Next in GenAI
Dive into my latest explorations in Generative AI! Here, you’ll find insights, tools, and tips to fuel your learning journey.
Whether it’s breaking down complex concepts, sharing exciting discoveries, or showcasing practical applications, these posts are crafted to inspire and inform. Stay curious and let’s explore the transformative power of Generative AI together!
- Using RAG to create an AI expert about your Company
Have you ever thought, “I’ve answered this question so many times!” or “This information is available online—why are they asking me?” If not, congratulations—you’re one of the lucky ones! But for most of us, these thoughts have crossed our minds at some point. Wouldn’t it be great if there were a tool to handle these… Read more: Using RAG to create an AI expert about your Company - Empowering Autonomous Task Execution with AI Agents
The field of artificial intelligence is advancing rapidly, and one of the most exciting developments is the emergence of autonomous AI agents. These agents are designed to follow ambiguous goals, interpreting user instructions without needing precise step-by-step directions. They build their own plans, execute tasks, and learn from interactions to achieve desired outcomes. In this… Read more: Empowering Autonomous Task Execution with AI Agents - Hands-On Tutorial: Using AI Agents to abstract Complex APIs
Leveraging LangChain’s OpenAPI Toolkit enables us to build AI agents that can abstract the complexities of interacting with large APIs. By separating high-level planning from low-level execution, agents can navigate extensive API specifications more efficiently, minimizing token usage and improving the coherence of long interaction sequences. In this hands-on tutorial, I’ll demonstrate how to create… Read more: Hands-On Tutorial: Using AI Agents to abstract Complex APIs - Fine-Tuning Techniques: Full Fine-Tuning vs. LoRA, and ReFT
Fine-tuning is a critical step in adapting pre-trained models to specific tasks. In this article, I’ll compare full fine-tuning with advanced techniques such as LoRA and ReFT. I’ll highlight the differences in methodology, efficiency, and performance to help you choose the best approach for your projects. 1. Full Fine-Tuning Full fine-tuning involves updating all model… Read more: Fine-Tuning Techniques: Full Fine-Tuning vs. LoRA, and ReFT - Hands-on Tutorial: Using Hugging Face to quickly Develop and Test ideas
In the rapidly evolving landscape of artificial intelligence and machine learning, the ability to swiftly prototype and test ideas is a crucial asset for researchers, developers, and data scientists alike. Hugging Face, a leading provider of cutting-edge natural language processing tools and models, has become an essential platform for accelerating innovation in AI development. With… Read more: Hands-on Tutorial: Using Hugging Face to quickly Develop and Test ideas - Hands-on Tutorial: Fine-Tuning a Pre-trained Model
Fine-tuning a pre-trained model is a powerful technique that allows you to adapt a model to specific tasks with minimal additional training. Whether you’re working on sentiment analysis, question-answering, or text generation, the process of fine-tuning can significantly enhance performance tailored to your dataset. In this tutorial, you will learn how to: In this tutorial,… Read more: Hands-on Tutorial: Fine-Tuning a Pre-trained Model
Interesting Tools and Frameworks
Embarking on your journey in generative AI can feel overwhelming with so many tools and frameworks available. To help you get started, here are three essential tools that are beginner-friendly yet powerful enough to unlock the potential of generative AI. Whether you’re building chatbots, experimenting with AI models, or exploring creative AI applications, these tools will serve as foundational stepping stones.
LangChain is a framework specifically designed for developing applications powered by large language models (LLMs). Its modular approach makes it ideal for creating AI workflows that integrate tools like chat interfaces, knowledge retrieval, or custom pipelines.
Hugging Face is a hub for pre-trained AI models and a thriving community of developers. Known for its user-friendly libraries like transformers and datasets, Hugging Face allows beginners to quickly experiment with natural language processing, text generation, and more.
Ollama is a relatively new but innovative tool that simplifies interaction with local AI models. It’s especially useful for those who want to experiment with generative AI without relying entirely on cloud-based services.
Hi, My name is Ricardo Garcês and I live in sunny Madeira Island. I’m a Generative AI enthusiast with almost 20 years of software development experience.
This blog is my platform to learn, explore, and share insights about this exciting field of Generative AI. My goal is to foster curiosity and collaboration while uncovering the incredible potential of Generative AI. Join me on this journey to discover tools, practical applications, and the transformative power of Gen AI!