In the evolving digital landscape, Large Language Models (LLMs) are rapidly gaining popularity, with a myriad of tech companies actively deploying AI-powered bots. This growing trend inspired me to embark on an exciting venture: the creation of my own personal GPT bot. Leveraging open-source models such as llama2 and mistral-7b, I've successfully hosted the bot on my private infrastructure. The choice of WhatsApp as the interface proved ideal, offering seamless interaction with both text and multimedia. This strategy not only facilitates user-friendly communication but also ensures the utmost privacy and control over my data, keeping sensitive conversations strictly confidential.

The primary goal of this project was twofold: firstly, to gain hands-on experience in running and hosting a personal GPT bot, and secondly, to delve into the burgeoning world of AI tools and practices, including exciting platforms like Ollama and Langchain. It also provided an opportunity to expand my technical repertoire by exploring a new tech stack, specifically Phoenix/Elixir.

Working in big tech often limits exposure to the diverse array of technologies available outside the corporate environment. This project served as a bridge, reconnecting me with the broader tech landscape.

It's time to build..