Blog·notes from the field
Deep dives into RAG, agents, inference, and the plumbing behind production AI systems. With a dose of copium that AI won't replace you.
What if your chunks in RAG were providing better context? Let's explore how to use contextual retrieval to enhance your RAG systems.
Did you have trouble making great images with AI? Maybe you were using the wrong model.
In the realm of machine learning, managing and tracking experiments can swiftly become a complex task, especially as projects scale. The introduction of tools like DVC (Data Version Control) has been a game-changer, allowing developers and data scientists to automate and streamline this process.
Welcome to the CryptoGPT tutorial! In this tutorial, we'll dive into a fascinating project that combines Streamlit, ChatGPT, and LangChain to analyze the sentiment of tweets related to cryptocurrencies. By utilizing Streamlit, we'll create a user-friendly interface that allows us to interact with our sentiment analysis application effortlessly.
Can you optimize the inference time of your LLM? How? Let's explore strategies to enhance the inference speed of your LLM.
Fine-tune a LayoutLMv3 model using PyTorch Lightning to perform classification on document images with imbalanced classes. You will learn how to use Hugging Face Transformers library, evaluate the model using confusion matrix, and upload the trained model to the Hugging Face Hub. The tutorial also covers installing and using various libraries like EasyOCR, and Torchmetrics. A complete Jupyter (Google Colab) notebook included.
