Local Seller AI: An AI-Powered Marketing Copilot for Small Businesses

Description and use

Local Seller AI is a web app that consolidates marketing content generation, pricing calculation, and a 7‑day planner for small businesses, leveraging open‑weight Hugging Face models.

Problem

Small sellers lack time and budget for marketing tasks such as writing product descriptions, social media captions, WhatsApp promos, and SEO keywords.

Outcome

The app delivers 27 automated tests that passed, indicating functional reliability for content generation, pricing, and planning features.

Workflow

• 1. User enters product details or selects sample content in Demo Mode.
• 2. App generates product descriptions, social media captions, WhatsApp promo messages, and SEO keywords in English, Hindi, or Hinglish using Hugging Face InferenceClient with Qwen2.5 or Llama 3.2 models.
• 3. User reviews and edits the generated content.
• 4. Pricing calculator computes suggested prices based on input parameters.
• 5. 7‑day marketing planner schedules posts and promotional activities.
• 6. User exports or copies the content for use on platforms.

Evidence

I built Local Seller AI using Python and Streamlit to create a simple, interactive web application.

Source

For AI-powered content generation, I integrated Hugging Face's InferenceClient with open-weight language models, including Qwen2.5 and Llama 3.2.

Source

I wrote automated tests for the main features and error-handling scenarios. All 27 automated tests passed.

Source

The app generates product descriptions, social media captions, WhatsApp promotional messages, and SEO keywords in English, Hindi, and Hinglish.

Source