RAG Explained: How to Make AI Remember Your Documents

// Without RAG:
User: "What's our refund policy?"
AI: "I don't have that information." (or worse, makes something up)

// With RAG:
User: "What's our refund policy?"
System: [searches documents] → [finds refund-policy.pdf]
AI: "Based on your policy document, refunds are available within
     30 days of purchase for unused products..." (accurate!)

// Split documents into chunks
import { RecursiveCharacterTextSplitter } from 'langchain/text_splitter';

const splitter = new RecursiveCharacterTextSplitter({
  chunkSize: 1000,     // Characters per chunk
  chunkOverlap: 200,   // Overlap between chunks
  separators: ['\n\n', '\n', '. ', ' '] // Split priorities
});

const chunks = await splitter.splitDocuments(documents);

// Generate embeddings using OpenAI
import { OpenAIEmbeddings } from '@langchain/openai';

const embeddings = new OpenAIEmbeddings({
  model: 'text-embedding-3-large',
});

// Each chunk becomes a 3072-dimensional vector
const vectors = await embeddings.embedDocuments(
  chunks.map(c => c.pageContent)
);

// Store in Pinecone (or Qdrant, Weaviate, Chroma, etc.)
import { PineconeStore } from '@langchain/pinecone';

const vectorStore = await PineconeStore.fromDocuments(
  chunks,
  embeddings,
  {
    pineconeIndex: index,
    namespace: 'company-docs',
  }
);

// Find relevant chunks for a question
const relevantDocs = await vectorStore.similaritySearch(
  "What is the refund policy?",
  4  // Return top 4 most relevant chunks
);

// Send the question + relevant context to the LLM
const response = await llm.invoke([
  {
    role: "system",
    content: `Answer the user's question based ONLY on the
    provided context. If the context doesn't contain the answer,
    say "I don't have that information."

    Context:
    ${relevantDocs.map(d => d.pageContent).join('\n\n')}`
  },
  {
    role: "user",
    content: "What is the refund policy?"
  }
]);