⚡ SellSpark AI: Building a Local AI Product Listing Generator with Qwen 2.5

Description and use

SellSpark AI is a local AI-powered product listing generator that uses Qwen 2.5 and Ollama. Users input product details, choose style and platform, and the app generates titles, descriptions, key points, captions, and hashtags without external APIs.

Problem

Small online sellers struggle to create attractive product descriptions, engaging social media captions, and effective marketing content manually, and hiring copywriters or paid AI services is expensive.

Outcome

SellSpark AI successfully generated product titles, descriptions, key selling points, Instagram captions, and hashtags for a sample product (Lavender Bliss Candle) using a locally running Qwen 2.5 model, eliminating external API costs and enhancing privacy.

Workflow

• 1. Install Ollama and pull Qwen 2.5 (1.5B) model locally.
• 2. Build a Streamlit interface for product input, style, and platform selection.
• 3. Connect Streamlit to Ollama via its local REST API.
• 4. Construct a structured prompt from user input and send to Qwen.
• 5. Receive generated content (title, description, selling points, caption, hashtags).
• 6. Provide copy‑friendly output and option to download as text file.
• 7. Handle AI connection status, errors, and prompt refinement for quality.
• 8. Verify generated content before publishing.

Evidence

SellSpark AI transforms basic product information into ready-to-review marketing content using a locally running open-weight AI model.

Source

The application runs locally, with Ollama handling AI inference.

Source

I tested SellSpark AI using a sample product: Lavender Bliss Candle… SellSpark AI successfully generated: An attractive product title, A professional product description, Key product features, An Instagram marketing caption, Relevant hashtags.

Source