LangChain 装饰器集成

LangChain decorators 是 LangChain 顶层的⼀层，为编写自定义 langchain 提示词和链提供了语法糖 🍭 对于反馈、问题、贡献 - 请在此处提⻅问题： ju-bezdek/langchain-decorators

Disclaimer: `LangChain decorators` is not created by the LangChain team and is not supported by it.

LangChain decorators 是 LangChain 顶层的⼀层，为编写自定义 langchain 提示词和链提供了语法糖 🍭

对于反馈、问题、贡献 - 请在此处提⻅问题： ju-bezdek/langchain-decorators

主要原则和优势：

• 更pythonic的编写代码方式
• 编写多⾏提示词，不会因缩进而打断您的代码流
• 利用 IDE 内置的 提示、类型检查 和 带文档的弹窗 功能，快速查看函数以了解提示词、它消耗的参数等
• 挥洒所有 🦜🔗 LangChain 生态系统的力量
• 添加对 可选参数 的支持
• 通过将参数绑定到类来轻松在提示词之间共享参数

以下是使用 LangChain Decorators ✨ 编写的代码示例

@llm_prompt
def write_me_short_post(topic:str, platform:str="twitter", audience:str = "developers")->str:
    """
    Write me a short header for my post about {topic} for {platform} platform.
    It should be for {audience} audience.
    (Max 15 words)
    """
    return

# run it naturally
write_me_short_post(topic="starwars")
# or
write_me_short_post(topic="starwars", platform="redit")

快速入门

安装

pip install langchain_decorators

示例

如何开始的⽐较好的建议是查看这里的示例：

• jupyter notebook
• colab notebook

定义其他参数

这里我们只是使用 llm_prompt 装饰器将函数标记为提示词，将其有效地转换为 LLMChain。而不是运行它

标准 LLMchain 比仅仅输入变量和提示词需要更多的初始化参数… 这里是装饰器中隐藏的这种实现细节。 它的工作原理如下：

1. 使用 全局设置：

# define global settings for all prompty (if not set - chatGPT is the current default)
from langchain_decorators import GlobalSettings

GlobalSettings.define_settings(
    default_llm=ChatOpenAI(temperature=0.0), this is default... can change it here globally
    default_streaming_llm=ChatOpenAI(temperature=0.0,streaming=True), this is default... can change it here for all ... will be used for streaming
)

2. 使用预定义的 提示词类型

#You can change the default prompt types
from langchain_decorators import PromptTypes, PromptTypeSettings

PromptTypes.AGENT_REASONING.llm = ChatOpenAI()

# Or you can just define your own ones:
class MyCustomPromptTypes(PromptTypes):
    GPT4=PromptTypeSettings(llm=ChatOpenAI(model="gpt-4"))

@llm_prompt(prompt_type=MyCustomPromptTypes.GPT4)
def write_a_complicated_code(app_idea:str)->str:
    ...

3. 在装饰器中直接定义设置

from langchain_openai import OpenAI

@llm_prompt(
    llm=OpenAI(temperature=0.7),
    stop_tokens=["\nObservation"],
    ...
    )
def creative_writer(book_title:str)->str:
    ...

传递记忆和/或回调：

要传递任何这些，只需在函数中声明它们（或使用 kwargs 传递任何内容）

@llm_prompt()
async def write_me_short_post(topic:str, platform:str="twitter", memory:SimpleMemory = None):
    """
    {history_key}
    Write me a short header for my post about {topic} for {platform} platform.
    It should be for {audience} audience.
    (Max 15 words)
    """
    pass

await write_me_short_post(topic="old movies")

简化的流式输出

如果我们想利用流式输出：

• 我们需要将提示词定义为异步函数
• 在装饰器上打开流式输出，或者我们可以定义带有流式输出的 PromptType
• 使用 StreamingContext 捕获流

这种方式，我们只需标记哪些提示词应该被流式输出，无需担心我们应⽤ LLM，传递创建和分发流式处理程序到我们链的特定部分… 只需在提示词/提示词类型上打开/关闭流式输出…

只有当我们以流式输出上下文中调用它时，流式输出才会发生… 我们可以定义一个简单的函数来处理流

# this code example is complete and should run as it is

from langchain_decorators import StreamingContext, llm_prompt

# this will mark the prompt for streaming (useful if we want stream just some prompts in our app... but don't want to pass distribute the callback handlers)
# note that only async functions can be streamed (will get an error if it's not)
@llm_prompt(capture_stream=True)
async def write_me_short_post(topic:str, platform:str="twitter", audience:str = "developers"):
    """
    Write me a short header for my post about {topic} for {platform} platform.
    It should be for {audience} audience.
    (Max 15 words)
    """
    pass


# just an arbitrary  function to demonstrate the streaming... will be some websockets code in the real world
tokens=[]
def capture_stream_func(new_token:str):
    tokens.append(new_token)

# if we want to capture the stream, we need to wrap the execution into StreamingContext...
# this will allow us to capture the stream even if the prompt call is hidden inside higher level method
# only the prompts marked with capture_stream will be captured here
with StreamingContext(stream_to_stdout=True, callback=capture_stream_func):
    result = await run_prompt()
    print("Stream finished ... we can distinguish tokens thanks to alternating colors")


print("\nWe've captured",len(tokens),"tokens🎉\n")
print("Here is the result:")
print(result)

提示词声明

默认情况下，提示词是整个函数的文档，除非您标记您的提示词

文档化您的提示词

我们可以指定我们的文档中的哪一部分是提示词定义，通过指定带有 <prompt> 语言标签的代码块

@llm_prompt
def write_me_short_post(topic:str, platform:str="twitter", audience:str = "developers"):
    """
    Here is a good way to write a prompt as part of a function docstring, with additional documentation for devs.

    It needs to be a code block, marked as a `<prompt>` language
    ```<prompt>
    为我的关于 {topic} 的帖子写一个简短的标题，适用于 {platform} 平台。
    它应该是为 {audience} 受众准备的。
    （最多 15 个字）

Now only to code block above will be used as a prompt, and the rest of the docstring will be used as a description for developers. (It has also a nice benefit that IDE (like VS code) will display the prompt properly (not trying to parse it as markdown, and thus not showing new lines properly)) """ return

## 对话消息提示词

对于对话模型，将提示词定义为消息模板集非常有⽤... 下面是如何操作的：

``` python
@llm_prompt
def simulate_conversation(human_input:str, agent_role:str="a pirate"):
    """
    ## System message
     - note the `:system` suffix inside the <prompt:_role_> tag


    ```<prompt:system>
    您是一个 {agent_role} 黑客。您必须像⼀个黑客那样行动。
    您总是用代码回复，使用 python 或 javascript 代码块...
    例如：

    ... 不要回复任何其他内容... 只用代码 - 尊重您的角色。

human message

(we are using the real role that are enforced by the LLM - GPT supports system, assistant, user)

Helo，你是谁

a reply:

\``` python <<- 使用 \ 转义应作为提示词一部分的内部代码块
def hello():
    print("Argh... 你这个讨厌的海盗，你好")
\```

we can also add some history using placeholder

{history}

{human_input}

Now only to code block above will be used as a prompt, and the rest of the docstring will be used as a description for developers. (It has also a nice benefit that IDE (like VS code) will display the prompt properly (not trying to parse it as markdown, and thus not showing new lines properly)) """ pass

这里的角色是模型原生的角色（assistant、user、system 对于 chatGPT）

# 可选部分
- 您可以定义您的提示词的整个部分，该部分应该是可选的
- 如果该部分中的任何输入缺失，则整个部分将不会被渲染

这种语法如下：

``` python
@llm_prompt
def prompt_with_optional_partials():
    """
    this text will be rendered always, but

    {? anything inside this block will be rendered only if all the {value}s parameters are not empty (None | "")   ?}

    you can also place it in between the words
    this too will be rendered{? , but
        this  block will be rendered only if {this_value} and {this_value}
        is not empty?} !
    """

输出解析器

• llm_prompt 装饰器原生尝试根据输出类型检测最佳输出解析器。（如果未设置，则返回原始字符串）
• 列表、字典和 pydantic 输出也原生支持（自动）

# this code example is complete and should run as it is

from langchain_decorators import llm_prompt

@llm_prompt
def write_name_suggestions(company_business:str, count:int)->list:
    """ Write me {count} good name suggestions for company that {company_business}
    """
    pass

write_name_suggestions(company_business="sells cookies", count=5)

更复杂结构

对于字典 / pydantic，您需要指定格式说明… 这可能很繁琐，这就是为什么您可以让输出解析器根据模型（pydantic）为您生成说明

from langchain_decorators import llm_prompt
from pydantic import BaseModel, Field


class TheOutputStructureWeExpect(BaseModel):
    name:str = Field (description="The name of the company")
    headline:str = Field( description="The description of the company (for landing page)")
    employees:list[str] = Field(description="5-8 fake employee names with their positions")

@llm_prompt()
def fake_company_generator(company_business:str)->TheOutputStructureWeExpect:
    """ Generate a fake company that {company_business}
    {FORMAT_INSTRUCTIONS}
    """
    return

company = fake_company_generator(company_business="sells cookies")

# print the result nicely formatted
print("Company name: ",company.name)
print("company headline: ",company.headline)
print("company employees: ",company.employees)

将提示词绑定到对象

from pydantic import BaseModel
from langchain_decorators import llm_prompt

class AssistantPersonality(BaseModel):
    assistant_name:str
    assistant_role:str
    field:str

    @property
    def a_property(self):
        return "whatever"

    def hello_world(self, function_kwarg:str=None):
        """
        We can reference any {field} or {a_property} inside our prompt... and combine it with {function_kwarg} in the method
        """


    @llm_prompt
    def introduce_your_self(self)->str:
        """
        ``` <prompt:system>
        您是一个名为 {assistant_name} 的助手。
        您的角色是充当 {assistant_role}

介绍你自己（少于 20 个字）

"""

personality = AssistantPersonality(assistant_name=“John”, assistant_role=“a pirate”)

print(personality.introduce_your_self(personality))

# 更多示例：

- 这些和几个更多示例也可在 [colab notebook 这里](https://colab.research.google.com/drive/1no-8WfeP6JaLD9yUtkPgym6x0G9ZYZOG#scrollTo=N4cf__D0E2Yk) 中找到
- 包括使用纯 langchain 装饰器实现的 [ReAct Agent 重新实现](https://colab.research.google.com/drive/1no-8WfeP6JaLD9yUtkPgym6x0G9ZYZOG#scrollTo=3bID5fryE2Yp)

---

> 官方原文：[src/oss/python/integrations/providers/langchain_decorators.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/providers/langchain_decorators.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。