sglang/docs/backend/structured_outputs.ipynb

Structured Outputs

You can specify a JSON schema, regular expression or EBNF to constrain the model output. The model output will be guaranteed to follow the given constraints. Only one constraint parameter (json_schema, regex, or ebnf) can be specified for a request.

SGLang supports three grammar backends:

• Outlines: Supports JSON schema and regular expression constraints.
• XGrammar(default): Supports JSON schema, regular expression, and EBNF constraints.
• Llguidance: Supports JSON schema, regular expression, and EBNF constraints.

We suggest using XGrammar for its better performance and utility. XGrammar currently uses the GGML BNF format. For more details, see XGrammar technical overview.

To use Outlines, simply add --grammar-backend outlines when launching the server. To use llguidance, add --grammar-backend llguidance when launching the server. If no backend is specified, XGrammar will be used as the default.

For better output quality, It's advisable to explicitly include instructions in the prompt to guide the model to generate the desired format. For example, you can specify, 'Please generate the output in the following JSON format: ...'.

OpenAI Compatible API

In [ ]:

import openai
import os
from sglang.test.test_utils import is_in_ci

if is_in_ci():
    from patch import launch_server_cmd
else:
    from sglang.utils 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 meta-llama/Meta-Llama-3.1-8B-Instruct --host 0.0.0.0"
)

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

In [ ]:

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="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {
            "role": "user",
            "content": "Please generate the information of the capital of France in the JSON format.",
        },
    ],
    temperature=0,
    max_tokens=128,
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "foo",
            # convert the pydantic model to json schema
            "schema": CapitalInfo.model_json_schema(),
        },
    },
)

response_content = response.choices[0].message.content
# validate the JSON response by the pydantic model
capital_info = CapitalInfo.model_validate_json(response_content)
print_highlight(f"Validated response: {capital_info.model_dump_json()}")

JSON Schema Directly

In [ ]:

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="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {
            "role": "user",
            "content": "Give me the information of the capital of France in the JSON format.",
        },
    ],
    temperature=0,
    max_tokens=128,
    response_format={
        "type": "json_schema",
        "json_schema": {"name": "foo", "schema": json.loads(json_schema)},
    },
)

print_highlight(response.choices[0].message.content)

EBNF

In [ ]:

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="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {"role": "system", "content": "You are a helpful geography bot."},
        {
            "role": "user",
            "content": "Give me the information of the capital of France.",
        },
    ],
    temperature=0,
    max_tokens=32,
    extra_body={"ebnf": ebnf_grammar},
)

print_highlight(response.choices[0].message.content)

Regular expression

In [ ]:

response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {"role": "user", "content": "What is the capital of France?"},
    ],
    temperature=0,
    max_tokens=128,
    extra_body={"regex": "(Paris|London)"},
)

print_highlight(response.choices[0].message.content)

Structural Tag

In [ ]:

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": "user",
            "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="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=messages,
    response_format={
        "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="],
    },
)

print_highlight(response.choices[0].message.content)

Native API and SGLang Runtime (SRT)

JSON

Using Pydantic

In [ ]:

import requests
import json
from pydantic import BaseModel, Field

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")


# 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")


# Make API request
messages = [
    {
        "role": "user",
        "content": "Here is the information of the capital of France in the JSON format.\n",
    }
]
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": 64,
            "json_schema": json.dumps(CapitalInfo.model_json_schema()),
        },
    },
)
print_highlight(response.json())


response_data = json.loads(response.json()["text"])
# validate the response by the pydantic model
capital_info = CapitalInfo.model_validate(response_data)
print_highlight(f"Validated response: {capital_info.model_dump_json()}")

JSON Schema Directly

In [ ]:

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

# JSON
response = requests.post(
    f"http://localhost:{port}/generate",
    json={
        "text": text,
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 64,
            "json_schema": json_schema,
        },
    },
)

print_highlight(response.json())

EBNF

In [ ]:

messages = [
    {
        "role": "user",
        "content": "Give me the information of the capital of France.",
    }
]
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": {
            "max_new_tokens": 128,
            "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_highlight(response.json())

Regular expression

In [ ]:

messages = [
    {
        "role": "user",
        "content": "Paris is the capital of",
    }
]
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": 64,
            "regex": "(France|England)",
        },
    },
)
print_highlight(response.json())

Structural Tag

In [ ]:

from transformers import AutoTokenizer

# generate an answer
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")

text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
payload = {
    "text": text,
    "sampling_params": {
        "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())

In [ ]:

terminate_process(server_process)

Offline Engine API

In [ ]:

import sglang as sgl

llm = sgl.Engine(
    model_path="meta-llama/Meta-Llama-3.1-8B-Instruct", grammar_backend="xgrammar"
)

JSON

Using Pydantic

In [ ]:

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": 0.1,
    "top_p": 0.95,
    "json_schema": json.dumps(CapitalInfo.model_json_schema()),
}

outputs = llm.generate(prompts, sampling_params)
for prompt, output in zip(prompts, outputs):
    print_highlight("===============================")
    print_highlight(f"Prompt: {prompt}")  # validate the output by the pydantic model
    capital_info = CapitalInfo.model_validate_json(output["text"])
    print_highlight(f"Validated output: {capital_info.model_dump_json()}")

JSON Schema Directly

In [ ]:

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": 0.1, "top_p": 0.95, "json_schema": json_schema}

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

EBNF

In [ ]:

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_highlight("===============================")
    print_highlight(f"Prompt: {prompt}\nGenerated text: {output['text']}")

Regular expression

In [ ]:

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_highlight("===============================")
    print_highlight(f"Prompt: {prompt}\nGenerated text: {output['text']}")

Structural Tag

In [ ]:

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


sampling_params = {
    "temperature": 0.8,
    "top_p": 0.95,
    "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_highlight("===============================")
    print_highlight(f"Prompt: {prompt}\nGenerated text: {output['text']}")

In [ ]:

llm.shutdown()