outlines:基于 Python 类型系统的大语言模型结构化输出项目

import outlines
from enum import Enum
from pydantic import BaseModel
from transformers import AutoTokenizer, AutoModelForCausalLM
from typing import List


MODEL_NAME = "microsoft/Phi-3-mini-4k-instruct"
model = outlines.from_transformers(
    AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto"),
    AutoTokenizer.from_pretrained(MODEL_NAME)
)


def alert_manager(ticket):
    print("Alert!", ticket)


class TicketPriority(str, Enum):
    low = "low"
    medium = "medium"
    high = "high"
    urgent = "urgent"

class ServiceTicket(BaseModel):
    priority: TicketPriority
    category: str
    requires_manager: bool
    summary: str
    action_items: List[str]


customer_email = """
Subject: URGENT - Cannot access my account after payment

I paid for the premium plan 3 hours ago and still can't access any features.
I've tried logging out and back in multiple times. This is unacceptable as I
have a client presentation in an hour and need the analytics dashboard.
Please fix this immediately or refund my payment.
"""

prompt = f"""
<|im_start|>user
Analyze this customer email:

{customer_email}
<|im_end|>
<|im_start|>assistant
"""

ticket = model(
    prompt,
    ServiceTicket,
    max_new_tokens=500
)

# Use structured data to route the ticket
ticket = ServiceTicket.model_validate_json(ticket)
if ticket.priority == "urgent" or ticket.requires_manager:
    alert_manager(ticket)

import outlines
from pydantic import BaseModel
from transformers import AutoTokenizer, AutoModelForCausalLM
from typing import List, Optional


MODEL_NAME = "microsoft/Phi-3-mini-4k-instruct"
model = outlines.from_transformers(
    AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto"),
    AutoTokenizer.from_pretrained(MODEL_NAME)
)


def update_inventory(product, category, sub_category):
    print(f"Updated {product.split(',')[0]} in category {category}/{sub_category}")


class ProductCategory(BaseModel):
    main_category: str
    sub_category: str
    attributes: List[str]
    brand_match: Optional[str]

# Process product descriptions in batches
product_descriptions = [
    "Apple iPhone 15 Pro Max 256GB Titanium, 6.7-inch Super Retina XDR display with ProMotion",
    "Organic Cotton T-Shirt, Men's Medium, Navy Blue, 100% Sustainable Materials",
    "KitchenAid Stand Mixer, 5 Quart, Red, 10-Speed Settings with Dough Hook Attachment"
]

template = outlines.Template.from_string("""
<|im_start|>user
Categorize this product:

{{ description }}
<|im_end|>
<|im_start|>assistant
""")

# Get structured categorization for all products
categories = model(
    [template(description=desc) for desc in product_descriptions],
    ProductCategory,
    max_new_tokens=200
)

# Use categorization for inventory management
categories = [
    ProductCategory.model_validate_json(category) for category in categories
]
for product, category in zip(product_descriptions, categories):
    update_inventory(product, category.main_category, category.sub_category)

import outlines
from typing import Union, List, Literal
from pydantic import BaseModel
from enum import Enum
from transformers import AutoTokenizer, AutoModelForCausalLM


MODEL_NAME = "microsoft/Phi-3-mini-4k-instruct"
model = outlines.from_transformers(
    AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto"),
    AutoTokenizer.from_pretrained(MODEL_NAME)
)

class EventType(str, Enum):
    conference = "conference"
    webinar = "webinar"
    workshop = "workshop"
    meetup = "meetup"
    other = "other"


class EventInfo(BaseModel):
    """Structured information about a tech event"""
    name: str
    date: str
    location: str
    event_type: EventType
    topics: List[str]
    registration_required: bool

# Create a union type that can either be a structured EventInfo or "I don't know"
EventResponse = Union[EventInfo, Literal["I don't know"]]

# Sample event descriptions
event_descriptions = [
    # Complete information
    """
    Join us for DevCon 2023, the premier developer conference happening on November 15-17, 2023
    at the San Francisco Convention Center. Topics include AI/ML, cloud infrastructure, and web3.
    Registration is required.
    """,

    # Insufficient information
    """
    Tech event next week. More details coming soon!
    """
]

# Process events
results = []
for description in event_descriptions:
    prompt = f"""
<|im_start>system
You are a helpful assistant
<|im_end|>
<|im_start>user
Extract structured information about this tech event:

{description}

If there is enough information, return a JSON object with the following fields:

- name: The name of the event
- date: The date where the event is taking place
- location: Where the event is taking place
- event_type: either 'conference', 'webinar', 'workshop', 'meetup' or 'other'
- topics: a list of topics of the conference
- registration_required: a boolean that indicates whether registration is required

If the information available does not allow you to fill this JSON, and only then, answer 'I don't know'.
<|im_end|>
<|im_start|>assistant
"""
    # Union type allows the model to return structured data or "I don't know"
    result = model(prompt, EventResponse, max_new_tokens=200)
    results.append(result)

# Display results
for i, result in enumerate(results):
    print(f"Event {i+1}:")
    if isinstance(result, str):
        print(f"  {result}")
    else:
        # It's an EventInfo object
        print(f"  Name: {result.name}")
        print(f"  Type: {result.event_type}")
        print(f"  Date: {result.date}")
        print(f"  Topics: {', '.join(result.topics)}")
    print()

# Use structured data in downstream processing
structured_count = sum(1 for r in results if isinstance(r, EventInfo))
print(f"Successfully extracted data for {structured_count} of {len(results)} events")

import outlines
from typing import Literal, List
import pandas as pd
from transformers import AutoTokenizer, AutoModelForCausalLM


MODEL_NAME = "microsoft/Phi-3-mini-4k-instruct"
model = outlines.from_transformers(
    AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto"),
    AutoTokenizer.from_pretrained(MODEL_NAME)
)


# Define classification categories using Literal
DocumentCategory = Literal[
    "Financial Report",
    "Legal Contract",
    "Technical Documentation",
    "Marketing Material",
    "Personal Correspondence"
]

# Sample documents to classify
documents = [
    "Q3 Financial Summary: Revenue increased by 15% year-over-year to $12.4M. EBITDA margin improved to 23% compared to 19% in Q3 last year. Operating expenses...",

    "This agreement is made between Party A and Party B, hereinafter referred to as 'the Parties', on this day of...",

    "The API accepts POST requests with JSON payloads. Required parameters include 'user_id' and 'transaction_type'. The endpoint returns a 200 status code on success."
]

template = outlines.Template.from_string("""
<|im_start|>user
Classify the following document into exactly one category among the following categories:
- Financial Report
- Legal Contract
- Technical Documentation
- Marketing Material
- Personal Correspondence

Document:
{{ document }}
<|im_end|>
<|im_start|>assistant
""")

# Classify documents
def classify_documents(texts: List[str]) -> List[DocumentCategory]:
    results = []

    for text in texts:
        prompt = template(document=text)
        # The model must return one of the predefined categories
        category = model(prompt, DocumentCategory, max_new_tokens=200)
        results.append(category)

    return results

# Perform classification
classifications = classify_documents(documents)

# Create a simple results table
results_df = pd.DataFrame({
    "Document": [doc[:50] + "..." for doc in documents],
    "Classification": classifications
})

print(results_df)

# Count documents by category
category_counts = pd.Series(classifications).value_counts()
print("\nCategory Distribution:")
print(category_counts)

import outlines
import json
from typing import List, Optional
from datetime import date
from transformers import AutoTokenizer, AutoModelForCausalLM


MODEL_NAME = "microsoft/phi-4"
model = outlines.from_transformers(
    AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto"),
    AutoTokenizer.from_pretrained(MODEL_NAME)
)


# Define a function with typed parameters
def schedule_meeting(
    title: str,
    date: date,
    duration_minutes: int,
    attendees: List[str],
    location: Optional[str] = None,
    agenda_items: Optional[List[str]] = None
):
    """Schedule a meeting with the specified details"""
    # In a real app, this would create the meeting
    meeting = {
        "title": title,
        "date": date,
        "duration_minutes": duration_minutes,
        "attendees": attendees,
        "location": location,
        "agenda_items": agenda_items
    }
    return f"Meeting '{title}' scheduled for {date} with {len(attendees)} attendees"

# Natural language request
user_request = """
I need to set up a product roadmap review with the engineering team for next
Tuesday at 2pm. It should last 90 minutes. Please invite john@example.com,
sarah@example.com, and the product team at product@example.com.
"""

# Outlines automatically infers the required structure from the function signature
prompt = f"""
<|im_start|>user
Extract the meeting details from this request:

{user_request}
<|im_end|>
<|im_start|>assistant
"""
meeting_params = model(prompt, schedule_meeting, max_new_tokens=200)

# The result is a dictionary matching the function parameters
meeting_params = json.loads(meeting_params)
print(meeting_params)

# Call the function with the extracted parameters
result = schedule_meeting(**meeting_params)
print(result)
# "Meeting 'Product Roadmap Review' scheduled for 2023-10-17 with 3 attendees"

import outlines
from typing import List, Literal
from transformers import AutoTokenizer, AutoModelForCausalLM


MODEL_NAME = "microsoft/phi-4"
model = outlines.from_transformers(
    AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto"),
    AutoTokenizer.from_pretrained(MODEL_NAME)
)


# 1. Create a reusable template with Jinja syntax
sentiment_template = outlines.Template.from_string("""
<|im_start>user
Analyze the sentiment of the following {{ content_type }}:

{{ text }}

Provide your analysis as either "Positive", "Negative", or "Neutral".
<|im_end>
<|im_start>assistant
""")

# 2. Generate prompts with different parameters
review = "This restaurant exceeded all my expectations. Fantastic service!"
prompt = sentiment_template(content_type="review", text=review)

# 3. Use the templated prompt with structured generation
result = model(prompt, Literal["Positive", "Negative", "Neutral"])
print(result)  # "Positive"

# Templates can also be loaded from files
example_template = outlines.Template.from_file("templates/few_shot.txt")

# Use with examples for few-shot learning
examples = [
    ("The food was cold", "Negative"),
    ("The staff was friendly", "Positive")
]
few_shot_prompt = example_template(examples=examples, query="Service was slow")
print(few_shot_prompt)