Outlines

Outlines: Structured Text Generation

When to Use This Skill

Use Outlines when you need to:

• Guarantee valid JSON/XML/code structure during generation
• Use Pydantic models for type-safe outputs
• Support local models (Transformers, llama.cpp, vLLM)
• Maximize inference speed with zero-overhead structured generation
• Generate against JSON schemas automatically
• Control token sampling at the grammar level

GitHub Stars: 8,000+ | From: dottxt.ai (formerly .txt)

Installation

# Base installation
pip install outlines

# With specific backends
pip install outlines transformers  # Hugging Face models
pip install outlines llama-cpp-python  # llama.cpp
pip install outlines vllm  # vLLM for high-throughput

Quick Start

Basic Example: Classification

import outlines
from typing import Literal

# Load model
model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")

# Generate with type constraint
prompt = "Sentiment of 'This product is amazing!': "
generator = outlines.generate.choice(model, ["positive", "negative", "neutral"])
sentiment = generator(prompt)

print(sentiment)  # "positive" (guaranteed one of these)

With Pydantic Models

from pydantic import BaseModel
import outlines

class User(BaseModel):
    name: str
    age: int
    email: str

model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")

# Generate structured output
prompt = "Extract user: John Doe, 30 years old, john@example.com"
generator = outlines.generate.json(model, User)
user = generator(prompt)

print(user.name)   # "John Doe"
print(user.age)    # 30
print(user.email)  # "john@example.com"

Core Concepts

1. Constrained Token Sampling

Outlines uses Finite State Machines (FSM) to constrain token generation at the logit level.

How it works:

1. Convert schema (JSON/Pydantic/regex) to context-free grammar (CFG)
2. Transform CFG into Finite State Machine (FSM)
3. Filter invalid tokens at each step during generation
4. Fast-forward when only one valid token exists

Benefits:

• Zero overhead: Filtering happens at token level
• Speed improvement: Fast-forward through deterministic paths
• Guaranteed validity: Invalid outputs impossible

import outlines

# Pydantic model -> JSON schema -> CFG -> FSM
class Person(BaseModel):
    name: str
    age: int

model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")

# Behind the scenes:
# 1. Person -> JSON schema
# 2. JSON schema -> CFG
# 3. CFG -> FSM
# 4. FSM filters tokens during generation

generator = outlines.generate.json(model, Person)
result = generator("Generate person: Alice, 25")

2. Structured Generators

Outlines provides specialized generators for different output types.

Choice Generator

# Multiple choice selection
generator = outlines.generate.choice(
    model,
    ["positive", "negative", "neutral"]
)

sentiment = generator("Review: This is great!")
# Result: One of the three choices

JSON Generator

from pydantic import BaseModel

class Product(BaseModel):
    name: str
    price: float
    in_stock: bool

# Generate valid JSON matching schema
generator = outlines.generate.json(model, Product)
product = generator("Extract: iPhone 15, $999, available")

# Guaranteed valid Product instance
print(type(product))  # <class '__main__.Product'>

Regex Generator

# Generate text matching regex
generator = outlines.generate.regex(
    model,
    r"[0-9]{3}-[0-9]{3}-[0-9]{4}"  # Phone number pattern
)

phone = generator("Generate phone number:")
# Result: "555-123-4567" (guaranteed to match pattern)

Integer/Float Generators

# Generate specific numeric types
int_generator = outlines.generate.integer(model)
age = int_generator("Person's age:")  # Guaranteed integer

float_generator = outlines.generate.float(model)
price = float_generator("Product price:")  # Guaranteed float

3. Model Backends

Outlines supports multiple local and API-based backends.

Transformers (Hugging Face)

import outlines

# Load from Hugging Face
model = outlines.models.transformers(
    "microsoft/Phi-3-mini-4k-instruct",
    device="cuda"  # Or "cpu"
)

# Use with any generator
generator = outlines.generate.json(model, YourModel)

llama.cpp

# Load GGUF model
model = outlines.models.llamacpp(
    "./models/llama-3.1-8b-instruct.Q4_K_M.gguf",
    n_gpu_layers=35
)

generator = outlines.generate.json(model, YourModel)

vLLM (High Throughput)

# For production deployments
model = outlines.models.vllm(
    "meta-llama/Llama-3.1-8B-Instruct",
    tensor_parallel_size=2  # Multi-GPU
)

generator = outlines.generate.json(model, YourModel)

OpenAI (Limited Support)

# Basic OpenAI support
model = outlines.models.openai(
    "gpt-4o-mini",
    api_key="your-api-key"
)

# Note: Some features limited with API models
generator = outlines.generate.json(model, YourModel)

4. Pydantic Integration

Outlines has first-class Pydantic support with automatic schema translation.

Basic Models

from pydantic import BaseModel, Field

class Article(BaseModel):
    title: str = Field(description="Article title")
    author: str = Field(description="Author name")
    word_count: int = Field(description="Number of words", gt=0)
    tags: list[str] = Field(description="List of tags")

model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")
generator = outlines.generate.json(model, Article)

article = generator("Generate article about AI")
print(article.title)
print(article.word_count)  # Guaranteed > 0

Nested Models

class Address(BaseModel):
    street: str
    city: str
    country: str

class Person(BaseModel):
    name: str
    age: int
    address: Address  # Nested model

generator = outlines.generate.json(model, Person)
person = generator("Generate person in New York")

print(person.address.city)  # "New York"

Enums and Literals

from enum import Enum
from typing import Literal

class Status(str, Enum):
    PENDING = "pending"
    APPROVED = "approved"
    REJECTED = "rejected"

class Application(BaseModel):
    applicant: str
    status: Status  # Must be one of enum values
    priority: Literal["low", "medium", "high"]  # Must be one of literals

generator = outlines.generate.json(model, Application)
app = generator("Generate application")

print(app.status)  # Status.PENDING (or APPROVED/REJECTED)

Common Patterns

Pattern 1: Data Extraction

from pydantic import BaseModel
import outlines

class CompanyInfo(BaseModel):
    name: str
    founded_year: int
    industry: str
    employees: int

model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")
generator = outlines.generate.json(model, CompanyInfo)

text = """
Apple Inc. was founded in 1976 in the technology industry.
The company employs approximately 164,000 people worldwide.
"""

prompt = f"Extract company information:\n{text}\n\nCompany:"
company = generator(prompt)

print(f"Name: {company.name}")
print(f"Founded: {company.founded_year}")
print(f"Industry: {company.industry}")
print(f"Employees: {company.employees}")

Pattern 2: Classification

from typing import Literal
import outlines

model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")

# Binary classification
generator = outlines.generate.choice(model, ["spam", "not_spam"])
result = generator("Email: Buy now! 50% off!")

# Multi-class classification
categories = ["technology", "business", "sports", "entertainment"]
category_gen = outlines.generate.choice(model, categories)
category = category_gen("Article: Apple announces new iPhone...")

# With confidence
class Classification(BaseModel):
    label: Literal["positive", "negative", "neutral"]
    confidence: float

classifier = outlines.generate.json(model, Classification)
result = classifier("Review: This product is okay, nothing special")

Pattern 3: Structured Forms

class UserProfile(BaseModel):
    full_name: str
    age: int
    email: str
    phone: str
    country: str
    interests: list[str]

model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")
generator = outlines.generate.json(model, UserProfile)

prompt = """
Extract user profile from:
Name: Alice Johnson
Age: 28
Email: alice@example.com
Phone: 555-0123
Country: USA
Interests: hiking, photography, cooking
"""

profile = generator(prompt)
print(profile.full_name)
print(profile.interests)  # ["hiking", "photography", "cooking"]

Pattern 4: Multi-Entity Extraction

class Entity(BaseModel):
    name: str
    type: Literal["PERSON", "ORGANIZATION", "LOCATION"]

class DocumentEntities(BaseModel):
    entities: list[Entity]

model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")
generator = outlines.generate.json(model, DocumentEntities)

text = "Tim Cook met with Satya Nadella at Microsoft headquarters in Redmond."
prompt = f"Extract entities from: {text}"

result = generator(prompt)
for entity in result.entities:
    print(f"{entity.name} ({entity.type})")

Pattern 5: Code Generation

class PythonFunction(BaseModel):
    function_name: str
    parameters: list[str]
    docstring: str
    body: str

model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")
generator = outlines.generate.json(model, PythonFunction)

prompt = "Generate a Python function to calculate factorial"
func = generator(prompt)

print(f"def {func.function_name}({', '.join(func.parameters)}):")
print(f'    """{func.docstring}"""')
print(f"    {func.body}")

Pattern 6: Batch Processing

def batch_extract(texts: list[str], schema: type[BaseModel]):
    """Extract structured data from multiple texts."""
    model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")
    generator = outlines.generate.json(model, schema)

    results = []
    for text in texts:
        result = generator(f"Extract from: {text}")
        results.append(result)

    return results

class Person(BaseModel):
    name: str
    age: int

texts = [
    "John is 30 years old",
    "Alice is 25 years old",
    "Bob is 40 years old"
]

people = batch_extract(texts, Person)
for person in people:
    print(f"{person.name}: {person.age}")

Backend Configuration

Transformers

import outlines

# Basic usage
model = outlines.models.transformers("microsoft/Phi-3-mini-4k-instruct")

# GPU configuration
model = outlines.models.transformers(
    "microsoft/Phi-3-mini-4k-instruct",
    device="cuda",
    model_kwargs={"torch_dtype": "float16"}
)

# Popular models
model = outlines.models.transformers("meta-llama/Llama-3.1-8B-Instruct")
model = outlines.models.transformers("mistralai/Mistral-7B-Instruct-v0.3")
model = outlines.models.transformers("Qwen/Qwen2.5-7B-Instruct")

llama.cpp

# Load GGUF model
model = outlines.models.llamacpp(
    "./models/llama-3.1-8b.Q4_K_M.gguf",
    n_ctx=4096,         # Context window
    n_gpu_layers=35,    # GPU layers
    n_threads=8         # CPU threads
)

# Full GPU offload
model = outlines.models.llamacpp(
    "./models/model.gguf",
    n_gpu_layers=-1  # All layers on GPU
)

vLLM (Production)

# Single GPU
model = outlines.models.vllm("meta-llama/Llama-3.1-8B-Instruct")

# Multi-GPU
model = outlines.models.vllm(
    "meta-llama/Llama-3.1-70B-Instruct",
    tensor_parallel_size=4  # 4 GPUs
)

# With quantization
model = outlines.models.vllm(
    "meta-llama/Llama-3.1-8B-Instruct",
    quantization="awq"  # Or "gptq"
)

Best Practices

1. Use Specific Types

# ✅ Good: Specific types
class Product(BaseModel):
    name: str
    price: float  # Not str
    quantity: int  # Not str
    in_stock: bool  # Not str

# ❌ Bad: Everything as string
class Product(BaseModel):
    name: str
    price: str  # Should be float
    quantity: str  # Should be int

2. Add Constraints

from pydantic import Field

# ✅ Good: With constraints
class User(BaseModel):
    name: str = Field(min_length=1, max_length=100)
    age: int = Field(ge=0, le=120)
    email: str = Field(pattern=r"^[\w\.-]+@[\w\.-]+\.\w+$")

# ❌ Bad: No constraints
class User(BaseModel):
    name: str
    age: int
    email: str

3. Use Enums for Categories

# ✅ Good: Enum for fixed set
class Priority(str, Enum):
    LOW = "low"
    MEDIUM = "medium"
    HIGH = "high"

class Task(BaseModel):
    title: str
    priority: Priority

# ❌ Bad: Free-form string
class Task(BaseModel):
    title: str
    priority: str  # Can be anything

4. Provide Context in Prompts

# ✅ Good: Clear context
prompt = """
Extract product information from the following text.
Text: iPhone 15 Pro costs $999 and is currently in stock.
Product:
"""

# ❌ Bad: Minimal context
prompt = "iPhone 15 Pro costs $999 and is currently in stock."

5. Handle Optional Fields

from typing import Optional

# ✅ Good: Optional fields for incomplete data
class Article(BaseModel):
    title: str  # Required
    author: Optional[str] = None  # Optional
    date: Optional[str] = None  # Optional
    tags: list[str] = []  # Default empty list

# Can succeed even if author/date missing

Comparison to Alternatives

When to choose Outlines:

• Using local models (Transformers, llama.cpp, vLLM)
• Need maximum inference speed
• Want Pydantic model support
• Require zero-overhead structured generation
• Control token sampling process

When to Choose Outlines vs Instructor

Decision Tree

Are you using LOCAL models (Transformers, llama.cpp, vLLM)?
├─ YES → Use **Outlines**
│  └─ Benefits: Zero overhead, grammar-based generation, maximum speed
│
└─ NO → Are you using API models (Anthropic, OpenAI, Google)?
   ├─ YES → Use **Instructor**
   │  └─ Benefits: Automatic retry, multi-provider support, easier setup
   │
   └─ NO → Do you need BOTH local and cloud?
      └─ YES → Use **Instructor** (supports both via provider abstraction)

Comparison Table

Use Cases for TRAE_Extractor-app

Use Outlines when:

• Running local models via Docker Model Runner
• Need maximum inference speed for captioning
• Generating structured data from local LLMs
• Want zero-overhead validation
• Using llama.cpp or vLLM for inference

Use Instructor when:

• Using cloud providers (Anthropic, OpenAI, Google, Perplexity)
• Need automatic retry on API failures
• Working with multi-provider setup
• Want easier setup and maintenance
• Need both local and cloud support

Docker Model Runner Integration

Pattern for Using Outlines with Docker Model Runner

import outlines
from outlines.models import llamacpp

# Load local model via Docker Model Runner
model = llamacpp(
    "./models/llama-3.1-8b.Q4_K_M.gguf",
    n_ctx=4096,
    n_gpu_layers=35
)

# Generate structured output
generator = outlines.generate.json(model, CaptionSchema)

async def generate_caption(image_description: str) -> CaptionSchema:
    try:
        caption = generator(f"Generate caption for: {image_description}")
        return caption
    except Exception as e:
        # Fallback to cloud if local fails
        logger.warning(f"Local model failed: {e}, falling back to cloud")
        return await generate_caption_cloud(image_description)

async def generate_caption_cloud(image_description: str) -> CaptionSchema:
    # Use Instructor with cloud provider
    from instructor import OpenAI
    client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
    
    return client.chat.completions.create(
        model="gpt-4o-mini",
        response_model=CaptionSchema,
        messages=[{"role": "user", "content": image_description}]
    )

Fallback Strategy: Local → Cloud

import outlines
from instructor import OpenAI
import logging

logger = logging.getLogger(__name__)

class HybridCaptionGenerator:
    """Hybrid generator using local Outlines with cloud Instructor fallback"""
    
    def __init__(self, local_model_path: str, cloud_api_key: str):
        self.local_model = outlines.models.llamacpp(
            local_model_path,
            n_ctx=4096,
            n_gpu_layers=35
        )
        self.cloud_client = OpenAI(api_key=cloud_api_key)
        self.use_local = True
    
    async def generate(self, prompt: str, schema: type):
        """Generate with automatic fallback to cloud"""
        if self.use_local:
            try:
                generator = outlines.generate.json(self.local_model, schema)
                result = generator(prompt)
                logger.info(f"Generated caption using local model")
                return result
            except Exception as e:
                logger.warning(f"Local model failed: {e}, switching to cloud")
                self.use_local = False
                # Retry with cloud
                return await self.generate(prompt, schema)
        else:
            # Use cloud provider
            generator = outlines.generate.json(self.cloud_client, schema)
            result = generator(prompt)
            logger.info(f"Generated caption using cloud model")
            return result
    
    def reset_to_local(self):
        """Reset to use local model after successful generation"""
        self.use_local = True
        logger.info("Switched back to local model")

Benchmark Performance: Local vs Cloud

import time
import outlines
from instructor import OpenAI

async def benchmark_caption_generation():
    """Compare local vs cloud performance"""
    prompts = [
        "A beautiful sunset at the beach",
        "A mountain landscape with snow",
        "A city skyline at night"
    ]
    
    # Local model benchmark
    local_model = outlines.models.llamacpp(
        "./models/llama-3.1-8b.Q4_K_M.gguf",
        n_ctx=4096,
        n_gpu_layers=35
    )
    local_generator = outlines.generate.json(local_model, CaptionSchema)
    
    local_times = []
    for prompt in prompts:
        start = time.time()
        result = local_generator(prompt)
        elapsed = time.time() - start
        local_times.append(elapsed)
    
    # Cloud model benchmark
    cloud_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
    cloud_generator = outlines.generate.json(cloud_client, CaptionSchema)
    
    cloud_times = []
    for prompt in prompts:
        start = time.time()
        result = cloud_generator(prompt)
        elapsed = time.time() - start
        cloud_times.append(elapsed)
    
    # Results
    avg_local = sum(local_times) / len(local_times)
    avg_cloud = sum(cloud_times) / len(cloud_times)
    speedup = avg_cloud / avg_local
    
    print(f"Local average: {avg_local:.2f}s")
    print(f"Cloud average: {avg_cloud:.2f}s")
    print(f"Speedup: {speedup:.2f}x faster")
    print(f"Local is {speedup:.0%} of cloud time")

When to choose alternatives:

• Instructor: Need API models with automatic retrying
• Guidance: Need token healing and complex workflows
• LMQL: Prefer declarative query syntax

Performance Characteristics

Speed:

• Zero overhead: Structured generation as fast as unconstrained
• Fast-forward optimization: Skips deterministic tokens
• 1.2-2x faster than post-generation validation approaches

Memory:

• FSM compiled once per schema (cached)
• Minimal runtime overhead
• Efficient with vLLM for high throughput

Accuracy:

• 100% valid outputs (guaranteed by FSM)
• No retry loops needed
• Deterministic token filtering

Resources

• Documentation: https://outlines-dev.github.io/outlines
• GitHub: https://github.com/outlines-dev/outlines (8k+ stars)
• Discord: https://discord.gg/R9DSu34mGd
• Blog: https://blog.dottxt.co

See Also

• references/json_generation.md - Comprehensive JSON and Pydantic patterns
• references/backends.md - Backend-specific configuration
• references/examples.md - Production-ready examples