LangChain - Quickstart

https://python.langchain.com/docs/get_started/quickstart

Quickstart | 🦜️🔗 Langchain

 

 

Installation​

To install LangChain run:

 

pip install langchain

 

For more details, see our Installation guide. 자세한 내용은 설치 가이드를 참조하세요.

 

 

Environment setup​

Using LangChain will usually require integrations with one or more model providers, data stores, APIs, etc. For this example, we'll use OpenAI's model APIs.

 

LangChain을 사용하려면 일반적으로 하나 이상의 모델 공급자, 데이터 저장소, API 등과의 통합이 필요합니다. 이 예에서는 OpenAI의 모델 API를 사용합니다.

 

First we'll need to install their Python package:

 

먼저 Python 패키지를 설치해야 합니다.

 

pip install openai

 

Accessing the API requires an API key, which you can get by creating an account and heading here. Once we have a key we'll want to set it as an environment variable by running:

 

API에 액세스하려면 API 키가 필요합니다. API 키는 계정을 생성하고 여기에서 얻을 수 있습니다. 키가 있으면 다음을 실행하여 이를 환경 변수로 설정하려고 합니다.

 

export OPENAI_API_KEY="..."

 

If you'd prefer not to set an environment variable you can pass the key in directly via the openai_api_key named parameter when initiating the OpenAI LLM class:

 

환경 변수를 설정하지 않으려는 경우 OpenAI LLM 클래스를 시작할 때 openai_api_key라는 매개변수를 통해 직접 키를 전달할 수 있습니다.

 

from langchain.llms import OpenAI

llm = OpenAI(openai_api_key="...")

 

나는 아래 방법 이용함.

 

 

Building an application

Now we can start building our language model application. LangChain provides many modules that can be used to build language model applications. Modules can be used as stand-alones in simple applications and they can be combined for more complex use cases.

 

이제 언어 모델 애플리케이션 구축을 시작할 수 있습니다. LangChain은 언어 모델 애플리케이션을 구축하는 데 사용할 수 있는 많은 모듈을 제공합니다. 모듈은 간단한 애플리케이션에서 독립 실행형으로 사용할 수 있으며 더 복잡한 사용 사례에서는 결합할 수 있습니다.

 

The most common and most important chain that LangChain helps create contains three things:

 

LangChain이 생성하는 데 도움이 되는 가장 일반적이고 가장 중요한 체인에는 다음 세 가지가 포함됩니다.

 

• LLM: The language model is the core reasoning engine here. In order to work with LangChain, you need to understand the different types of language models and how to work with them.
• LLM: 언어 모델은 여기서 핵심 추론 엔진입니다. LangChain을 사용하려면 다양한 유형의 언어 모델과 이를 사용하는 방법을 이해해야 합니다.
• Prompt Templates: This provides instructions to the language model. This controls what the language model outputs, so understanding how to construct prompts and different prompting strategies is crucial.
• 프롬프트 템플릿: 언어 모델에 대한 지침을 제공합니다. 이는 언어 모델의 출력을 제어하므로 프롬프트와 다양한 프롬프트 전략을 구성하는 방법을 이해하는 것이 중요합니다.
• Output Parsers: These translate the raw response from the LLM to a more workable format, making it easy to use the output downstream.
• 출력 파서: LLM의 원시 응답을 보다 실행 가능한 형식으로 변환하여 출력 다운스트림을 쉽게 사용할 수 있도록 합니다.

In this getting started guide we will cover those three components by themselves, and then go over how to combine all of them. Understanding these concepts will set you up well for being able to use and customize LangChain applications. Most LangChain applications allow you to configure the LLM and/or the prompt used, so knowing how to take advantage of this will be a big enabler.

 

이 시작 가이드에서는 이 세 가지 구성 요소를 단독으로 다룬 다음 이 모든 구성 요소를 결합하는 방법을 살펴보겠습니다. 이러한 개념을 이해하면 LangChain 애플리케이션을 사용하고 사용자 정의하는 데 도움이 됩니다. 대부분의 LangChain 애플리케이션에서는 LLM 및/또는 사용되는 프롬프트를 구성할 수 있으므로 이를 활용하는 방법을 아는 것이 큰 도움이 될 것입니다.

 

LLMs

There are two types of language models, which in LangChain are called:

 

LangChain에는 두 가지 유형의 언어 모델이 있습니다.

 

• LLMs: this is a language model which takes a string as input and returns a string
• LLM: 문자열을 입력으로 받아 문자열을 반환하는 언어 모델입니다.
• ChatModels: this is a language model which takes a list of messages as input and returns a message
• ChatModels: 메시지 목록을 입력으로 받아 메시지를 반환하는 언어 모델입니다.

The input/output for LLMs is simple and easy to understand - a string. But what about ChatModels? The input there is a list of ChatMessages, and the output is a single ChatMessage. A ChatMessage has two required components:

 

LLM의 입력/출력은 간단하고 이해하기 쉽습니다. 즉, 문자열입니다. 하지만 ChatModel은 어떻습니까? 입력에는 ChatMessage 목록이 있고 출력은 단일 ChatMessage입니다. ChatMessage에는 두 가지 필수 구성 요소가 있습니다.

 

• content: This is the content of the message  메시지의 내용입니다..
• role: This is the role of the entity from which the ChatMessage is coming from. ChatMessage가 나오는 엔터티의 역할입니다.

LangChain provides several objects to easily distinguish between different roles:

 

LangChain은 서로 다른 역할을 쉽게 구별할 수 있는 여러 개체를 제공합니다.

 

• HumanMessage: A ChatMessage coming from a human/user.
• AIMessage: A ChatMessage coming from an AI/assistant.
• SystemMessage: A ChatMessage coming from the system.
• FunctionMessage: A ChatMessage coming from a function call.

If none of those roles sound right, there is also a ChatMessage class where you can specify the role manually. For more information on how to use these different messages most effectively, see our prompting guide.

 

이러한 역할 중 어느 것도 적절하지 않은 경우 역할을 수동으로 지정할 수 있는 ChatMessage 클래스도 있습니다. 이러한 다양한 메시지를 가장 효과적으로 사용하는 방법에 대한 자세한 내용은 메시지 안내 가이드를 참조하세요.

 

LangChain provides a standard interface for both, but it's useful to understand this difference in order to construct prompts for a given language model. The standard interface that LangChain provides has two methods:

 

LangChain은 두 가지 모두에 대한 표준 인터페이스를 제공하지만 주어진 언어 모델에 대한 프롬프트를 구성하려면 이러한 차이점을 이해하는 것이 유용합니다. LangChain이 제공하는 표준 인터페이스에는 두 가지 방법이 있습니다.

 

• predict: Takes in a string, returns a string  문자열을 받아 문자열을 반환합니다.
• predict_messages: Takes in a list of messages, returns a message.  메시지 목록을 가져와 메시지를 반환합니다.

Let's see how to work with these different types of models and these different types of inputs. First, let's import an LLM and a ChatModel.

 

이러한 다양한 유형의 모델과 다양한 유형의 입력을 사용하여 작업하는 방법을 살펴보겠습니다. 먼저 LLM과 ChatModel을 가져오겠습니다.

 

from langchain.llms import OpenAI
from langchain.chat_models import ChatOpenAI

llm = OpenAI()
chat_model = ChatOpenAI()

llm.predict("hi!")
>>> "Hi"

chat_model.predict("hi!")
>>> "Hi"

 

 

Note) 아래와 같은 에러메시지가 나오면 Langchain을 최신 버전으로 업그레이드 합니다.

pip install langchain --upgrade

 

The OpenAI and ChatOpenAI objects are basically just configuration objects. You can initialize them with parameters like temperature and others, and pass them around.

 

OpenAI 및 ChatOpenAI 개체는 기본적으로 구성 개체입니다. temperature  및 기타 매개변수로 초기화하고 전달할 수 있습니다.

 

Next, let's use the predict method to run over a string input.

 

다음으로 예측 메서드를 사용하여 문자열 입력을 실행해 보겠습니다.

 

text = "What would be a good company name for a company that makes colorful socks?"

llm.predict(text)
# >> Feetful of Fun

chat_model.predict(text)
# >> Socks O'Color

Finally, let's use the predict_messages method to run over a list of messages.

 

마지막으로 Predict_messages 메서드를 사용하여 메시지 목록을 살펴보겠습니다.

 

from langchain.schema import HumanMessage

text = "What would be a good company name for a company that makes colorful socks?"
messages = [HumanMessage(content=text)]

llm.predict_messages(messages)
# >> Feetful of Fun

chat_model.predict_messages(messages)
# >> Socks O'Color

For both these methods, you can also pass in parameters as keyword arguments. For example, you could pass in temperature=0 to adjust the temperature that is used from what the object was configured with. Whatever values are passed in during run time will always override what the object was configured with.

 

두 가지 방법 모두 매개변수를 키워드 인수로 전달할 수도 있습니다. 예를 들어, 온도=0을 전달하여 객체 구성에 사용되는 온도를 조정할 수 있습니다. 런타임 중에 전달되는 값은 항상 개체 구성을 재정의합니다.

 

Prompt templates

 

Most LLM applications do not pass user input directly into an LLM. Usually they will add the user input to a larger piece of text, called a prompt template, that provides additional context on the specific task at hand.

 

대부분의 LLM 응용 프로그램은 사용자 입력을 LLM에 직접 전달하지 않습니다. 일반적으로 그들은 현재 특정 작업에 대한 추가 컨텍스트를 제공하는 프롬프트 템플릿이라는 더 큰 텍스트에 사용자 입력을 추가합니다.

 

In the previous example, the text we passed to the model contained instructions to generate a company name. For our application, it'd be great if the user only had to provide the description of a company/product, without having to worry about giving the model instructions.

 

이전 예에서 모델에 전달한 텍스트에는 회사 이름을 생성하는 지침이 포함되어 있습니다. 우리 애플리케이션의 경우 사용자가 모델 지침을 제공하는 것에 대해 걱정할 필요 없이 회사/제품에 대한 설명만 제공하면 좋을 것입니다.

 

PromptTemplates help with exactly this! They bundle up all the logic for going from user input into a fully formatted prompt. This can start off very simple - for example, a prompt to produce the above string would just be:

 

PromptTemplate이 바로 이 작업에 도움이 됩니다! 사용자 입력을 완전히 형식화된 프롬프트로 전환하기 위한 모든 논리를 묶습니다. 이는 매우 간단하게 시작할 수 있습니다. 예를 들어 위 문자열을 생성하라는 프롬프트는 다음과 같습니다.

 

from langchain.prompts import PromptTemplate

prompt = PromptTemplate.from_template("What is a good name for a company that makes {product}?")
prompt.format(product="colorful socks")

What is a good name for a company that makes colorful socks?

However, the advantages of using these over raw string formatting are several. You can "partial" out variables - e.g. you can format only some of the variables at a time. You can compose them together, easily combining different templates into a single prompt. For explanations of these functionalities, see the section on prompts for more detail.

 

그러나 원시 문자열 형식화에 비해 이를 사용하면 여러 가지 장점이 있습니다. 변수를 "부분적으로" 출력할 수 있습니다. 한 번에 일부 변수만 형식화할 수 있습니다. 다양한 템플릿을 하나의 프롬프트로 쉽게 결합하여 함께 구성할 수 있습니다. 이러한 기능에 대한 설명은 프롬프트 섹션을 참조하세요.

 

PromptTemplates can also be used to produce a list of messages. In this case, the prompt not only contains information about the content, but also each message (its role, its position in the list, etc) Here, what happens most often is a ChatPromptTemplate is a list of ChatMessageTemplates. Each ChatMessageTemplate contains instructions for how to format that ChatMessage - its role, and then also its content. Let's take a look at this below:

 

PromptTemplate을 사용하여 메시지 목록을 생성할 수도 있습니다. 이 경우 프롬프트에는 콘텐츠에 대한 정보뿐만 아니라 각 메시지(해당 역할, 목록에서의 위치 등)도 포함됩니다. 여기서 가장 자주 발생하는 것은 ChatPromptTemplate이 ChatMessageTemplate의 목록이라는 것입니다. 각 ChatMessageTemplate에는 해당 ChatMessage(해당 역할 및 콘텐츠)의 형식을 지정하는 방법에 대한 지침이 포함되어 있습니다. 아래에서 이에 대해 살펴보겠습니다.

 

from langchain.prompts.chat import ChatPromptTemplate

template = "You are a helpful assistant that translates {input_language} to {output_language}."
human_template = "{text}"

chat_prompt = ChatPromptTemplate.from_messages([
    ("system", template),
    ("human", human_template),
])

chat_prompt.format_messages(input_language="English", output_language="French", text="I love programming.")

 

[
    SystemMessage(content="You are a helpful assistant that translates English to French.", additional_kwargs={}),
    HumanMessage(content="I love programming.")
]

 

Output parsers

OutputParsers convert the raw output of an LLM into a format that can be used downstream. There are few main type of OutputParsers, including:

 

OutputParser는 LLM의 원시 출력을 다운스트림에서 사용할 수 있는 형식으로 변환합니다. 다음을 포함하여 몇 가지 주요 유형의 OutputParser가 있습니다.

 

• Convert text from LLM -> structured information (e.g. JSON)
• LLM에서 텍스트 변환 -> 구조화된 정보(예: JSON)
• Convert a ChatMessage into just a string
• ChatMessage를 문자열로 변환
• Convert the extra information returned from a call besides the message (like OpenAI function invocation) into a string.
• 메시지(예: OpenAI 함수 호출) 외에 호출에서 반환된 추가 정보를 문자열로 변환합니다.

For full information on this, see the section on output parsers

Output parsers | 🦜️🔗 Langchain

이에 대한 자세한 내용은 section on output parsers 을 참조하세요.

 

In this getting started guide, we will write our own output parser - one that converts a comma separated list into a list.

 

이 시작 가이드에서는 쉼표로 구분된 목록을 목록으로 변환하는 자체 출력 구문 분석기를 작성합니다.

 

from langchain.schema import BaseOutputParser

class CommaSeparatedListOutputParser(BaseOutputParser):
    """Parse the output of an LLM call to a comma-separated list."""


    def parse(self, text: str):
        """Parse the output of an LLM call."""
        return text.strip().split(", ")

CommaSeparatedListOutputParser().parse("hi, bye")
# >> ['hi', 'bye']

PromptTemplate + LLM + OutputParser

 

We can now combine all these into one chain. This chain will take input variables, pass those to a prompt template to create a prompt, pass the prompt to a language model, and then pass the output through an (optional) output parser. This is a convenient way to bundle up a modular piece of logic. Let's see it in action!

 

이제 이 모든 것을 하나의 체인으로 결합할 수 있습니다. 이 체인은 입력 변수를 가져와 프롬프트 템플릿에 전달하여 프롬프트를 생성하고, 프롬프트를 언어 모델에 전달한 다음 (선택 사항) 출력 구문 분석기를 통해 출력을 전달합니다. 이는 모듈식 로직 조각을 묶는 편리한 방법입니다. 실제로 확인해 봅시다!

 

from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import ChatPromptTemplate
from langchain.schema import BaseOutputParser

class CommaSeparatedListOutputParser(BaseOutputParser):
    """Parse the output of an LLM call to a comma-separated list."""


    def parse(self, text: str):
        """Parse the output of an LLM call."""
        return text.strip().split(", ")

template = """You are a helpful assistant who generates comma separated lists.
A user will pass in a category, and you should generate 5 objects in that category in a comma separated list.
ONLY return a comma separated list, and nothing more."""
human_template = "{text}"

chat_prompt = ChatPromptTemplate.from_messages([
    ("system", template),
    ("human", human_template),
])
chain = chat_prompt | ChatOpenAI() | CommaSeparatedListOutputParser()
chain.invoke({"text": "colors"})
# >> ['red', 'blue', 'green', 'yellow', 'orange']

Note that we are using the | syntax to join these components together. This | syntax is called the LangChain Expression Language. To learn more about this syntax, read the documentation here.

 

우리는 | 이러한 구성 요소를 함께 결합하는 구문입니다. 이 | 구문을 LangChain 표현 언어라고 합니다. 이 구문에 대해 자세히 알아보려면 여기에서 설명서를 읽어보세요.

 

Next steps​

This is it! We've now gone over how to create the core building block of LangChain applications. There is a lot more nuance in all these components (LLMs, prompts, output parsers) and a lot more different components to learn about as well. To continue on your journey:

 

여기까지 입니다! 이제 우리는 LangChain 애플리케이션의 핵심 빌딩 블록을 생성하는 방법을 살펴보았습니다. 이러한 모든 구성 요소(LLM, 프롬프트, 출력 구문 분석기)에는 훨씬 더 많은 미묘한 차이가 있으며, 배워야 할 구성 요소도 훨씬 더 많습니다. 여행을 계속하려면:

 

• Dive deeper into LLMs, prompts, and output parsers
• LLM, 프롬프트 및 출력 파서에 대해 자세히 알아보세요.
• Learn the other key components  다른 주요 구성 요소 알아보기
• Read up on LangChain Expression Language to learn how to chain these components together
• 이러한 구성 요소를 함께 연결하는 방법을 알아보려면 LangChain Expression Language를 읽어보세요.
• Check out our helpful guides for detailed walkthroughs on particular topics
• 특정 주제에 대한 자세한 설명을 보려면 유용한 가이드를 확인하세요.
• Explore end-to-end use cases  엔드투엔드 사용 사례 살펴보기

Retrieval-augmented generation (RAG) | 🦜️🔗 Langchain