Uncategorized

Answering questions based on domain knowledge (like internal documentation, contracts, books, etc.) is challenging. In this article we explore an advanced technique called Retrieval-Augmented Generation (RAG) in order to achieve this with great accuracy, mixing semantic search and text generation with models like ChatDolphin, LLaMA, ChatGPT, GPT-4…

Generative models sometimes take some time to return a result, so it is interesting to leverage token streaming in order to see the result appear on the fly in the UI. Here is how you can achieve such a text streaming frontend for your LLM with Go, FastAPI and Javascript.

Many organizations want to integrate AI into their product or into their internal processes, but without sacrificing data privacy. For such organizations, the solution is to download and deploy AI models on their own servers instead of sending their data to the cloud. We are going to discuss this on-premise strategy in this article (also