Recently I’ve been interested in some of the ways that we can use embeddings to compare images, text, and other data. Embeddings allow us to create features and applications like image search, retrieval-augmented generation, and many more. You can think of an embedding as just a list of numbers (a vector) that represents the semantic meaning of a given piece of data. this allows us to compare two embeddings and determine how similar they are....
Today I was playing around with an LLM called Mistral 7B by running it locally with Ollama. Once installed, Ollama provides a chat interface and an API that you can use and run wherever. curl http://localhost:11434/api/generate -d '{ "model": "mistral", "prompt":"tell me a joke?" }' When running this API call, I noticed that responses were streamed back to the client in a way that appears to be token by token. Take a look at running the command....
This year I’m starting a new role with Roboflow. I’ll be helping companies build and deploy computer vision applications. The team, the product, and the mission are all incredible and I’m excited to be a part of building the future of computer vision. With this in mind, I thought it’d be fun to document my journey as I learn some of the tools and techniques that we use to build computer vision applications – starting with the Supervision python package....