MarketMitra-AI
What I Built MarketMitra-AI is a social media post generator for small businesses—such as local shops, food businesses, and independent service providers—that need promotional content but may not have time or budget for a copywriter. Enter a business and product description, price, target audience, preferred platform, language, tone, and optional call to action. The app generates a caption, short…
MarketMitra-AI is a social media post generator specifically designed for small businesses like local shops, food establishments, and independent service providers. These businesses often require promotional content but may struggle with time constraints or budget limitations to hire a professional copywriter. To address this need, the MarketMitra-AI app allows users to input their business and product details, target audience, preferred platform, language, tone, and optional call to action.
Upon entering this information, the app generates a caption, short description, hashtags, a call to action, and a WhatsApp message. Currently, the app supports Instagram, Facebook, and WhatsApp, with output available in English, Hindi, and Hinglish. The MarketMitra-AI project is designed to run locally, meaning it does not send users' business information to a remote AI API. Instead, it sends prompts to an Ollama model that runs on the user's own computer.
The app's functionality is built on a Flask backend that serves the interface, validates requests, communicates with the Ollama model, and returns the generated content. The frontend of the app is constructed using HTML, CSS, and JavaScript. The Ollama model used in this project is Llama 3.2 3B, which is accessed via the Ollama platform.
To demonstrate the app's capabilities, a demo mode is available for users to try the interface without relying on the Ollama model. This demo mode can be accessed by visiting http://127.0.0.1:5000. To run the app, users must first install the project dependencies and Ollama. After pulling the Llama 3.2 3B model using the command ollama pull llama3.2:3b, they can start the app by running python app.py. The app can then be accessed through a web browser at http://127.0.0.1:5000.
The code for the MarketMitra-AI project is available on GitHub at https://github.com/anubhav9236/MarketMitra-AI.git. The current README file still contains a placeholder for the user's GitHub username, and there is no indication that a Git remote has been configured for this repository.
The development of MarketMitra-AI highlights the benefits of open innovation in creating AI-powered tools. By running the model locally, users can keep their business details on their own machine, ensuring privacy and allowing for easier inspection and adaptation of the model. However, it is important to note that the project does not claim that every component or model adheres to an OSI-approved open-source license.
Users should verify the licenses of all relevant models and dependencies to ensure compliance with their intended use.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
