大纲
Outlines 是一个用于约束语言生成的Python库。它提供了对各种语言模型的统一接口,并允许使用正则表达式匹配、类型约束、JSON模式和上下文无关文法等技术进行结构化生成。
Outlines 支持多个后端,包括:
- Hugging Face Transformers
- llama.cpp
- vLLM
- MLX
此集成允许您将Outlines模型与LangChain一起使用,提供LLM和聊天模型接口。
安装与设置
要使用LangChain的Outlines,你需要安装Outlines库:
pip install outlines
根据您选择的后端,您可能需要安装额外的依赖项:
- 对于Transformers:
pip install transformers torch datasets
- 对于 llama.cpp:
pip install llama-cpp-python
- 对于vLLM:
pip install vllm
- 对于MLX:
pip install mlx
LLM
要在LangChain中使用Outlines作为LLM,你可以使用Outlines
类:
from langchain_community.llms import Outlines
聊天模型
要在LangChain中使用Outlines作为聊天模型,你可以使用ChatOutlines
类:
from langchain_community.chat_models import ChatOutlines
模型配置
无论是 Outlines
还是 ChatOutlines
类,它们都共享相似的配置选项:
model = Outlines(
model="meta-llama/Llama-2-7b-chat-hf", # Model identifier
backend="transformers", # Backend to use (transformers, llamacpp, vllm, or mlxlm)
max_tokens=256, # Maximum number of tokens to generate
stop=["\n"], # Optional list of stop strings
streaming=True, # Whether to stream the output
# Additional parameters for structured generation:
regex=None,
type_constraints=None,
json_schema=None,
grammar=None,
# Additional model parameters:
model_kwargs={"temperature": 0.7}
)
模型标识符
model
参数可以是:
- 一个 Hugging Face 模型名称(例如,"meta-llama/Llama-2-7b-chat-hf")
- 模型的本地路径
- 对于GGUF模型,格式为“repo_id/文件名”(例如,“TheBloke/Llama-2-7B-Chat-GGUF/llama-2-7b-chat.Q4_K_M.gguf”)
后端选项
backend
参数指定要使用的后端:
"transformers"
: 用于 Hugging Face Transformers 模型(默认)"llamacpp"
: 用于使用 llama.cpp 的 GGUF 模型"transformers_vision"
: 用于视觉语言模型(例如,LLaVA)"vllm"
: 用于使用vLLM库的模型"mlxlm"
: 用于使用MLX框架的模型
结构化生成
大纲提供了几种用于结构化生成的方法:
-
Regex Matching:
model = Outlines(
model="meta-llama/Llama-2-7b-chat-hf",
regex=r"((25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)"
)This will ensure the generated text matches the specified regex pattern (in this case, a valid IP address).
-
Type Constraints:
model = Outlines(
model="meta-llama/Llama-2-7b-chat-hf",
type_constraints=int
)This restricts the output to valid Python types (int, float, bool, datetime.date, datetime.time, datetime.datetime).
-
JSON Schema:
from pydantic import BaseModel
class Person(BaseModel):
name: str
age: int
model = Outlines(
model="meta-llama/Llama-2-7b-chat-hf",
json_schema=Person
)This ensures the generated output adheres to the specified JSON schema or Pydantic model.
-
Context-Free Grammar:
model = Outlines(
model="meta-llama/Llama-2-7b-chat-hf",
grammar="""
?start: expression
?expression: term (("+" | "-") term)*
?term: factor (("*" | "/") factor)*
?factor: NUMBER | "-" factor | "(" expression ")"
%import common.NUMBER
"""
)This generates text that adheres to the specified context-free grammar in EBNF format.
使用示例
LLM 示例
from langchain_community.llms import Outlines
llm = Outlines(model="meta-llama/Llama-2-7b-chat-hf", max_tokens=100)
result = llm.invoke("Tell me a short story about a robot.")
print(result)
聊天模型示例
from langchain_community.chat_models import ChatOutlines
from langchain_core.messages import HumanMessage, SystemMessage
chat = ChatOutlines(model="meta-llama/Llama-2-7b-chat-hf", max_tokens=100)
messages = [
SystemMessage(content="You are a helpful AI assistant."),
HumanMessage(content="What's the capital of France?")
]
result = chat.invoke(messages)
print(result.content)
流式处理示例
from langchain_community.chat_models import ChatOutlines
from langchain_core.messages import HumanMessage
chat = ChatOutlines(model="meta-llama/Llama-2-7b-chat-hf", streaming=True)
for chunk in chat.stream("Tell me a joke about programming."):
print(chunk.content, end="", flush=True)
print()
结构化输出示例
from langchain_community.llms import Outlines
from pydantic import BaseModel
class MovieReview(BaseModel):
title: str
rating: int
summary: str
llm = Outlines(
model="meta-llama/Llama-2-7b-chat-hf",
json_schema=MovieReview
)
result = llm.invoke("Write a short review for the movie 'Inception'.")
print(result)
附加功能
分词器访问
您可以访问模型的底层分词器:
tokenizer = llm.tokenizer
encoded = tokenizer.encode("Hello, world!")
decoded = tokenizer.decode(encoded)