User question
    │
    ▼
[Embed question] ──► [Vector DB search] ──► Top 5 relevant KB chunks
                                                       │
                                                       ▼
                                          [Claude/GPT with context]
                                                       │
                                                       ▼
                                          Answer + citations → User
                                                       │
                       [Unanswered? → Escalate to human]

import requests
from bs4 import BeautifulSoup

def scrape_kb_article(url):
    html = requests.get(url).text
    soup = BeautifulSoup(html, 'html.parser')
    title = soup.select_one('h1').text.strip()
    body = soup.select_one('article').text.strip()
    return {'title': title, 'url': url, 'body': body}

# For DomainIndia KB:
articles = []
for slug_url in get_all_kb_urls():
    articles.append(scrape_kb_article(slug_url))

from langchain.text_splitter import RecursiveCharacterTextSplitter
from openai import OpenAI
import psycopg2

client = OpenAI()
splitter = RecursiveCharacterTextSplitter(chunk_size=800, chunk_overlap=100)
conn = psycopg2.connect("dbname=chatbot")
cur = conn.cursor()

for article in articles:
    chunks = splitter.split_text(article['body'])
    # Batch embed
    embeddings = client.embeddings.create(
        model='text-embedding-3-small',
        input=chunks,
    ).data

    for i, (chunk, emb) in enumerate(zip(chunks, embeddings)):
        cur.execute("""
            INSERT INTO kb_chunks (article_url, article_title, chunk_index, content, embedding)
            VALUES (%s, %s, %s, %s, %s)
        """, (article['url'], article['title'], i, chunk, emb.embedding))

conn.commit()

CREATE EXTENSION IF NOT EXISTS vector;

CREATE TABLE kb_chunks (
    id            bigserial PRIMARY KEY,
    article_url   text NOT NULL,
    article_title text NOT NULL,
    chunk_index   int,
    content       text NOT NULL,
    embedding     vector(1536),
    created_at    timestamptz DEFAULT now()
);

CREATE INDEX ON kb_chunks USING hnsw (embedding vector_cosine_ops);

import anthropic

claude = anthropic.Anthropic()

def answer(question, conversation_history=[]):
    # 1. Embed the question
    q_vec = client.embeddings.create(
        model='text-embedding-3-small',
        input=question,
    ).data[0].embedding

    # 2. Retrieve top 5 chunks
    cur.execute("""
        SELECT article_title, article_url, content,
               1 - (embedding <=> %s::vector) AS similarity
        FROM kb_chunks
        ORDER BY embedding <=> %s::vector
        LIMIT 5
    """, (q_vec, q_vec))
    chunks = cur.fetchall()

    # 3. Build context
    context = "

---

".join([
        f"## {title} ({url})
{content}"
        for title, url, content, _ in chunks
    ])

    # 4. Call Claude with strict grounding prompt
    system = """You are a helpful customer support assistant for DomainIndia.
Answer ONLY from the provided knowledge base context below.
If the context doesn't cover the question, say "I don't have information about that in our knowledge base — let me connect you with our team."
Always cite the article URL you used in format [source: URL].
Be concise — 2-3 paragraphs max."""

    user_msg = f"Context:
{context}

Question: {question}"

    resp = claude.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=500,
        system=system,
        messages=conversation_history + [{"role": "user", "content": user_msg}],
    )

    return {
        "answer": resp.content[0].text,
        "sources": [{"title": t, "url": u} for t, u, _, _ in chunks[:3]],
    }

history = []
while True:
    q = input("You: ")
    result = answer(q, history)
    print("Bot:", result['answer'])
    history.append({"role": "user", "content": q})
    history.append({"role": "assistant", "content": result['answer']})
    # Trim if too long (Claude has 1M tokens but cost scales)
    if len(history) > 20: history = history[-20:]

HANDOFF_TRIGGERS = [
    'talk to human', 'agent please', 'real person', 'not helpful'
]

def should_handoff(question, result):
    if any(t in question.lower() for t in HANDOFF_TRIGGERS): return True
    if result.get('top_similarity', 1) < 0.4: return True
    if "I don't have information" in result['answer']: return True
    return False

if should_handoff(question, result):
    # Create ticket in your system
    create_support_ticket(user_id, question, history)
    return "I've escalated this to our support team — they'll reach you at your email within 30 minutes."

<div id="chat-widget" style="position:fixed; bottom:20px; right:20px; width:350px;">
  <div id="chat-header" style="background:#0f172a; color:white; padding:10px; border-radius:8px 8px 0 0;">
    Support Assistant
  </div>
  <div id="chat-messages" style="height:400px; overflow-y:auto; border:1px solid #ccc; padding:10px;"></div>
  <input id="chat-input" placeholder="Ask a question..." style="width:100%; padding:10px; border:1px solid #ccc;">
</div>

<script>
  const sessionId = crypto.randomUUID();
  const input = document.getElementById('chat-input');
  const messages = document.getElementById('chat-messages');

  input.addEventListener('keypress', async (e) => {
    if (e.key !== 'Enter') return;
    const q = input.value;
    input.value = '';
    append('user', q);

    const resp = await fetch('/api/chat', {
      method: 'POST',
      headers: {'Content-Type': 'application/json'},
      body: JSON.stringify({ sessionId, question: q }),
    });
    const { answer, sources } = await resp.json();
    append('bot', answer, sources);
  });

  function append(who, text, sources = []) {
    const div = document.createElement('div');
    div.innerHTML = `<b>${who}:</b> ${text}`;
    if (sources.length) {
      div.innerHTML += '<br><small>Sources: ' +
        sources.map(s => `<a href="${s.url}" target="_blank">${s.title}</a>`).join(', ') +
        '</small>';
    }
    messages.appendChild(div);
    messages.scrollTop = messages.scrollHeight;
  }
</script>

# Cron: nightly 3 AM
0 3 * * * python3 /opt/chatbot/reindex.py