Guidance

# Base installation
pip install guidance

# With specific backends
pip install guidance[transformers]  # Hugging Face models
pip install guidance[llama_cpp]     # llama.cpp models

from guidance import models, gen

# Load model (supports OpenAI, Transformers, llama.cpp)
lm = models.OpenAI("gpt-4")

# Generate with constraints
result = lm + "The capital of France is " + gen("capital", max_tokens=5)

print(result["capital"])  # "Paris"

from guidance import models, gen, system, user, assistant

# Local model (supports constrained generation)
lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# Use context managers for chat format
with system():
    lm += "You are a helpful assistant."

with user():
    lm += "What is the capital of France?"

with assistant():
    lm += gen(max_tokens=20)

from guidance import system, user, assistant, gen

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# System message
with system():
    lm += "You are a JSON generation expert."

# User message
with user():
    lm += "Generate a person object with name and age."

# Assistant response
with assistant():
    lm += gen("response", max_tokens=100)

print(lm["response"])

from guidance import models, gen

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# Constrain to valid email format
lm += "Email: " + gen("email", regex=r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")

# Constrain to date format (YYYY-MM-DD)
lm += "Date: " + gen("date", regex=r"\d{4}-\d{2}-\d{2}")

# Constrain to phone number
lm += "Phone: " + gen("phone", regex=r"\d{3}-\d{3}-\d{4}")

print(lm["email"])  # Guaranteed valid email
print(lm["date"])   # Guaranteed YYYY-MM-DD format

from guidance import models, gen, select

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# Constrain to specific choices
lm += "Sentiment: " + select(["positive", "negative", "neutral"], name="sentiment")

# Multiple-choice selection
lm += "Best answer: " + select(
    ["A) Paris", "B) London", "C) Berlin", "D) Madrid"],
    name="answer"
)

print(lm["sentiment"])  # One of: positive, negative, neutral
print(lm["answer"])     # One of: A, B, C, or D

# Without token healing
prompt = "The capital of France is "
# Last token: " is "
# First generated token might be " Par" (with leading space)
# Result: "The capital of France is  Paris" (double space!)

from guidance import models, gen

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# Token healing enabled by default
lm += "The capital of France is " + gen("capital", max_tokens=5)
# Result: "The capital of France is Paris" (correct spacing)

from guidance import models, gen
from guidance import json as gen_json
from pydantic import BaseModel, Field

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# JSON via a Pydantic schema (guidance.json compiles the schema to a grammar)
class Person(BaseModel):
    name: str = Field(pattern=r"[A-Za-z ]+")
    age: int
    email: str = Field(pattern=r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")

lm += gen_json(name="person", schema=Person)

print(lm["person"])  # Guaranteed valid JSON matching the schema

# Or compose grammar functions directly:
grammar = "name=" + gen("name", regex=r"[A-Za-z ]+") + " age=" + gen("age", regex=r"[0-9]+")
lm += grammar

from guidance import guidance, gen, models

@guidance
def generate_person(lm):
    """Generate a person with name and age."""
    lm += "Name: " + gen("name", max_tokens=20, stop="\n")
    lm += "\nAge: " + gen("age", regex=r"[0-9]+", max_tokens=3)
    return lm

# Use the function
lm = models.Transformers("microsoft/Phi-4-mini-instruct")
lm = generate_person(lm)

print(lm["name"])
print(lm["age"])

@guidance(stateless=False)
def react_agent(lm, question, tools, max_rounds=5):
    """ReAct agent with tool use."""
    lm += f"Question: {question}\n\n"

    for i in range(max_rounds):
        # Thought
        lm += f"Thought {i+1}: " + gen("thought", stop="\n")

        # Action
        lm += "\nAction: " + select(list(tools.keys()), name="action")

        # Execute tool
        tool_result = tools[lm["action"]]()
        lm += f"\nObservation: {tool_result}\n\n"

        # Check if done
        lm += "Done? " + select(["Yes", "No"], name="done")
        if lm["done"] == "Yes":
            break

    # Final answer
    lm += "\nFinal Answer: " + gen("answer", max_tokens=100)
    return lm

from guidance import models

lm = models.OpenAI(
    model="gpt-4o-mini",
    api_key="your-api-key"  # Or set OPENAI_API_KEY env var
)

from guidance.models import Transformers

lm = Transformers(
    "microsoft/Phi-4-mini-instruct",
    device="cuda"  # Or "cpu"
)

from guidance.models import LlamaCpp

lm = LlamaCpp(
    model_path="/path/to/model.gguf",
    n_ctx=4096,
    n_gpu_layers=35
)

from guidance import models, gen, system, user, assistant

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

with system():
    lm += "You generate valid JSON."

with user():
    lm += "Generate a user profile with name, age, and email."

with assistant():
    lm += """{
    "name": """ + gen("name", regex=r'"[A-Za-z ]+"', max_tokens=30) + """,
    "age": """ + gen("age", regex=r"[0-9]+", max_tokens=3) + """,
    "email": """ + gen("email", regex=r'"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}"', max_tokens=50) + """
}"""

print(lm)  # Valid JSON guaranteed

from guidance import models, gen, select

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

text = "This product is amazing! I love it."

lm += f"Text: {text}\n"
lm += "Sentiment: " + select(["positive", "negative", "neutral"], name="sentiment")
lm += "\nConfidence: " + gen("confidence", regex=r"[0-9]+", max_tokens=3) + "%"

print(f"Sentiment: {lm['sentiment']}")
print(f"Confidence: {lm['confidence']}%")

from guidance import models, gen, guidance

@guidance
def chain_of_thought(lm, question):
    """Generate answer with step-by-step reasoning."""
    lm += f"Question: {question}\n\n"

    # Generate multiple reasoning steps
    for i in range(3):
        lm += f"Step {i+1}: " + gen(f"step_{i+1}", stop="\n", max_tokens=100) + "\n"

    # Final answer
    lm += "\nTherefore, the answer is: " + gen("answer", max_tokens=50)

    return lm

lm = models.Transformers("microsoft/Phi-4-mini-instruct")
lm = chain_of_thought(lm, "What is 15% of 200?")

print(lm["answer"])

from guidance import models, gen, select, guidance

@guidance(stateless=False)
def react_agent(lm, question):
    """ReAct agent with tool use."""
    tools = {
        "calculator": lambda expr: eval(expr),
        "search": lambda query: f"Search results for: {query}",
    }

    lm += f"Question: {question}\n\n"

    for round in range(5):
        # Thought
        lm += f"Thought: " + gen("thought", stop="\n") + "\n"

        # Action selection
        lm += "Action: " + select(["calculator", "search", "answer"], name="action")

        if lm["action"] == "answer":
            lm += "\nFinal Answer: " + gen("answer", max_tokens=100)
            break

        # Action input
        lm += "\nAction Input: " + gen("action_input", stop="\n") + "\n"

        # Execute tool
        if lm["action"] in tools:
            result = tools[lm["action"]](lm["action_input"])
            lm += f"Observation: {result}\n\n"

    return lm

lm = models.Transformers("microsoft/Phi-4-mini-instruct")
lm = react_agent(lm, "What is 25 * 4 + 10?")
print(lm["answer"])

from guidance import models, gen, guidance

@guidance
def extract_entities(lm, text):
    """Extract structured entities from text."""
    lm += f"Text: {text}\n\n"

    # Extract person
    lm += "Person: " + gen("person", stop="\n", max_tokens=30) + "\n"

    # Extract organization
    lm += "Organization: " + gen("organization", stop="\n", max_tokens=30) + "\n"

    # Extract date
    lm += "Date: " + gen("date", regex=r"\d{4}-\d{2}-\d{2}", max_tokens=10) + "\n"

    # Extract location
    lm += "Location: " + gen("location", stop="\n", max_tokens=30) + "\n"

    return lm

text = "Tim Cook announced at Apple Park on 2024-09-15 in Cupertino."

lm = models.Transformers("microsoft/Phi-4-mini-instruct")
lm = extract_entities(lm, text)

print(f"Person: {lm['person']}")
print(f"Organization: {lm['organization']}")
print(f"Date: {lm['date']}")
print(f"Location: {lm['location']}")