38 lines
1.5 KiB
Markdown
38 lines
1.5 KiB
Markdown
---
|
||
title: "LangChain"
|
||
type: entity
|
||
tags: [llm, framework, rag, document-loading]
|
||
sources: ["RAG从入门到精通系列1：基础RAG"]
|
||
last_updated: 2026-04-16
|
||
---
|
||
|
||
## Basic Information
|
||
- **Type**: LLM Application Framework
|
||
- **Source**: RAG从入门到精通系列1：基础RAG
|
||
|
||
## Definition
|
||
LangChain is a framework for building LLM applications, providing over 160 different document loaders for loading data from various sources, as well as components for building RAG pipelines.
|
||
|
||
## Key Features
|
||
- **Document Loaders**: 160+ loaders for various data sources
|
||
- **Chain Abstraction**: Link retrieval and generation components together
|
||
- **Retriever Interface**: Unified abstraction for retrieval components
|
||
- **PromptTemplate**: Template system for constructing prompts
|
||
- **Integration**: Works with various LLMs (Qwen, GPT-4, Claude, etc.) and vector databases (Qdrant, Chroma, Pinecone, etc.)
|
||
|
||
## Applications in RAG
|
||
- Loading external documents via document loaders
|
||
- Splitting documents into chunks (Splits)
|
||
- Creating retrievers from vector stores
|
||
- Chaining retrieval and generation into a unified pipeline
|
||
- Converting raw AIMessage outputs to clean string results
|
||
|
||
## Related Concepts
|
||
- [[RAG]]：LangChain is commonly used to build RAG pipelines
|
||
- [[LlamaIndex]]：Alternative framework for building LLM applications
|
||
- [[向量数据库]]：Vector stores integrated with LangChain
|
||
- [[Qdrant]]：Vector database mentioned in RAG tutorials
|
||
|
||
## Related Entities
|
||
- [[Qwen]]：LLM often used with LangChain
|