Structured Outputs For Reasoning Models#

When working with reasoning models that use special tokens like <think>...</think> to denote reasoning sections, you might want to allow free-form text within these sections while still enforcing grammar constraints on the rest of the output.

SGLang provides a feature to disable grammar restrictions within reasoning sections. This is particularly useful for models that need to perform complex reasoning steps before providing a structured output.

To enable this feature, use the --reasoning-parser flag which decide the think_end_token, such as </think>, when launching the server. You can also specify the reasoning parser using the --reasoning-parser flag.

Supported Models#

Currently, SGLang supports the following reasoning models:

DeepSeek R1 series: The reasoning content is wrapped with <think> and </think> tags.
QwQ: The reasoning content is wrapped with <think> and </think> tags.

Usage#

OpenAI Compatible API#

Specify the --grammar-backend, --reasoning-parser option.

[ ]:

import openai
import os

from sglang.test.doc_patch import launch_server_cmd
from sglang.utils import wait_for_server, print_highlight, terminate_process

os.environ["TOKENIZERS_PARALLELISM"] = "false"


server_process, port = launch_server_cmd(
    "python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-7B --host 0.0.0.0 --reasoning-parser deepseek-r1 --log-level warning"
)

wait_for_server(f"http://localhost:{port}")
client = openai.Client(base_url=f"http://127.0.0.1:{port}/v1", api_key="None")

JSON#

you can directly define a JSON schema or use Pydantic to define and validate the response.

Using Pydantic

[ ]:

from pydantic import BaseModel, Field


# Define the schema using Pydantic
class CapitalInfo(BaseModel):
    name: str = Field(..., pattern=r"^\w+$", description="Name of the capital city")
    population: int = Field(..., description="Population of the capital city")


response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    messages=[
        {
            "role": "assistant",
            "content": "Give me the information and population of the capital of France in the JSON format.",
        },
    ],
    temperature=0,
    max_tokens=2048,
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "foo",
            # convert the pydantic model to json schema
            "schema": CapitalInfo.model_json_schema(),
        },
    },
)

print_highlight(
    f"reasoing_content: {response.choices[0].message.reasoning_content}\n\ncontent: {response.choices[0].message.content}"
)

JSON Schema Directly

[ ]:

import json

json_schema = json.dumps(
    {
        "type": "object",
        "properties": {
            "name": {"type": "string", "pattern": "^[\\w]+$"},
            "population": {"type": "integer"},
        },
        "required": ["name", "population"],
    }
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    messages=[
        {
            "role": "assistant",
            "content": "Give me the information and population of the capital of France in the JSON format.",
        },
    ],
    temperature=0,
    max_tokens=2048,
    response_format={
        "type": "json_schema",
        "json_schema": {"name": "foo", "schema": json.loads(json_schema)},
    },
)

print_highlight(
    f"reasoing_content: {response.choices[0].message.reasoning_content}\n\ncontent: {response.choices[0].message.content}"
)

EBNF#

[ ]:

ebnf_grammar = """
root ::= city | description
city ::= "London" | "Paris" | "Berlin" | "Rome"
description ::= city " is " status
status ::= "the capital of " country
country ::= "England" | "France" | "Germany" | "Italy"
"""

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    messages=[
        {"role": "system", "content": "You are a helpful geography bot."},
        {
            "role": "assistant",
            "content": "Give me the information and population of the capital of France in the JSON format.",
        },
    ],
    temperature=0,
    max_tokens=2048,
    extra_body={"ebnf": ebnf_grammar},
)

print_highlight(
    f"reasoing_content: {response.choices[0].message.reasoning_content}\n\ncontent: {response.choices[0].message.content}"
)

Regular expression#

[ ]:

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    messages=[
        {"role": "assistant", "content": "What is the capital of France?"},
    ],
    temperature=0,
    max_tokens=2048,
    extra_body={"regex": "(Paris|London)"},
)

print_highlight(
    f"reasoing_content: {response.choices[0].message.reasoning_content}\n\ncontent: {response.choices[0].message.content}"
)

Structural Tag#

[ ]:

tool_get_current_weather = {
    "type": "function",
    "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {
                    "type": "string",
                    "description": "The city to find the weather for, e.g. 'San Francisco'",
                },
                "state": {
                    "type": "string",
                    "description": "the two-letter abbreviation for the state that the city is"
                    " in, e.g. 'CA' which would mean 'California'",
                },
                "unit": {
                    "type": "string",
                    "description": "The unit to fetch the temperature in",
                    "enum": ["celsius", "fahrenheit"],
                },
            },
            "required": ["city", "state", "unit"],
        },
    },
}

tool_get_current_date = {
    "type": "function",
    "function": {
        "name": "get_current_date",
        "description": "Get the current date and time for a given timezone",
        "parameters": {
            "type": "object",
            "properties": {
                "timezone": {
                    "type": "string",
                    "description": "The timezone to fetch the current date and time for, e.g. 'America/New_York'",
                }
            },
            "required": ["timezone"],
        },
    },
}

schema_get_current_weather = tool_get_current_weather["function"]["parameters"]
schema_get_current_date = tool_get_current_date["function"]["parameters"]


def get_messages():
    return [
        {
            "role": "system",
            "content": f"""
# Tool Instructions
- Always execute python code in messages that you share.
- When looking for real time information use relevant functions if available else fallback to brave_search
You have access to the following functions:
Use the function 'get_current_weather' to: Get the current weather in a given location
{tool_get_current_weather["function"]}
Use the function 'get_current_date' to: Get the current date and time for a given timezone
{tool_get_current_date["function"]}
If a you choose to call a function ONLY reply in the following format:
<{{start_tag}}={{function_name}}>{{parameters}}{{end_tag}}
where
start_tag => `<function`
parameters => a JSON dict with the function argument name as key and function argument value as value.
end_tag => `</function>`
Here is an example,
<function=example_function_name>{{"example_name": "example_value"}}</function>
Reminder:
- Function calls MUST follow the specified format
- Required parameters MUST be specified
- Only call one function at a time
- Put the entire function call reply on one line
- Always add your sources when using search results to answer the user query
You are a helpful assistant.""",
        },
        {
            "role": "assistant",
            "content": "You are in New York. Please get the current date and time, and the weather.",
        },
    ]


messages = get_messages()

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    messages=messages,
    response_format={
        "type": "structural_tag",
        "max_new_tokens": 2048,
        "structures": [
            {
                "begin": "<function=get_current_weather>",
                "schema": schema_get_current_weather,
                "end": "</function>",
            },
            {
                "begin": "<function=get_current_date>",
                "schema": schema_get_current_date,
                "end": "</function>",
            },
        ],
        "triggers": ["<function="],
    },
)

print_highlight(
    f"reasoing_content: {response.choices[0].message.reasoning_content}\n\ncontent: {response.choices[0].message.content}"
)

Native API and SGLang Runtime (SRT)#

JSON#

Using Pydantic

[ ]:

import requests
from pydantic import BaseModel, Field
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-7B")


# Define the schema using Pydantic
class CapitalInfo(BaseModel):
    name: str = Field(..., pattern=r"^\w+$", description="Name of the capital city")
    population: int = Field(..., description="Population of the capital city")


messages = [
    {
        "role": "assistant",
        "content": "Give me the information and population of the capital of France in the JSON format.",
    },
]
text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
# Make API request
response = requests.post(
    f"http://localhost:{port}/generate",
    json={
        "text": text,
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 2048,
            "json_schema": json.dumps(CapitalInfo.model_json_schema()),
        },
    },
)
print(response.json())


reasoing_content = response.json()["text"].split("</think>")[0]
content = response.json()["text"].split("</think>")[1]
print_highlight(f"reasoing_content: {reasoing_content}\n\ncontent: {content}")

JSON Schema Directly

[ ]:

json_schema = json.dumps(
    {
        "type": "object",
        "properties": {
            "name": {"type": "string", "pattern": "^[\\w]+$"},
            "population": {"type": "integer"},
        },
        "required": ["name", "population"],
    }
)

# JSON
text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
response = requests.post(
    f"http://localhost:{port}/generate",
    json={
        "text": text,
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 2048,
            "json_schema": json_schema,
        },
    },
)

print_highlight(response.json())

EBNF#

[ ]:

response = requests.post(
    f"http://localhost:{port}/generate",
    json={
        "text": "Give me the information of the capital of France.",
        "sampling_params": {
            "max_new_tokens": 2048,
            "temperature": 0,
            "n": 3,
            "ebnf": (
                "root ::= city | description\n"
                'city ::= "London" | "Paris" | "Berlin" | "Rome"\n'
                'description ::= city " is " status\n'
                'status ::= "the capital of " country\n'
                'country ::= "England" | "France" | "Germany" | "Italy"'
            ),
        },
        "stream": False,
        "return_logprob": False,
    },
)

print(response.json())

Regular expression#

[ ]:

response = requests.post(
    f"http://localhost:{port}/generate",
    json={
        "text": "Paris is the capital of",
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 2048,
            "regex": "(France|England)",
        },
    },
)
print(response.json())

Structural Tag#

[ ]:

text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
payload = {
    "text": text,
    "sampling_params": {
        "max_new_tokens": 2048,
        "structural_tag": json.dumps(
            {
                "type": "structural_tag",
                "structures": [
                    {
                        "begin": "<function=get_current_weather>",
                        "schema": schema_get_current_weather,
                        "end": "</function>",
                    },
                    {
                        "begin": "<function=get_current_date>",
                        "schema": schema_get_current_date,
                        "end": "</function>",
                    },
                ],
                "triggers": ["<function="],
            }
        ),
    },
}


# Send POST request to the API endpoint
response = requests.post(f"http://localhost:{port}/generate", json=payload)
print_highlight(response.json())

[ ]:

terminate_process(server_process)

Offline Engine API#

[ ]:

import sglang as sgl

llm = sgl.Engine(
    model_path="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    reasoning_parser="deepseek-r1",
    grammar_backend="xgrammar",
)

JSON#

Using Pydantic

[ ]:

import json
from pydantic import BaseModel, Field


prompts = [
    "Give me the information of the capital of China in the JSON format.",
    "Give me the information of the capital of France in the JSON format.",
    "Give me the information of the capital of Ireland in the JSON format.",
]


# Define the schema using Pydantic
class CapitalInfo(BaseModel):
    name: str = Field(..., pattern=r"^\w+$", description="Name of the capital city")
    population: int = Field(..., description="Population of the capital city")


sampling_params = {
    "temperature": 0,
    "top_p": 0.95,
    "max_new_tokens": 2048,
    "json_schema": json.dumps(CapitalInfo.model_json_schema()),
}

outputs = llm.generate(prompts, sampling_params)
for prompt, output in zip(prompts, outputs):
    print("===============================")
    print(f"Prompt: {prompt}\nGenerated text: {output['text']}")

JSON Schema Directly

[ ]:

prompts = [
    "Give me the information of the capital of China in the JSON format.",
    "Give me the information of the capital of France in the JSON format.",
    "Give me the information of the capital of Ireland in the JSON format.",
]

json_schema = json.dumps(
    {
        "type": "object",
        "properties": {
            "name": {"type": "string", "pattern": "^[\\w]+$"},
            "population": {"type": "integer"},
        },
        "required": ["name", "population"],
    }
)

sampling_params = {"temperature": 0, "max_new_tokens": 2048, "json_schema": json_schema}

outputs = llm.generate(prompts, sampling_params)
for prompt, output in zip(prompts, outputs):
    print("===============================")
    print(f"Prompt: {prompt}\nGenerated text: {output['text']}")

EBNF#

[ ]:

prompts = [
    "Give me the information of the capital of France.",
    "Give me the information of the capital of Germany.",
    "Give me the information of the capital of Italy.",
]

sampling_params = {
    "temperature": 0.8,
    "top_p": 0.95,
    "ebnf": (
        "root ::= city | description\n"
        'city ::= "London" | "Paris" | "Berlin" | "Rome"\n'
        'description ::= city " is " status\n'
        'status ::= "the capital of " country\n'
        'country ::= "England" | "France" | "Germany" | "Italy"'
    ),
}

outputs = llm.generate(prompts, sampling_params)
for prompt, output in zip(prompts, outputs):
    print("===============================")
    print(f"Prompt: {prompt}\nGenerated text: {output['text']}")

Regular expression#

[ ]:

prompts = [
    "Please provide information about London as a major global city:",
    "Please provide information about Paris as a major global city:",
]

sampling_params = {"temperature": 0.8, "top_p": 0.95, "regex": "(France|England)"}

outputs = llm.generate(prompts, sampling_params)
for prompt, output in zip(prompts, outputs):
    print("===============================")
    print(f"Prompt: {prompt}\nGenerated text: {output['text']}")

[ ]:

text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
prompts = [text]


sampling_params = {
    "temperature": 0.8,
    "top_p": 0.95,
    "max_new_tokens": 2048,
    "structural_tag": json.dumps(
        {
            "type": "structural_tag",
            "structures": [
                {
                    "begin": "<function=get_current_weather>",
                    "schema": schema_get_current_weather,
                    "end": "</function>",
                },
                {
                    "begin": "<function=get_current_date>",
                    "schema": schema_get_current_date,
                    "end": "</function>",
                },
            ],
            "triggers": ["<function="],
        }
    ),
}


# Send POST request to the API endpoint
outputs = llm.generate(prompts, sampling_params)
for prompt, output in zip(prompts, outputs):
    print("===============================")
    print(f"Prompt: {prompt}\nGenerated text: {output['text']}")

[ ]:

llm.shutdown()

Structured Outputs For Reasoning Models

Contents

Structured Outputs For Reasoning Models#

Supported Models#

Usage#

OpenAI Compatible API#

JSON#

EBNF#

Regular expression#

Structural Tag#

Native API and SGLang Runtime (SRT)#

JSON#

EBNF#

Regular expression#

Structural Tag#

Offline Engine API#

JSON#

EBNF#

Regular expression#