(content)
return f"Success: The file '{path}' has been written."
except Exception as e:
return f"Error: An exception occurred while writing the file - {str(e)}"
messages = [{"role": "user", "content": "Write a Python quicksort algorithm and name the file quick_sort.py."}]
response = dashscope.Generation.call(
# Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Model Studio Anda: api_key="sk-xxx",
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen3-coder-next',
messages=messages,
tools=tools,
result_format='message'
)
if response.status_code == 200:
assistant_output = response.output.choices[0].message
messages.append(assistant_output)
# Jika tidak diperlukan pemanggilan tool, cetak langsung kontennya
if "tool_calls" not in assistant_output or not assistant_output["tool_calls"]:
print(f"Tidak diperlukan pemanggilan tool. Respons langsung: {assistant_output['content']}")
else:
# Masuk ke loop pemanggilan tool
while "tool_calls" in assistant_output and assistant_output["tool_calls"]:
for tool_call in assistant_output["tool_calls"]:
func_name = tool_call["function"]["name"]
arguments = json.loads(tool_call["function"]["arguments"])
tool_call_id = tool_call.get("id")
print(f"Memanggil tool [{func_name}] dengan argumen: {arguments}")
# Jalankan tool
tool_result = write_file(**arguments)
# Buat pesan balasan tool
tool_message = {
"role": "tool",
"content": tool_result,
"tool_call_id": tool_call_id
}
print(f"Tool mengembalikan: {tool_message['content']}")
messages.append(tool_message)
# Panggil model lagi untuk mendapatkan respons bahasa alami yang dirangkum
response = dashscope.Generation.call(
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen3-coder-next',
messages=messages,
tools=tools,
result_format='message'
)
if response.status_code == 200:
print(f"Respons akhir model: {response.output.choices[0].message.content}")
assistant_output = response.output.choices[0].message
messages.append(assistant_output)
else:
print(f"Error selama pembuatan respons ringkasan: {response}")
break
else:
print(f"Error eksekusi: {response}")
Copy
Calling tool [write_file] with arguments: {'content': 'def quick_sort(arr):\\n if len(arr) <= 1:\\n return arr\\n pivot = arr[len(arr) // 2]\\n left = [x for x in arr if x < pivot]\\n middle = [x for x in arr if x == pivot]\\n right = [x for x in arr if x > pivot]\\n return quick_sort(left) + middle + quick_sort(right)\\n\\nif __name__ == \\"__main__\\":\\n example_list = [3, 6, 8, 10, 1, 2, 1]\\n print(\\"Original list:\\", example_list)\\n sorted_list = quick_sort(example_list)\\n print(\\"Sorted list:\\", sorted_list)', 'path': 'quick_sort.py'}
Tool returned: Success: The file 'quick_sort.py' has been written.
Final model response: The `quick_sort.py` file has been successfully created with the Python implementation of the quicksort algorithm. You can run this file to see the sorting result for the example list. Let me know if you need any further modifications or explanations!
Copy
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.protocol.Protocol;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.tools.FunctionDefinition;
import com.alibaba.dashscope.tools.ToolCallBase;
import com.alibaba.dashscope.tools.ToolCallFunction;
import com.alibaba.dashscope.tools.ToolFunction;
import com.alibaba.dashscope.utils.JsonUtils;
import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.ObjectMapper;
import java.io.File;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
public class Main {
/**
* Menulis konten ke file.
* @param arguments String JSON yang dikirim oleh model, berisi parameter yang dibutuhkan oleh tool.
* @return String dengan hasil eksekusi tool.
*/
public static String writeFile(String arguments) {
try {
ObjectMapper objectMapper = new ObjectMapper();
JsonNode argsNode = objectMapper.readTree(arguments);
String path = argsNode.get("path").asText();
String content = argsNode.get("content").asText();
// Untuk alasan keamanan, fitur penulisan file dinonaktifkan secara default. Untuk menggunakannya, hapus komentar pada baris berikut dan pastikan jalurnya aman.
// File file = new File(path);
// File parentDir = file.getParentFile();
// if (parentDir != null && !parentDir.exists()) {
// parentDir.mkdirs();
// }
// Files.write(Paths.get(path), content.getBytes(StandardCharsets.UTF_8));
return "Success: File '" + path + "' has been written";
} catch (Exception e) {
return "Error: An exception occurred while writing the file - " + e.getMessage();
}
}
public static void main(String[] args) {
try {
// Definisikan skema parameter tool.
String writePropertyParams =
"{\"type\":\"object\",\"properties\":{\"path\":{\"type\":\"string\",\"description\":\"The relative or absolute path of the target file\"},\"content\":{\"type\":\"string\",\"description\":\"The string content to write to the file\"}},\"required\":[\"path\",\"content\"]}";
FunctionDefinition writeFileFunction = FunctionDefinition.builder()
.name("write_file")
.description("Writes content to a specified file. Creates the file if it does not exist.")
.parameters(JsonUtils.parseString(writePropertyParams).getAsJsonObject())
.build();
Generation gen = new Generation(Protocol.HTTP.getValue(), "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1");
String userInput = "Write a Python script for quick sort and name it quick_sort.py";
List<Message> messages = new ArrayList<>();
messages.add(Message.builder().role(Role.USER.getValue()).content(userInput).build());
// Panggilan model pertama.
GenerationParam param = GenerationParam.builder()
.model("qwen3-coder-next")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.messages(messages)
.tools(Arrays.asList(ToolFunction.builder().function(writeFileFunction).build()))
.resultFormat(GenerationParam.ResultFormat.MESSAGE)
.build();
GenerationResult result = gen.call(param);
Message assistantOutput = result.getOutput().getChoices().get(0).getMessage();
messages.add(assistantOutput);
// Jika tidak diperlukan pemanggilan tool, cetak langsung kontennya
if (assistantOutput.getToolCalls() == null || assistantOutput.getToolCalls().isEmpty()) {
System.out.println("Tidak diperlukan pemanggilan tool. Respons langsung: " + assistantOutput.getContent());
} else {
// Masuk ke loop pemanggilan tool.
while (assistantOutput.getToolCalls() != null && !assistantOutput.getToolCalls().isEmpty()) {
for (ToolCallBase toolCall : assistantOutput.getToolCalls()) {
ToolCallFunction functionCall = (ToolCallFunction) toolCall;
String funcName = functionCall.getFunction().getName();
String arguments = functionCall.getFunction().getArguments();
System.out.println("Memanggil tool [" + funcName + "], argumen: " + arguments);
// Jalankan tool.
String toolResult = writeFile(arguments);
// Buat pesan balasan tool.
Message toolMessage = Message.builder()
.role("tool")
.toolCallId(toolCall.getId())
.content(toolResult)
.build();
System.out.println("Tool mengembalikan: " + toolMessage.getContent());
messages.add(toolMessage);
}
// Panggil model lagi untuk mendapatkan respons bahasa alami yang dirangkum.
param.setMessages(messages);
result = gen.call(param);
assistantOutput = result.getOutput().getChoices().get(0).getMessage();
messages.add(assistantOutput);
}
System.out.println("Respons akhir model: " + assistantOutput.getContent());
}
} catch (NoApiKeyException | InputRequiredException e) {
System.err.println("Error: " + e.getMessage());
} catch (Exception e) {
e.printStackTrace();
}
}
}
Copy
Calling tool [write_file] with arguments: {"content": "def quick_sort(arr):\\n if len(arr) <= 1:\\n return arr\\n pivot = arr[len(arr) // 2]\\n left = [x for x in arr if x < pivot]\\n middle = [x for x in arr if x == pivot]\\n right = [x for x in arr if x > pivot]\\n return quick_sort(left) + middle + quick_sort(right)\\n\\nif __name__ == \\\"__main__\\\":\\n example_array = [3, 6, 8, 10, 1, 2, 1]\\n print(\\\"Original array:\\\", example_array)\\n sorted_array = quick_sort(example_array)\\n print(\\\"Sorted array:\\\", sorted_array)", "path": "quick_sort.py"}
Tool returned: Success: The file 'quick_sort.py' has been written.
Final model response: I have successfully created the Python code file `quick_sort.py` for you. This file contains a `quick_sort` function and an example of its usage. You can run it in your terminal or editor to test the quicksort functionality.
Contoh ini menunjukkan langkah pertama proses pemanggilan tool: mengirim permintaan dan mengambil maksud model untuk memanggil tool.URL bervariasi berdasarkan wilayah.Response
Copy
curl --location "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "qwen3-coder-next",
"input": {
"messages": [{
"role": "user",
"content": "Write a Python quicksort algorithm and name the file quick_sort.py."
}]
},
"parameters": {
"result_format": "message",
"tools": [
{
"type": "function",
"function": {
"name": "write_file",
"description": "Writes content to a specified file. Creates the file if it does not exist.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "The relative or absolute path of the object file."
},
"content": {
"type": "string",
"description": "The string content to write to the file."
}
},
"required": ["path", "content"]
}
}
}
]
}
}'
Copy
{
"output": {
"choices": [
{
"finish_reason": "tool_calls",
"message": {
"role": "assistant",
"tool_calls": [
{
"function": {
"name": "write_file",
"arguments": "{\"content\": \"def quick_sort(arr):\\\\n if len(arr) <= 1:\\\\n return arr\\\\n pivot = arr[len(arr) // 2]\\\\n left = [x for x in arr if x < pivot]\\\\n middle = [x for x in arr if x == pivot]\\\\n right = [x for x in arr if x > pivot]\\\\n return quick_sort(left) + middle + quick_sort(right)\\\\n\\\\nif __name__ == \\\\\\\"__main__\\\\\\\":\\\\n example_list = [3, 6, 8, 10, 1, 2, 1]\\\\n print(\\\\\\\"Original list:\\\\\\\", example_list)\\\\n sorted_list = quick_sort(example_list)\\\\n print(\\\\\\\"Sorted list:\\\\\\\", sorted_list), \"path\": \"quick_sort.py\"}"
},
"index": 0,
"id": "call_645b149bbd274e8bb3789aae",
"type": "function"
}
],
"content": ""
}
}
]
},
"usage": {
"total_tokens": 684,
"output_tokens": 193,
"input_tokens": 491,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"request_id": "d2386acd-fce3-9d0f-8015-c5f3a8bf9f5c"
}
Penyelesaian kode
Qwen-Coder mendukung dua metode penyelesaian kode. Pilih salah satu sesuai kebutuhan Anda:- Mode parsial: Metode ini cocok untuk semua model Qwen-Coder dan wilayah. Metode ini mendukung penyelesaian awalan (prefix completion) dan mudah diimplementasikan. Kami merekomendasikan metode ini.
- Completions API: Metode ini hanya didukung untuk model seri
qwen2.5-coderdi wilayah China (Beijing). Metode ini mendukung penyelesaian awalan dan penyelesaian isi tengah (fill-in-the-middle).
Mode Parsial
Fitur ini memungkinkan model secara otomatis melengkapi sisa kode Anda berdasarkan awalan yang diberikan. Untuk menggunakan fitur ini, tambahkan pesan denganrole diatur ke assistant dan partial: true ke daftar messages. content dari pesan assistant adalah awalan kode yang Anda berikan. Untuk informasi lebih lanjut, lihat Mode parsial.
- OpenAI compatible
- DashScope
- Python
- Node.js
- curl
PermintaanResponse
Copy
import os
from openai import OpenAI
client = OpenAI(
# Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Alibaba Cloud Model Studio Anda: api_key="sk-xxx",
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
model="qwen3-coder-next",
messages=[{
"role": "user",
"content": "Help me write a Python script to generate prime numbers up to 100. Do not output non-code content or Markdown code blocks."
},
{
"role": "assistant",
"content": "def generate_prime_number",
"partial": True
}]
)
print(completion.choices[0].message.content)
Copy
(n):
primes = []
for i in range(2, n+1):
is_prime = True
for j in range(2, int(i**0.5)+1):
if i % j == 0:
is_prime = False
break
if is_prime:
primes.append(i)
return primes
prime_numbers = generate_prime_number(100)
print(prime_numbers)
Contoh permintaanResponse
Copy
import OpenAI from "openai";
const client = new OpenAI(
{
// Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Model Studio Anda: apiKey: "sk-xxx",
apiKey: process.env.DASHSCOPE_API_KEY,
baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
}
);
async function main() {
const completion = await client.chat.completions.create({
model: "qwen3-coder-next",
messages: [
{ role: "user", content: "Help me write a Python script to generate prime numbers up to 100. Do not output non-code content or Markdown code blocks." },
{ role: "assistant", content: "def generate_prime_number", partial: true}
],
});
console.log(completion.choices[0].message.content);
}
main();
Copy
(n):
primes = []
for i in range(2, n+1):
is_prime = True
for j in range(2, int(i**0.5)+1):
if i % j == 0:
is_prime = False
break
if is_prime:
primes.append(i)
return primes
prime_numbers = generate_prime_number(100)
print(prime_numbers)
Contoh permintaanURL bervariasi berdasarkan wilayah.Response
Copy
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-coder-next",
"messages": [{
"role": "user",
"content": "Help me write a Python script to generate prime numbers up to 100. Do not output non-code content or Markdown code blocks."
},
{
"role": "assistant",
"content": "def generate_prime_number",
"partial": true
}]
}'
Copy
{
"choices": [
{
"message": {
"content": "(n):\n primes = []\n for num in range(2, n + 1):\n is_prime = True\n for i in range(2, int(num ** 0.5) + 1):\n if num % i == 0:\n is_prime = False\n break\n if is_prime:\n primes.append(num)\n return primes\n\nprime_numbers = generate_prime_number(100)\nprint(prime_numbers)",
"role": "assistant"
},
"finish_reason": "stop",
"index": 0,
"logprobs": null
}
],
"object": "chat.completion",
"usage": {
"prompt_tokens": 38,
"completion_tokens": 93,
"total_tokens": 131,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"created": 1761634556,
"system_fingerprint": null,
"model": "qwen3-coder-next",
"id": "chatcmpl-c108050a-bb6d-4423-9d36-f64aa6a32976"
}
- Python
- curl
Contoh permintaanResponse
Copy
from http import HTTPStatus
import dashscope
import os
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'
messages = [{
"role": "user",
"content": "Help me write a Python script to generate prime numbers up to 100. Do not output non-code content or Markdown code blocks."
},
{
"role": "assistant",
"content": "def generate_prime_number",
"partial": True
}]
response = dashscope.Generation.call(
# Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Model Studio Anda: api_key="sk-xxx",
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen3-coder-next',
messages=messages,
result_format='message',
)
if response.status_code == HTTPStatus.OK:
print(response.output.choices[0].message.content)
else:
print(f"Kode respons HTTP: {response.status_code}")
print(f"Kode error: {response.code}")
print(f"Pesan error: {response.message}")
Copy
(n):
primes = []
for i in range(2, n+1):
is_prime = True
for j in range(2, int(i**0.5)+1):
if i % j == 0:
is_prime = False
break
if is_prime:
primes.append(i)
return primes
prime_numbers = generate_prime_number(100)
print(prime_numbers)
Contoh PermintaanURL bervariasi berdasarkan wilayah.Response
Copy
curl -X POST "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-coder-next",
"input":{
"messages":[{
"role": "user",
"content": "Help me write a Python script to generate prime numbers up to 100. Do not output non-code content or Markdown code blocks."
},
{
"role": "assistant",
"content": "def generate_prime_number",
"partial": true
}]
},
"parameters": {
"result_format": "message"
}
}'
Copy
{
"output": {
"choices": [
{
"message": {
"content": "(n):\n prime_list = []\n for i in range(2, n+1):\n is_prime = True\n for j in range(2, int(i**0.5)+1):\n if i % j == 0:\n is_prime = False\n break\n if is_prime:\n prime_list.append(i)\n return prime_list\n\nprime_numbers = generate_prime_number(100)\nprint(prime_numbers)",
"role": "assistant"
},
"finish_reason": "stop"
}
]
},
"usage": {
"total_tokens": 131,
"output_tokens": 92,
"input_tokens": 39,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"request_id": "9917f629-e819-4519-af44-b0e677e94b2c"
}
Completions API
Completions API hanya tersedia untuk model di wilayah China (Beijing) dan memerlukan Kunci API dari wilayah China (Beijing).
fim (Fill-in-the-Middle) dalam prompt untuk memandu penyelesaian model.
- Penyelesaian berbasis awalan
- Penyelesaian berbasis awalan dan akhiran
Templat prompt:
Copy
<|fim_prefix|>{prefix_content}<|fim_suffix|>
<|fim_prefix|>dan<|fim_suffix|>adalah token khusus yang memandu model untuk melengkapi teks. Jangan ubah token ini.- Ganti
{prefix_content}dengan informasi awalan Anda, seperti nama fungsi, parameter input, dan instruksi penggunaan.
Copy
import os
from openai import OpenAI
client = OpenAI(
base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
api_key=os.getenv("DASHSCOPE_API_KEY")
)
completion = client.completions.create(
model="qwen-coder-turbo",
prompt="<|fim_prefix|>def quick_sort(arr):<|fim_suffix|>",
)
print(completion.choices[0].text)
Templat prompt:
Copy
<|fim_prefix|>{prefix_content}<|fim_suffix|>{suffix_content}<|fim_middle|>
<|fim_prefix|>,<|fim_suffix|>, dan<|fim_middle|>adalah token khusus yang memandu model untuk melengkapi teks. Jangan ubah token ini.- Ganti
{prefix_content}dengan informasi awalan Anda, seperti nama fungsi, parameter input, dan instruksi penggunaan. - Ganti
{suffix_content}dengan informasi akhiran Anda, seperti parameter return fungsi.
Copy
import os
from openai import OpenAI
client = OpenAI(
base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
api_key=os.getenv("DASHSCOPE_API_KEY")
)
prefix_content = """def reverse_words_with_special_chars(s):
'''
Reverse each word in a string while preserving the position of non-alphabetic characters and word order.
Example:
reverse_words_with_special_chars("Hello, world!") -> "olleH, dlrow!"
Parameters:
s (str): The input string, which may contain punctuation.
Returns:
str: The processed string with words reversed but non-alphabetic characters in their original positions.
'''
"""
suffix_content = "return result"
completion = client.completions.create(
model="qwen-coder-turbo",
prompt=f"<|fim_prefix|>{prefix_content}<|fim_suffix|>{suffix_content}<|fim_middle|>",
)
print(completion.choices[0].text)
Produksi
Untuk mengoptimalkan efisiensi dan mengurangi biaya penggunaan model Qwen-Coder, pertimbangkan saran berikut:- Aktifkankeluaran streaming: Atur
stream=Trueuntuk menerima hasil antara secara real time. Hal ini mengurangi risiko timeout dan meningkatkan pengalaman pengguna. - Turunkan suhu: Tugas pembuatan kode biasanya memerlukan hasil yang deterministik dan akurat. Menurunkan parameter
suhumengurangi keacakan output yang dihasilkan. - Gunakan model yang mendukung cache konteks: Dalam skenario dengan banyak awalan berulang, seperti penyelesaian kode dan tinjauan kode, menggunakan model yang mendukung cache konteks dapat secara efektif mengurangi overhead.
- Kontrol jumlah tool: Untuk memastikan pemanggilan model yang efisien dan hemat biaya, jangan melewatkan lebih dari 20 tool dalam parameter
toolsper panggilan. Melewatkan banyak deskripsi tool mengonsumsi token input berlebihan, yang meningkatkan biaya, mengurangi kecepatan respons, dan membuat model lebih sulit memilih tool yang tepat. Untuk informasi lebih lanjut, lihat Function Calling.
Penagihan dan Pembatasan laju
-
Penagihan dasar: Anda ditagih berdasarkan jumlah token input
tokendan token outputtokenuntuk setiap permintaan. Harga satuan bervariasi tergantung model. Untuk harga spesifik, lihat Daftar model. -
Item penagihan khusus:
- Penagihan bertingkat: Model seri
qwen3-codermenggunakan metode penagihan bertingkat. Ketika jumlah token input dalam permintaan tunggal mencapai tingkat tertentu, semua token input dan output untuk permintaan tersebut ditagih sesuai tarif tingkat tersebut. - Cache konteks: Untuk model yang mendukung cache konteks, mekanisme caching dapat secara signifikan mengurangi biaya untuk permintaan dengan banyak input berulang, seperti dalam tinjauan kode. Teks input yang mengenai cache implisit ditagih sebesar 20% dari tarif standar. Teks input yang mengenai cache eksplisit ditagih sebesar 10% dari tarif standar. Untuk informasi lebih lanjut, lihat Cache konteks.
- Pemanggilan tool (Function Calling): Saat Anda menggunakan fitur pemanggilan tool, deskripsi tool yang Anda definisikan dalam parameter
toolstermasuk dalam jumlah totaltokendan dikenakan biaya.
- Penagihan bertingkat: Model seri
- Pembatasan laju: Panggilan API dikenakan batas ganda berdasarkan permintaan per menit (RPM) dan token per menit (TPM). Untuk informasi lebih lanjut, lihat Pembatasan laju.
- Kuota gratis(hanya wilayah Singapura): Setelah Anda mengaktifkan Model Studio atau permintaan model Anda disetujui, setiap model Qwen-Coder mencakup kuota gratis 1 juta token untuk pengguna baru yang berlaku selama 90 hari.
Referensi API
Untuk informasi lebih lanjut tentang parameter input dan output model Qwen-Coder, lihat Pembuatan teks.FAQ
Mengapa tool pengembangan seperti Qwen Code dan Claude Code mengonsumsi banyak token?
Saat Anda menggunakan tool pengembangan eksternal untuk memanggil model Qwen-Coder, tool tersebut mungkin melakukan beberapa panggilan API, yang mengonsumsi banyak token. Untuk metode spesifik memantau dan mengurangi konsumsi token, lihat dokumen Qwen Code dan Claude Code. Anda dapat mengaktifkan fitur stop-when-quota-exhausted untuk menghindari biaya tambahan setelah kuota gratis Anda habis. Anda juga dapat membeli paket coding AI. Paket ini menawarkan biaya tetap bulanan untuk kuota permintaan bulanan yang dapat digunakan dalam tool AI. Untuk informasi lebih lanjut, lihat dokumen Ikhtisar Paket Coding.Bagaimana cara melihat penggunaan model?
Satu jam setelah Anda memanggil model, buka halaman Pemantauan (Singapura atau Beijing). Atur kondisi kueri, seperti rentang waktu dan ruang kerja. Kemudian, di area Model, temukan model target dan klik Pantau di kolom Tindakan untuk melihat statistik pemanggilan model. Untuk informasi lebih lanjut, lihat dokumen Pemantauan.Data diperbarui setiap jam. Selama periode puncak, mungkin terjadi latensi hingga satu jam.
Bagaimana cara membuat model hanya mengeluarkan kode tanpa teks penjelasan apa pun?
Anda dapat menggunakan metode berikut:- Batasan prompt: Berikan instruksi yang jelas dalam prompt, misalnya: "Kembalikan hanya kode. Jangan sertakan penjelasan, komentar, atau tag Markdown apa pun."
- Atur urutan
stop: Gunakan frasa sepertistop=["\n# Explanation:", "Note:"]untuk menghentikan generasi sebelum model mulai menghasilkan teks penjelasan. Untuk informasi lebih lanjut, lihat Referensi API Qwen.