Alibaba Cloud Model Studio:structured output

from openai import OpenAI
import os

client = OpenAI(
    # The API keys for the Singapore and Beijing regions are different. If you have not set the environment variable, replace the following line with your API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The base_url for the Singapore region. For the Beijing region, use https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen-flash",
    messages=[
        {
            "role": "system",
            "content": "Extract the name and age and return the information in JSON format."
        },
        {
            "role": "user",
            "content": "Hello everyone, my name is Alex Brown. I am 34 years old. My email is alexbrown@example.com. I enjoy playing basketball and traveling.", 
        },
    ],
    response_format={"type": "json_object"}
)

json_string = completion.choices[0].message.content
print(json_string)

Return result

{
  "name": "Alex Brown",
  "age": 34
}

import OpenAI from "openai";

const openai = new OpenAI({
    // If you have not configured the environment variable, replace the following line with your API key: apiKey: "sk-xxx"
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following baseURL is for the Singapore region. To use a model in the Beijing region, replace the baseURL with: https://dashscope.aliyuncs.com/compatible-mode/v1
    baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
});

const completion = await openai.chat.completions.create({
    model: "qwen-flash",
    messages: [
        {
            role: "system",
            content: "Extract the name and age information and return it in JSON format."
        },
        {
            role: "user",
            content: "Hello everyone, my name is Alex Brown, I am 34 years old, and my email is alexbrown@example.com. I enjoy playing basketball and traveling."
        }
    ],
    response_format: {
        type: "json_object"
    }
});

const jsonString = completion.choices[0].message.content;
console.log(jsonString);

Return result

{
  "Name": "Alex Brown",
  "Age": 34
}

# ======= Important =======
# The API keys for the Singapore and China (Beijing) regions are different. For more information about how to get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===
curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen-plus",
    "messages": [
        {
            "role": "system",
            "content": "You need to extract the name (string), age (string), and email (string). Output a JSON string. Do not output any other content.\nExamples:\nQ: My name is John Doe, I am 25 years old, and my email is johndoe@example.com\nA:{\"name\":\"John Doe\",\"age\":\"25 years old\",\"email\":\"johndoe@example.com\"}\nQ: My name is Jane Smith, I am 30 years old, and my email is janesmith@example.com\nA:{\"name\":\"Jane Smith\",\"age\":\"30 years old\",\"email\":\"janesmith@example.com\"}\nQ: My name is Peter Jones, my email is peterjones@example.com, and I am 40 years old\nA:{\"name\":\"Peter Jones\",\"age\":\"40 years old\",\"email\":\"peterjones@example.com\"}"
        },
        {
            "role": "user", 
            "content": "Hello everyone, my name is Alex Brown, and I am 34 years old. My email is alexbrown@example.com"
        }
    ],
    "response_format": {
        "type": "json_object"
    }
}'

Return result

{
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "{\"name\":\"Alex Brown\",\"age\":\"34 years old\""}"
            },
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null
        }
    ],
    "object": "chat.completion",
    "usage": {
        "prompt_tokens": 207,
        "completion_tokens": 20,
        "total_tokens": 227,
        "prompt_tokens_details": {
            "cached_tokens": 0
        }
    },
    "created": 1756455080,
    "system_fingerprint": null,
    "model": "qwen-plus",
    "id": "chatcmpl-624b665b-fb93-99e7-9ebd-bb6d86d314d2"
}

import os
import dashscope
# The following URL is for the Singapore region. To use a model in the Beijing region, replace the URL with https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages=[
    {
        "role": "system",
        "content": "Extract the name and age and return the information in JSON format."
    },
    {
        "role": "user",
        "content": "Hello everyone, my name is Alex Brown. I am 34 years old. My email is alexbrown@example.com. I enjoy playing basketball and traveling.", 
    },
]
response = dashscope.Generation.call(
    # To use a model in the China (Beijing) region, you must use an API key specific to that region. You can obtain an API key from: https://bailian.console.alibabacloud.com/?tab=model#/api-key
    # If you have not configured the environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model="qwen-flash", 
    messages=messages,
    result_format='message',
    response_format={'type': 'json_object'}
    )
json_string = response.output.choices[0].message.content
print(json_string)

Return result

{
  "name": "Alex Brown",
  "age": 34
}

Return result

{
  "name": "Alex Brown",
  "age": 34
}

# ======= Important =======
# The API keys for the Singapore and China (Beijing) regions are different. For more information about how to get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/text-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen-flash",
    "input": {
        "messages": [
            {
                "role": "system",
                "content": "Extract the name and age, and return the information in JSON format."
            },
            {
                "role": "user", 
                "content": "Hello everyone, my name is Alex Brown, I am 34 years old, my email is alexbrown@example.com, and I like to play basketball and travel."
            }
        ]
    },
    "parameters": {
        "result_format": "message",
        "response_format": {
            "type": "json_object"
        }
    }
}'

Return result

{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "role": "assistant",
                    "content": "{\n  \"Name\": \"Alex Brown\",\n  \"Age\": 34\n}"
                }
            }
        ]
    },
    "usage": {
        "total_tokens": 72,
        "output_tokens": 18,
        "input_tokens": 54,
        "cached_tokens": 0
    },
    "request_id": "xxx-xxx-xxx-xxx-xxx"
}

import OpenAI from "openai";

const openai = new OpenAI({
  // The API keys for the Singapore and China (Beijing) regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
  // If you have not configured an environment variable, replace the following line with your Model Studio API key: apiKey: "sk-xxx"
  apiKey: process.env.DASHSCOPE_API_KEY,
  // The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with https://dashscope.aliyuncs.com/compatible-mode/v1
  baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
});

async function main() {
  const response = await openai.chat.completions.create({
    model: "qwen3-vl-plus",
    messages: [{
        role: "system",
        content: [{
          type: "text",
          text: "You are a helpful assistant."
        }]
      },
      {
        role: "user",
        content: [{
            type: "image_url",
            image_url: {
              "url": "http://duguang-labelling.oss-cn-shanghai.aliyuncs.com/demo_ocr/receipt_zh_demo.jpg"
            }
          },
          {
            type: "text",
            text: "Extract the ticket information (including travel_date, trains, seat_num, arrival_site, and price) and the invoice information (as an array, including invoice_code and invoice_number) from the image. Output a JSON object that contains the ticket and invoice arrays."
          }
        ]
      }
    ],
    response_format: {type: "json_object"}
  });
  console.log(response.choices[0].message.content);
}

main()

Return result

{
  "ticket": [
    {
      "travel_date": "2013-06-29",
      "trains": "Serial Number",
      "seat_num": "371",
      "arrival_site": "Development Zone",
      "price": "8.00"
    }
  ],
  "invoice": [
    {
      "invoice_code": "221021325353",
      "invoice_number": "10283819"
    }
  ]
}

from openai import OpenAI
import os
import json
import textwrap  # Used to handle the indentation of multi-line strings and improve code readability.

# Predefine example responses to show the model the expected output format.
# Example 1: A complete response that includes a hobby.
example1_response = json.dumps(
    {
        "info": {"name": "John Doe", "age": "25 years old", "email": "johndoe@example.com"},
        "hobby": ["singing"]
    },
    ensure_ascii=False
)
# Example 2: A response that includes multiple hobbies.
example2_response = json.dumps(
    {
        "info": {"name": "Jane Smith", "age": "30 years old", "email": "janesmith@example.com"},
        "hobby": ["dancing", "swimming"]
    },
    ensure_ascii=False
)
# Example 3: A response that does not include the hobby field (hobby is optional).
example3_response = json.dumps(
    {
        "info": {"name": "Peter Jones", "age": "28 years old", "email": "peterjones@example.com"}
    },
    ensure_ascii=False
)
# Example 4: A response that does not include the hobby field.
example4_response = json.dumps(
    {
        "info": {"name": "Emily White", "age": "35 years old", "email": "emilywhite@example.com"}
    },
    ensure_ascii=False
)

# Initialize the OpenAI client and configure the API key and base URL.
client = OpenAI(
    # The API keys for the Singapore and Beijing regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

# The dedent function removes common leading whitespace from every line in a string. 
# This lets you indent strings neatly in your code, and the extra spaces will not be included at runtime.
system_prompt = textwrap.dedent(f"""\
    Extract personal information from the user input and output it in the specified JSON Schema format:

    [Output Format Requirements]
    The output must strictly follow the JSON structure below:
    {{
      "info": {{
        "name": "String. Required. The name.",
        "age": "String. Required. The format is 'number years old', for example, '25 years old'.",
        "email": "String. Required. A standard email format, for example, 'user@example.com'."
      }},
      "hobby": ["Array of strings. Optional. Contains all of the hobbies. If no hobbies are mentioned, this field must be omitted from the output."]
    }}

    [Field Extraction Rules]
    1. name: Identify the name from the text. This field is required.
    2. age: Identify the age information and convert it to the 'number years old' format. This field is required.
    3. email: Identify the email address and keep its original format. This field is required.
    4. hobby: Identify the hobbies and output them as an array of strings. If no hobbies are mentioned, omit the hobby field entirely.

    [Reference Examples]
    Example 1 (includes a hobby):
    Q: My name is John Doe, I'm 25 years old, my email is johndoe@example.com, and I like to sing.
    A: {example1_response}

    Example 2 (includes multiple hobbies):
    Q: My name is Jane Smith, I'm 30 years old, my email is janesmith@example.com, and I enjoy dancing and swimming.
    A: {example2_response}

    Example 3 (does not include hobbies):
    Q: My name is Peter Jones, I'm 28 years old, and my email is peterjones@example.com.
    A: {example3_response}

    Example 4 (does not include hobbies):
    Q: I'm Emily White, 35 years old. My email is emilywhite@example.com.
    A: {example4_response}

    Strictly follow the format and rules above to extract information and output the JSON. If the user does not mention any hobbies, do not include the hobby field in the output.\
""")

# Call the LLM API to extract information.
completion = client.chat.completions.create(
    model="qwen-plus",  # Specify the model to use, which is qwen-plus.
    messages=[
        {
            "role": "system",
            "content": system_prompt  # Use the system prompt defined above.
        },
        {
            "role": "user",
            "content": "Hi everyone, my name is Alex Brown. I'm 34 years old, my email is alexbrown@example.com, and I like to play basketball and travel.", 
        },
    ],
    response_format={"type": "json_object"},  # Specify the response format as JSON to ensure structured output.
)

# Extract and print the JSON result generated by the model.
json_string = completion.choices[0].message.content
print(json_string)

Return result

{
  "info": {
    "name": "Alex Brown",
    "age": "34",
    "email": "alexbrown@example.com"
  },
  "hobby": ["basketball", "travel"]  
}

import OpenAI from "openai";

// Predefine example responses to show the model the expected output format.
// Example 1: A complete response that contains all fields.
const example1Response = JSON.stringify({
    info: { name: "John Doe", age: "25 years old", email: "johndoe@example.com" },
    hobby: ["singing"]
}, null, 2);

// Example 2: A response that contains multiple hobbies.
const example2Response = JSON.stringify({
    info: { name: "Jane Smith", age: "30 years old", email: "janesmith@example.com" },
    hobby: ["dancing", "swimming"]
}, null, 2);

// Example 3: A response without the hobby field. The hobby field is optional.
const example3Response = JSON.stringify({
    info: { name: "Peter Jones", age: "28 years old", email: "peterjones@example.com" }
}, null, 2);

// Example 4: Another response without the hobby field.
const example4Response = JSON.stringify({
    info: { name: "Emily White", age: "35 years old", email: "emilywhite@example.com" }
}, null, 2);

// Initialize the OpenAI client configuration.
const openai = new OpenAI({
    // The API keys for the Singapore and Beijing regions are different.
    // If the environment variable is not configured, replace the following line with your Alibaba Cloud Model Studio API key: apiKey: "sk-xxx",
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
    baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
});

// Create a chat completion request. Use a structured prompt to improve output accuracy.
const completion = await openai.chat.completions.create({
    model: "qwen-plus",
    messages: [
        {
            role: "system",
            content: `Please extract personal information from the user input and output it in the specified JSON Schema format.

[Output Format Requirements]
The output must strictly follow the JSON structure below:
{
  "info": {
    "name": "String type, required field, name",
    "age": "String type, required field, format: '[number] years old', for example, '25 years old'",
    "email": "String type, required field, standard email format, for example, 'user@example.com'"
  },
  "hobby": ["String array type, optional. Contains all user hobbies. Omit this field if no hobbies are mentioned."]
}

[Field Extraction Rules]
1. name: Identify the name from the text and extract it. This field is required.
2. age: Identify the age information, convert it to the '[number] years old' format, and extract it. This field is required.
3. email: Identify the email address, keep its original format, and extract it. This field is required.
4. hobby: Identify the hobbies and output them as a string array. If no hobby information is mentioned, omit the hobby field entirely from the output.

[Reference Examples]
Example 1 (with a hobby):
Q: My name is John Doe, I am 25 years old, my email is johndoe@example.com, and my hobby is singing.
A: ${example1Response}

Example 2 (with multiple hobbies):
Q: My name is Jane Smith, I am 30 years old, my email is janesmith@example.com, and I usually like dancing and swimming.
A: ${example2Response}

Example 3 (without a hobby):
Q: My name is Peter Jones, I am 28 years old, and my email is peterjones@example.com.
A: ${example3Response}

Example 4 (without a hobby):
Q: I am Emily White, 35 years old, and my email is emilywhite@example.com.
A: ${example4Response}

Please strictly follow the preceding format and rules to extract information and output the JSON. If the user does not mention any hobbies, do not include the hobby field in the output.`
        },
        {
            role: "user",
            content: "Hello everyone, my name is Alex Brown, I am 34 years old, my email is alexbrown@example.com, and I usually like to play basketball and travel."
        }
    ],
    response_format: {
        type: "json_object"
    }
});

// Extract and print the JSON result generated by the model.
const jsonString = completion.choices[0].message.content;
console.log(jsonString);

Return result

{
  "info": {
    "name": "Alex Brown",
    "age": "34 years old",
    "email": "alexbrown@example.com"
  },
  "hobby": [
    "Playing basketball",
    "Traveling"
  ]
}

import os
import json
import dashscope
# The following is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# Predefine example responses to show the model the expected output format.
example1_response = json.dumps(
    {
        "info": {"name": "John Doe", "age": "25 years old", "email": "johndoe@example.com"},
        "hobby": ["singing"]
    },
    ensure_ascii=False
)
example2_response = json.dumps(
    {
        "info": {"name": "Jane Smith", "age": "30 years old", "email": "janesmith@example.com"},
        "hobby": ["dancing", "swimming"]
    },
    ensure_ascii=False
)
example3_response = json.dumps(
    {
        "info": {"name": "Peter Jones", "age": "40 years old", "email": "peterjones@example.com"},
        "hobby": ["Rap", "basketball"]
    },
    ensure_ascii=False
)

messages=[
        {
            "role": "system",
            "content": f"""Please extract personal information from the user input and output it in the specified JSON Schema format:

[Output Format Requirements]
The output must strictly follow the JSON structure below:
{{
  "info": {{
    "name": "string, required, the name",
    "age": "string, required, in the format of 'number years old', for example, '25 years old'",
    "email": "string, required, in the standard email format, for example, 'user@example.com'"
  }},
  "hobby": ["string array, optional, contains all of the hobbies. If no hobbies are mentioned, omit this field entirely."]
}}

[Field Extraction Rules]
1. name: Identify the name from the text. This field is required.
2. age: Identify the age information and convert it to the "number years old" format. This field is required.
3. email: Identify the email address and keep its original format. This field is required.
4. hobby: Identify the hobbies and output them as a string array. If no hobby information is mentioned, omit the hobby field entirely.

[Reference Examples]
Example 1 (includes a hobby):
Q: My name is John Doe, I am 25 years old, my email is johndoe@example.com, and my hobby is singing.
A: {example1_response}

Example 2 (includes multiple hobbies):
Q: My name is Jane Smith, I am 30 years old, my email is janesmith@example.com, and I like dancing and swimming.
A: {example2_response}

Example 3 (includes multiple hobbies):
Q: My email is peterjones@example.com, I am 40 years old, my name is Peter Jones, and I can rap and play basketball.
A: {example3_response}

Please strictly follow the preceding format and rules to extract information and output the JSON. If the user does not mention any hobbies, do not include the hobby field in the output."""
        },
        {
            "role": "user",
            "content": "Hello everyone, my name is Alex Brown, I am 34 years old, my email is alexbrown@example.com, and I like to play basketball and travel.", 
        },
    ]
response = dashscope.Generation.call(
    # If you use a model in the China (Beijing) region, you must use an API key for the China (Beijing) region. Get it at: https://bailian.console.alibabacloud.com/?tab=model#/api-key
    # If the environment variable is not configured, replace the following line with your Alibaba Cloud Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model="qwen-plus", 
    messages=messages,
    result_format='message',
    response_format={'type': 'json_object'}
    )
json_string = response.output.choices[0].message.content
print(json_string)

Return result

{
  "info": {
    "name": "Alex Brown",
    "age": "34 years old",
    "email": "alexbrown@example.com"
  },
  "hobby": [
    "Playing basketball",
    "Traveling"
  ]
}

Return result

{
  "info": {
    "name": "Alex Brown",
    "age": "34",
    "email": "alexbrown@example.com"
  },
  "hobby": [
    "Playing basketball",
    "Traveling"
  ]
}