ChatOutlines

该指南将帮助您开始使用 Outlines chat models。如需获取 ChatOutlines 所有功能和配置的详细文档，请访问 API reference。

Outlines 是一个用于受限语言生成的库。它允许您使用各种后端的大型语言模型（LLMs），同时对生成的输出应用约束。

概览

集成详情

Class	Package	Local	Serializable	JS support	Package downloads	Package latest
ChatOutlines	langchain-community	✅	❌	❌

模型特性

Tool calling	Structured output	JSON mode	Image input	Audio input	Video input	Token-level streaming	Native async	Token usage	Logprobs
✅	✅	✅	✅	❌	❌	✅	❌	❌	❌

设置

要访问 Outlines 模型，您需要有互联网连接以下载模型权重从 huggingface。根据不同的后端，您需要安装所需的依赖项（请参阅 Outlines docs）。

凭证

Outlines 没有内置的身份验证机制。

安装

LangChain Outlines 集成位于 langchain-community 包中，并且需要 outlines 库：

%pip install -qU langchain-community outlines

实例化

现在我们可以实例化我们的模型对象并生成聊天补全：

from langchain_community.chat_models.outlines import ChatOutlines

# For llamacpp backend
model = ChatOutlines(model="TheBloke/phi-2-GGUF/phi-2.Q4_K_M.gguf", backend="llamacpp")

# For vllm backend (not available on Mac)
model = ChatOutlines(model="meta-llama/Llama-3.2-1B", backend="vllm")

# For mlxlm backend (only available on Mac)
model = ChatOutlines(model="mistralai/Ministral-8B-Instruct-2410", backend="mlxlm")

# For huggingface transformers backend
model = ChatOutlines(model="microsoft/phi-2")  # defaults to transformers backend

API Reference:ChatOutlines

调用

from langchain_core.messages import HumanMessage

messages = [HumanMessage(content="What will the capital of mars be called?")]
response = model.invoke(messages)

response.content

API Reference:HumanMessage

流式传输

ChatOutlines 支持向外流式传输 token：

messages = [HumanMessage(content="Count to 10 in French:")]

for chunk in model.stream(messages):
    print(chunk.content, end="", flush=True)

链式调用

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a helpful assistant that translates {input_language} to {output_language}.",
        ),
        ("human", "{input}"),
    ]
)

chain = prompt | model
chain.invoke(
    {
        "input_language": "English",
        "output_language": "German",
        "input": "I love programming.",
    }
)

API Reference:ChatPromptTemplate

受约束的生成

ChatOutlines 允许你对生成的输出应用各种约束：

正则表达式约束

model.regex = r"((25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)"

response = model.invoke("What is the IP address of Google's DNS server?")

response.content

类型约束

model.type_constraints = int
response = model.invoke("What is the answer to life, the universe, and everything?")

response.content

Pydantic 和 JSON Schemas

from pydantic import BaseModel


class Person(BaseModel):
    name: str


model.json_schema = Person
response = model.invoke("Who are the main contributors to LangChain?")
person = Person.model_validate_json(response.content)

person

上下文无关文法

model.grammar = """
?start: expression
?expression: term (("+" | "-") term)*
?term: factor (("*" | "/") factor)*
?factor: NUMBER | "-" factor | "(" expression ")"
%import common.NUMBER
%import common.WS
%ignore WS
"""
response = model.invoke("Give me a complex arithmetic expression:")

response.content

LangChain 的结构化输出

你也可以将 LangChain 的结构化输出与 ChatOutlines 结合使用：

from pydantic import BaseModel


class AnswerWithJustification(BaseModel):
    answer: str
    justification: str


_model = model.with_structured_output(AnswerWithJustification)
result = _model.invoke("What weighs more, a pound of bricks or a pound of feathers?")

result

API 参考

如需了解 ChatOutlines 所有功能和配置的详细文档，请前往 API 参考：https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.outlines.ChatOutlines.html

Outlines 全套文档：

https://dottxt-ai.github.io/outlines/latest/

Related

• Chat model conceptual guide
• Chat model how-to guides