大纲
这将帮助您快速开始使用 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。它允许您使用各种后端的大规模语言模型（LLMs），并在生成的输出中应用约束。
概览
集成细节
| Class | 包 | 本地 | 序列化 | JS支持 | Package downloads | Package 最新版本 |
|---|---|---|---|---|---|---|
| Outlines | langchain-community | ✅ | beta | ❌ |  |  |
设置
要访问 Outlines 模型，您需要连接互联网以从 huggingface 下载模型权重。根据所需的后端，请安装相应的依赖项（请参见Outlines 文档）
Credentials
没有内置身份验证机制用于Outlines。
安装
The LangChain Outlines集成存在于langchain-community包中，并需要outlines库:
%pip install -qU langchain-community outlines
Instantiation
现在我们就可以实例化我们的模型对象并生成聊天完成内容:
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
Invocation
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:提示模板
流式传输
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)
约束生成
Outlines 允许您对生成的输出应用各种约束条件：
Regex Constraint
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
Type Constraints
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
详细文档包含了所有ChatOutlines功能和配置，请参阅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/