PinnedAstropomeaiGemini Pro API: Hey Gemini! Developing a Voice-Activated Multimodal AI AppYou may have dreamed of the future of AI after watching Deepmind’s demo videos, but the integration of voice and image remains a mystery to…7 min read·Dec 27, 2023----
AstropomeaiTitle: Implementing RAG with Firebase GenkitFirebase is a mobile and web application development platform provided by Google. It offers various functions such as authentication…8 min read·13 hours ago----
AstropomeaiTitle: llama-3-vision-alpha: How to Convert LLaMA-3 into a Vision ModelLLaMA is a large-scale language model developed by Meta, but it doesn’t originally have vision capabilities. However, a method to extend…4 min read·May 3, 2024----
AstropomeaiCreating a Custom YouTube Search Tool for Use with LangGraphLangChain is a framework designed to facilitate the development of applications utilizing Large Language Models (LLMs). LangGraph, built on…5 min read·Feb 14, 2024--1--1
AstropomeaiLaunching My GPT on the GPT Store: A Step-by-Step GuideWith the GPT Store now available, I’m excited to share the process I followed to publish my own GPT model. Interestingly, only TXT record…3 min read·Jan 22, 2024----
AstropomeaiCreating Interactive AI Programs Using the Gemini APIWith the advent of Google’s latest multimodal AI, Gemini, a new user experience integrating text, voice, and image processing has become…4 min read·Dec 16, 2023----
AstropomeaiGPT-4-vision: Realizing Autonomous Driving with LLMDisclaimer: The author does not possess specialized knowledge in automobiles or autonomous driving technologies, so please excuse any…3 min read·Dec 4, 2023----
AstropomeaiGPT-4-vision: Trying Out Real-time Image Analysis Based on ContextIn this article, we delve into a process that captures video frames in real-time using a PC’s camera, encodes them into Base64 format, and…3 min read·Nov 25, 2023----
AstropomeaiIntegrating YouTube API with GPTs for Video SearchOverview of the Action4 min read·Nov 25, 2023----
AstropomeaiCreating an AI Agent mastering various tools with Streamlit × Langchain🦜Until now, we have been developing the LangChain AI Agent. This time, we decided to introduce a GUI to pursue a more intuitive operability…3 min read·Sep 16, 2023----