Integrating AI Chatbots into Your Business: A Practical Guide

// Traditional rule-based approach
if (intent === "check_order_status") {
    if (hasOrderNumber) {
        return lookupOrder(orderNumber);
    } else {
        return "Please provide your order number.";
    }
} else if (intent === "return_item") {
    // Another rigid branch...
} else {
    return "I'm sorry, I don't understand. Please contact support.";
}

// Problems:
// - Can't handle variations in phrasing
// - No context awareness between turns
// - Requires manual rule creation for every scenario
// - Fails ungracefully on unexpected inputs

█Œ─────────────────────────────────────────────────────────────────────┐
│                         RAG Pipeline                                 │
└─────────────────────────────────────────────────────────────────────█˜

1. INDEXING (Offline, one-time setup)
   █Œ──────────────┐     █Œ──────────────┐     █Œ──────────────┐
   │   Documents  │────█¶│   Chunking   │────█¶│  Embedding   │
   │  (PDFs, docs,│     │  (Split into │     │  (Convert to │
   │   wikis)     │     │   passages)  │     │   vectors)   │
   └──────────────█˜     └──────────────█˜     └──────█¬───────█˜
                                                    │
                                                    ۬
                                            █Œ──────────────┐
                                            │   Vector DB  │
                                            │  (Pinecone,  │
                                            │   Weaviate)  │
                                            └──────────────█˜

2. RETRIEVAL + GENERATION (Runtime, per query)
   █Œ──────────────┐     █Œ──────────────┐     █Œ──────────────┐
   │  User Query  │────█¶│   Embed      │────█¶│   Vector     │
   │  "What's our │     │   Query      │     │   Search     │
   │   refund     │     │              │     │   (Top K)    │
   │   policy?"   │     └──────────────█˜     └──────█¬───────█˜
   └──────────────█˜                                 │
                                                    │ Retrieved passages
                                                    ۬
                                            █Œ──────────────┐
                                            │   LLM with   │
                                            │   Context    │
                                            │              │
                                            │ "Based on    │
                                            │  the refund  │
                                            │  policy doc, │
                                            │  customers   │
                                            │  can..."     │
                                            └──────────────█˜

from langchain.document_loaders import DirectoryLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Pinecone
from langchain.chat_models import ChatOpenAI
from langchain.chains import RetrievalQA

# Step 1: Load and chunk documents
loader = DirectoryLoader('./knowledge_base/', glob="**/*.pdf")
documents = loader.load()

text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    separators=["\n\n", "\n", " ", ""]
)
chunks = text_splitter.split_documents(documents)

# Step 2: Create embeddings and store in vector DB
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
vectorstore = Pinecone.from_documents(
    chunks, 
    embeddings, 
    index_name="company-knowledge"
)

# Step 3: Create retrieval chain
llm = ChatOpenAI(model="gpt-4-turbo", temperature=0)
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever(search_kwargs={"k": 5}),
    return_source_documents=True
)

# Step 4: Query
response = qa_chain.invoke({
    "query": "What is our refund policy for enterprise customers?"
})
print(response["result"])
print("Sources:", [doc.metadata for doc in response["source_documents"]])