Langchain - Introduction

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

Introduction | 🦜️🔗 Langchain

 

 

 

LangChain is a framework for developing applications powered by language models. It enables applications that:

 

LangChain은 언어 모델을 기반으로 하는 애플리케이션을 개발하기 위한 프레임워크입니다. 이는 다음과 같은 애플리케이션을 가능하게 합니다.

 

• Are context-aware: connect a language model to sources of context (prompt instructions, few shot examples, content to ground its response in, etc.)
• 상황 인식: 언어 모델을 상황 소스( prompt instructions, few shot examples, content to ground its response in, etc. )에 연결합니다.
  
  
• Reason: rely on a language model to reason (about how to answer based on provided context, what actions to take, etc.)
• 이유: 추론하기 위해 언어 모델에 의존합니다(제공된 맥락에 따라 대답하는 방법, 취해야 할 조치 등에 대해).

 

The main value props of LangChain are:

 

LangChain의 주요 가치 제안은 다음과 같습니다:

 

1. Components: abstractions for working with language models, along with a collection of implementations for each abstraction. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
   
   구성요소: 각 추상화에 대한 구현 모음과 함께 언어 모델 작업을 위한 추상화입니다. LangChain 프레임워크의 나머지 부분을 사용하는지 여부에 관계없이 구성 요소는 모듈식이며 사용하기 쉽습니다.
   
   
2. Off-the-shelf chains: a structured assembly of components for accomplishing specific higher-level tasks
   
   기성품 체인: 특정 상위 수준 작업을 수행하기 위한 구성 요소의 구조화된 어셈블리

Off-the-shelf chains make it easy to get started. For complex applications, components make it easy to customize existing chains and build new ones.

 

기성품 체인을 사용하면 쉽게 시작할 수 있습니다. 복잡한 애플리케이션의 경우 구성요소를 사용하면 기존 체인을 쉽게 맞춤화하고 새 체인을 구축할 수 있습니다.

 

 

Get started​

Here’s how to install LangChain, set up your environment, and start building.

 

LangChain을 설치하고, 환경을 설정하고, 구축을 시작하는 방법은 다음과 같습니다.

 

We recommend following our Quickstart guide to familiarize yourself with the framework by building your first LangChain application.

 

첫 번째 LangChain 애플리케이션을 구축하여 프레임워크에 익숙해지려면 빠른 시작 가이드를 따르는 것이 좋습니다.

 

Note: These docs are for the LangChain Python package. For documentation on LangChain.js, the JS/TS version, head here.

 

참고: 이 문서는 LangChain Python 패키지용입니다. JS/TS 버전인 LangChain.js에 대한 문서를 보려면 여기를 방문하세요.

 

 

Modules​

LangChain provides standard, extendable interfaces and external integrations for the following modules, listed from least to most complex:

LangChain은 가장 덜 복잡한 것부터 가장 복잡한 것 순으로 나열된 다음 모듈에 대해 확장 가능한 표준 인터페이스와 외부 통합을 제공합니다.

Model I/O​

Interface with language models  언어 모델과의 인터페이스

Retrieval​

Interface with application-specific data 애플리케이션별 데이터와의 인터페이스

Chains​

Construct sequences of calls  호출 시퀀스 구성

Agents​

Let chains choose which tools to use given high-level directives

 

체인이 주어진 높은 수준의 지시문에 사용할 도구를 선택하도록 허용

Memory​

Persist application state between runs of a chain  체인 실행 간에 애플리케이션 상태 유지

Callbacks​

Log and stream intermediate steps of any chain  모든 체인의 중간 단계를 기록하고 스트리밍합니다.

 

 

Examples, ecosystem, and resources​

Use cases​

Walkthroughs and best-practices for common end-to-end use cases, like:

 

다음과 같은 일반적인 엔드투엔드 사용 사례에 대한 연습 및 모범 사례:

 

• Document question answering   문서 질의 응답
• Chatbots  챗봇
• Analyzing structured data  구조화된 데이터 분석
• and much more...

Guides​

Learn best practices for developing with LangChain.

 

LangChain 개발 모범 사례를 알아보세요.

 

Ecosystem​

LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of integrations and dependent repos.

 

LangChain은 우리의 프레임워크와 통합되고 그 위에 구축되는 풍부한 도구 생태계의 일부입니다. 점점 늘어나는 통합 및 종속 저장소 목록을 확인하세요.

 

Additional resources​

Our community is full of prolific developers, creative builders, and fantastic teachers. Check out YouTube tutorials for great tutorials from folks in the community, and Gallery for a list of awesome LangChain projects, compiled by the folks at KyroLabs.

 

우리 커뮤니티는 활발한 개발자, 창의적인 개발자, 환상적인 교사로 가득 차 있습니다. YouTube 튜토리얼에서 커뮤니티 사람들의 훌륭한 튜토리얼을 확인하고 갤러리에서 KyroLabs 사람들이 편집한 멋진 LangChain 프로젝트 목록을 확인하세요.

 

Community​

Head to the Community navigator to find places to ask questions, share feedback, meet other developers, and dream about the future of LLM’s.

 

커뮤니티 탐색기로 이동하여 질문하고, 피드백을 공유하고, 다른 개발자를 만나고, LLM의 미래에 대해 꿈꿀 수 있는 장소를 찾으세요.

 

API refer

Head to the reference section for full documentation of all classes and methods in the LangChain Python package.

 

LangChain Python 패키지의 모든 클래스와 메서드에 대한 전체 문서를 보려면 참조 섹션으로 이동하세요.