Welcome to ZSC Online Marketing Agency

Innovative digital solutions designed to elevate your brand in a competitive market.

Get Started

About Us

At ZSC, we are a full-service digital agency dedicated to crafting digital experiences that elevate your brand. Our team of experts in marketing, design, and development blend creativity with technology to deliver exceptional results.

Why Choose Us?

Our Services

Digital Marketing

Boost your online presence with targeted campaigns, SEO, and social media management.

Graphic Designing

Create stunning visuals and brand identities with our expert design services.

Video Editing

Engage your audience with professionally crafted video content and creative editing.

Pricing Plans

Beginner

$100/month

Essential features to kickstart your marketing efforts.

Start Now

Professional

$250/month

Advanced tools for growing businesses and boosting productivity.

Start Now

Expert

$450/month

Comprehensive solutions with cutting-edge features and support.

Contact Us

Our Portfolio

Portfolio Project 1
Project 1 Description
Portfolio Project 2
Project 2 Description
Portfolio Project 3
Project 3 Description

What Our Clients Say

"ZSC transformed our social media presence. Their creative strategies and stunning visuals helped our brand stand out."

– Ahmed Raza

"Working with ZSC was a game-changer. Their innovative approach and attention to detail exceeded our expectations."

– Sana Malik

"Their expertise in digital marketing and design truly makes a difference. I highly recommend ZSC for any business."

– Ali Khan
Skip to Content

About us

WhatsApp Button WhatsApp ```python #!/usr/bin/env python3 import os from dotenv import load_dotenv from bs4 import BeautifulSoup import requests import pinecone from openai import OpenAI from langchain.embeddings.openai import OpenAIEmbeddings from langchain.vectorstores import Pinecone import smtplib from email.mime.text import MIMEText from email.mime.multipart import MIMEMultipart # Load env vars load_dotenv() OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") PINECONE_API_KEY = os.getenv("PINECONE_API_KEY") PINECONE_ENV = os.getenv("PINECONE_ENV") SMTP_HOST = os.getenv("EMAIL_HOST") SMTP_PORT = int(os.getenv("EMAIL_PORT", 587)) SMTP_USER = os.getenv("EMAIL_USER") SMTP_PASS = os.getenv("EMAIL_PASS") WEBSITE_URLS = os.getenv("WEBSITE_URLS", "").split(",") # comma-separated URLs # Initialize Pinecone & OpenAI pinecone.init(api_key=PINECONE_API_KEY, environment=PINECONE_ENV) index_name = "website-index" if index_name not in pinecone.list_indexes(): pinecone.create_index(index_name, dimension=1536, metric="cosine") index = pinecone.Index(index_name) vectorstore = Pinecone(index, OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY), text_key="text") openai_client = OpenAI(api_key=OPENAI_API_KEY) # 1. Scrape & index (run once) def scrape_index(): docs = [] for url in WEBSITE_URLS: r = requests.get(url) soup = BeautifulSoup(r.text, "html.parser") text = "\n".join(p.get_text() for p in soup.find_all("p")) docs.append({"text": text, "metadata": {"source": url}}) vectorstore.add_documents(docs) # 2. Retrieve def retrieve(question, k=5): results = vectorstore.similarity_search(question, k=k) return "\n---\n".join(f"Source: {d.metadata['source']}\n{d.page_content}" for d in results) # 3. Query LLM def ask_gpt(prompt, model="gpt-4"): resp = openai_client.chat.completions.create( model=model, messages=[{"role":"user","content":prompt}] ) return resp.choices[0].message.content.strip() # 4. Merge answers def merge(a, b): prompt = f"Combine the key points into a concise reply:\nAnswer1:\n{a}\n---\nAnswer2:\n{b}" return ask_gpt(prompt) # 5. Send email def send_email(to, subject, body): msg = MIMEMultipart() msg['From'] = SMTP_USER msg['To'] = to msg['Subject'] = subject msg.attach(MIMEText(body, 'html')) with smtplib.SMTP(SMTP_HOST, SMTP_PORT) as server: server.starttls() server.login(SMTP_USER, SMTP_PASS) server.send_message(msg) # Main CLI flow def main(): if os.getenv("INDEXED") != "1": print("Indexing website...") scrape_index() os.environ["INDEXED"] = "1" question = input("Enter your question: ") email = input("Enter your email: ") ctx = retrieve(question) ans1 = ask_gpt(f"Context:\n{ctx}\nQuestion: {question}") ans2 = ask_gpt(f"Alternate context:\n{ctx}\nQuestion: {question}") final = merge(ans1, ans2) print("Final Answer:\n", final) send_email(email, "Your Answer", final) if __name__ == '__main__': main() ``` --- Below is the **front-end widget** code you can embed in your website. Place the HTML, CSS and JS in your site files, and adjust the `fetch` URL to point to your deployed backend's `/ask` endpoint. ```html
Chatbot
``` ```css /* chatbot_widget.css */ #chatbot-icon { position: fixed; bottom: 20px; right: 20px; cursor: pointer; } #chatbot-window { position: fixed; bottom: 80px; right: 20px; width: 300px; max-height: 400px; background: white; border: 1px solid #ccc; border-radius: 8px; box-shadow: 0 2px 10px rgba(0,0,0,0.1); display: flex; flex-direction: column; } #chatbot-window.hidden { display: none; } #chatbot-header { padding: 10px; background: #007bff; color: white; display: flex; justify-content: space-between; align-items: center; border-top-left-radius: 8px; border-top-right-radius: 8px; } #chatbot-messages { flex: 1; padding: 10px; overflow-y: auto; } #chatbot-input { border: none; border-top: 1px solid #eee; padding: 10px; } .user { text-align: right; margin: 5px; background: #e1ffc7; padding: 5px; border-radius: 4px; } .bot { text-align: left; margin: 5px; background: #f1f0f0; padding: 5px; border-radius: 4px; } ```