Generative AI | News, how-tos, features, reviews, and videos
How to implement a local RAG system using LangChain, SQLite-vss, Ollama, and Meta’s Llama 2 large language model.
Go Developer Survey respondents who build AI-powered applications and services already use Go or want to migrate to Go for those workloads.
Google introduced an LLM inference engine, a library of reference diffusion models, and TPU optimizations for transformer models at Google Cloud Next ’24.
Other updates include grounding applications and virtual agents in Google Search via Vertex AI and Vertex AI agent builder.
Formerly Duet AI for Developers, Gemini Code Assist taps Google’s most powerful generative AI model for code completion, code generation, and code chat.
AI-powered assistant for Google Cloud can help design, deploy, and configure apps, troubleshoot issues, and optimize performance and costs.
Gemini's availability across Google Cloud database offerings is expected to help developers code and migrate faster than Duet AI, which was integrated last year.
Hardware requirements vary for machine learning and other compute-intensive workloads. Get to know these GPU specs and Nvidia GPU models.
Companies investing in generative AI find that testing and quality assurance are two of the most critical areas for improvement. Here are four strategies for testing LLMs embedded in generative AI apps.
Prompt engineering is the newest art of convincing machines to do what humans want. Here are 10 things you need to know about writing LLM prompts.