Ollama

A conversational agent for e-commerce built with Ollama, LangChain, and ChromaDB, comparing three open-source LLMs — Qwen3 4B, Llama 3.2 3B, and Phi-4-mini — for product search, order tracking, recommendations, and RAG-powered FAQ. Benchmarks tool-calling accuracy, multi-intent handling, and response time across all three models.

‘Gabo’ is a RAG (Retrieval-Augmented Generation) system designed to enhance the capabilities of LLMs (Large Language Models) such as ‘DeepSeek-R1’, ‘Llama 3.2’, and ‘Phi 3.5’. This project honors Colombian author Gabriel García Márquez by marking the tenth anniversary of his death.

Ollama is a great tool for testing LLMs and Embedding models locally. It’s possible to use this tool in Google Colab, but when you run ollama serve, your script will get stuck in that cell, and you won’t be able to run the following cells. Luckily, the solution is simple and can be done with code.