Xây Dựng RAG Pipeline Với LangChain Trong 30 Phút

mkdir rag-pipeline && cd rag-pipeline
npm init -y
npm install langchain @langchain/openai @langchain/community chromadb

import { DirectoryLoader } from "langchain/document_loaders/fs/directory";
import { PDFLoader } from "langchain/document_loaders/fs/pdf";
 
const loader = new DirectoryLoader("./docs", {
  ".pdf": (path) => new PDFLoader(path),
  ".txt": (path) => new TextLoader(path),
});
 
const docs = await loader.load();

import { RecursiveCharacterTextSplitter } from "langchain/text_splitter";
 
const splitter = new RecursiveCharacterTextSplitter({
  chunkSize: 1000,
  chunkOverlap: 200,
});
 
const chunks = await splitter.splitDocuments(docs);

import { OpenAIEmbeddings } from "@langchain/openai";
import { Chroma } from "@langchain/community/vectorstores/chroma";
 
const vectorStore = await Chroma.fromDocuments(
  chunks,
  new OpenAIEmbeddings(),
  { collectionName: "my-docs" }
);

import { ChatOpenAI } from "@langchain/openai";
import { RetrievalQAChain } from "langchain/chains";
 
const model = new ChatOpenAI({ modelName: "gpt-4o" });
const chain = RetrievalQAChain.fromLLM(model, vectorStore.asRetriever());
 
const result = await chain.call({
  query: "Chính sách hoàn tiền là gì?"
});