Skip to main content
Open In ColabOpen on GitHub

大纲

这将帮助您开始使用Outlines LLM。有关所有Outlines功能和配置的详细文档，请前往API参考。

Outlines 是一个用于约束语言生成的库。它允许你在使用大型语言模型（LLMs）和各种后端的同时，对生成的输出应用约束。

概述​

集成详情​

类包本地可序列化JS支持包下载包最新
Outlineslangchain-community✅测试版❌PyPI - 下载量PyPI - 版本

设置​

要访问Outlines模型，您需要有一个互联网连接以从huggingface下载模型权重。根据您使用的后端，您需要安装所需的依赖项（请参阅Outlines文档）

凭证​

Outlines 没有内置的认证机制。

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完成：

from langchain_community.llms import Outlines

# For use with llamacpp backend
model = Outlines(model="microsoft/Phi-3-mini-4k-instruct", backend="llamacpp")

# For use with vllm backend (not available on Mac)
model = Outlines(model="microsoft/Phi-3-mini-4k-instruct", backend="vllm")

# For use with mlxlm backend (only available on Mac)
model = Outlines(model="microsoft/Phi-3-mini-4k-instruct", backend="mlxlm")

# For use with huggingface transformers backend
model = Outlines(
    model="microsoft/Phi-3-mini-4k-instruct"
)  # defaults to backend="transformers"
API Reference:Outlines

调用​

model.invoke("Hello how are you?")

链式调用​

from langchain_core.prompts import PromptTemplate

prompt = PromptTemplate.from_template("How to say {input} in {output_language}:\n")

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

流处理​

Outlines 支持令牌的流式传输：

for chunk in model.stream("Count to 10 in French:"):
    print(chunk, end="", flush=True)

受限生成​

大纲允许您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

类型约束​

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

JSON 模式​

from pydantic import BaseModel


class Person(BaseModel):
    name: str


model.json_schema = Person
response = model.invoke("Who is the author of LangChain?")
person = Person.model_validate_json(response)

person

语法约束​

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

API 参考​

有关所有ChatOutlines功能和配置的详细文档，请访问API参考：https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.outlines.ChatOutlines.html

大纲文档:​

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

这个页面有帮助吗？