guidance

指南：受约束的大模型生成

何时使用此技能

在以下情况下使用 Guidance：

• 通过正则表达式或语法控制大模型输出语法
• 确保生成有效的 JSON/XML/代码
• 与传统提示词方法相比降低延迟
• 强制采用结构化格式（日期、电子邮件、ID 等）
• 使用 Python 风格的控制流构建多步骤工作流
• 通过语法约束防止无效输出

GitHub Stars：18,000+ | 来自：Microsoft Research

安装

# Base installation
pip install guidance

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

快速入门

基本示例：结构化生成

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"

使用 Anthropic Claude

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

# Configure Claude
lm = models.Anthropic("claude-sonnet-4-5-20250929")

# 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)

核心概念

1. 上下文管理器

Guidance 使用 Python 风格的上下文管理器进行聊天式交互。

from guidance import system, user, assistant, gen

lm = models.Anthropic("claude-sonnet-4-5-20250929")

# 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"])

优点：

• 自然的聊天流程
• 清晰的角色区分
• 易于阅读和维护

2. 受约束的生成

Guidance 使用正则表达式或语法确保输出符合指定模式。

正则表达式约束

from guidance import models, gen

lm = models.Anthropic("claude-sonnet-4-5-20250929")

# 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

工作原理：

• 将正则表达式转换为 token 级别的语法
• 在生成过程中筛除无效 token
• 模型只能生成符合模式的输出

选项约束

from guidance import models, gen, select

lm = models.Anthropic("claude-sonnet-4-5-20250929")

# 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

3. Token 修复

Guidance 会自动“修复”提示词与生成内容之间的 token 边界。

**问题：**分词会产生不自然的边界。

# 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!)

**解决方案：**Guidance 回退一个 token 并重新生成。

from guidance import models, gen

lm = models.Anthropic("claude-sonnet-4-5-20250929")

# 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)

优点：

• 自然的文本边界
• 没有别扭的空格问题
• 模型性能更好（能看到自然的 token 序列）

4. 基于语法的生成

使用上下文无关语法定义复杂结构。

from guidance import models, gen

lm = models.Anthropic("claude-sonnet-4-5-20250929")

# JSON grammar (simplified)
json_grammar = """
{
    "name": <gen name regex="[A-Za-z ]+" max_tokens=20>,
    "age": <gen age regex="[0-9]+" max_tokens=3>,
    "email": <gen email regex="[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}" max_tokens=50>
}
"""

# Generate valid JSON
lm += gen("person", grammar=json_grammar)

print(lm["person"])  # Guaranteed valid JSON structure

使用场景：

• 复杂的结构化输出
• 嵌套数据结构
• 编程语言语法
• 特定领域语言

5. Guidance 函数

使用 @guidance 装饰器创建可复用的生成模式。

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.Anthropic("claude-sonnet-4-5-20250929")
lm = generate_person(lm)

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

有状态函数：

@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

后端配置

Anthropic Claude

from guidance import models

lm = models.Anthropic(
    model="claude-sonnet-4-5-20250929",
    api_key="your-api-key"  # Or set ANTHROPIC_API_KEY env var
)

OpenAI

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

本地模型（Transformers）

from guidance.models import Transformers

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

本地模型（llama.cpp）

from guidance.models import LlamaCpp

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

常见模式

模式 1：JSON 生成

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

lm = models.Anthropic("claude-sonnet-4-5-20250929")

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

模式 2：分类

from guidance import models, gen, select

lm = models.Anthropic("claude-sonnet-4-5-20250929")

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']}%")

模式 3：多步骤推理

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.Anthropic("claude-sonnet-4-5-20250929")
lm = chain_of_thought(lm, "What is 15% of 200?")

print(lm["answer"])

模式 4：ReAct Agent

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.Anthropic("claude-sonnet-4-5-20250929")
lm = react_agent(lm, "What is 25 * 4 + 10?")
print(lm["answer"])

模式 5：数据提取

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.Anthropic("claude-sonnet-4-5-20250929")
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']}")

最佳实践

1. 使用正则表达式验证格式

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

# ❌ Bad: Free generation may produce invalid emails
lm += "Email: " + gen("email", max_tokens=50)

2. 对固定类别使用 select()

# ✅ Good: Guaranteed valid category
lm += "Status: " + select(["pending", "approved", "rejected"], name="status")

# ❌ Bad: May generate typos or invalid values
lm += "Status: " + gen("status", max_tokens=20)

3. 利用 Token 修复

# Token healing is enabled by default
# No special action needed - just concatenate naturally
lm += "The capital is " + gen("capital")  # Automatic healing

4. 使用 stop 序列

# ✅ Good: Stop at newline for single-line outputs
lm += "Name: " + gen("name", stop="\n")

# ❌ Bad: May generate multiple lines
lm += "Name: " + gen("name", max_tokens=50)

5. 创建可复用函数

# ✅ Good: Reusable pattern
@guidance
def generate_person(lm):
    lm += "Name: " + gen("name", stop="\n")
    lm += "\nAge: " + gen("age", regex=r"[0-9]+")
    return lm

# Use multiple times
lm = generate_person(lm)
lm += "\n\n"
lm = generate_person(lm)

6. 平衡约束

# ✅ Good: Reasonable constraints
lm += gen("name", regex=r"[A-Za-z ]+", max_tokens=30)

# ❌ Too strict: May fail or be very slow
lm += gen("name", regex=r"^(John|Jane)$", max_tokens=10)

与其他方案的比较

特性	Guidance	Instructor	Outlines	LMQL
正则表达式约束	✅ 是	❌ 否	✅ 是	✅ 是
语法支持	✅ CFG	❌ 否	✅ CFG	✅ CFG
Pydantic 验证	❌ 否	✅ 是	✅ 是	❌ 否
Token 修复	✅ 是	❌ 否	✅ 是	❌ 否
本地模型	✅ 是	⚠️ 有限	✅ 是	✅ 是
API 模型	✅ 是	✅ 是	⚠️ 有限	✅ 是
Python 风格语法	✅ 是	✅ 是	✅ 是	❌ 类 SQL
学习曲线	低	低	中	高

选择 Guidance 的情况：

• 需要正则表达式/语法约束
• 希望使用 token 修复
• 通过控制流构建复杂工作流
• 使用本地模型（Transformers、llama.cpp）
• 偏好 Python 风格语法

选择其他方案的情况：

• Instructor：需要 Pydantic 验证和自动重试
• Outlines：需要 JSON Schema 验证
• LMQL：偏好声明式查询语法

性能特征

延迟降低：

• 对于受约束的输出，速度比传统提示词方式快 30-50%
• Token 修复可减少不必要的重新生成
• 语法约束可防止生成无效 Token

内存使用：

• 相比不受约束的生成，仅有极少额外开销
• 语法编译后会缓存，供后续使用
• 推理时可高效筛选 Token

Token 效率：

• 防止为无效输出浪费 Token
• 无需重试循环
• 直接生成有效输出

资源

• 文档：https://guidance.readthedocs.io
• GitHub：https://github.com/guidance-ai/guidance（18k+ stars）
• Notebook：https://github.com/guidance-ai/guidance/tree/main/notebooks
• Discord：可获取社区支持

另请参阅

• references/constraints.md - 全面的正则表达式和语法模式
• references/backends.md - 特定后端的配置
• references/examples.md - 可用于生产环境的示例