Skip to main content
Open In ColabOpen on GitHub

大纲

这将帮助您开始使用 Outlines 大型语言模型。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。它允许您在使用大型语言模型（LLMs）时应用各种后端并对生成的输出施加约束。

概览​

集成详情​

类包本地可序列化的JS 支持软件包下载最新包裹
Outlineslangchain-community✅beta❌PyPI - DownloadsPyPI - Version

设置​

要访问Outlines模型，您需要有互联网连接以从huggingface下载模型权重。根据后端的不同，您需要安装所需的依赖项（参见Outlines文档）。

凭据​

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.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 参考：大纲

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 参考：PromptTemplate

流式传输​

Outlines 支持令牌流式传输：

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

约束生成​

Outlines 允许你对生成的输出应用各种约束：

正则约束​

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ChatOutlines所有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

文档大纲：​

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