Emmanuel Taiwo’s Post

I Created a DDLTodo App with Claude 3.5 Sonnet in 5 prompts: How could it Different from 100 Others I’ve Used? Continue reading on Generative AI » #genai #generativeai #ai

Check out Gradio for quick LLM App demo creation

After the recent OpenAI announcement of `gpt-4o-mini`, i'm sure we're all thinking about it : the cheap and fast option just got a whole lot smarter ! ♻️ Does that mean you should switch from `gpt-3.5` ? 👉 Well probably, but first you need to check how this new model performs with your existing tasks. Hugues breaks down for you how to use Literal AI to evaluate and validate your app's performance on different models.

Delighted to unveil my latest project: a Game Recommender System driven by cutting-edge Generative AI! 🎮✨ Harnessing the power of the Retrieval-Augmented Generation (RAG) model and the Mistral large language model (LLM), I've developed a system that goes beyond mere game recommendations—it offers a profound understanding of user preferences and behaviors. Here’s why this project stands out: 🔍 RAG Model: Leveraging retrieval-augmented techniques to dynamically source real-time game data, ensuring recommendations are precise and diverse. 🤖 LLM Mistral: With its advanced language processing capabilities, Mistral interprets user inputs with naturalness and intuition, delivering personalized interactions. 📊 VectorDB: Enhancing recommendation accuracy by integrating vectorized representations of user preferences and game attributes. 🎯 Gen AI Innovation: By seamlessly merging retrieval-based and generative AI methods, our system tailors recommendations to each user's unique tastes. While developing this project, I encountered challenges such as scraping real-time Play Store data, accessing various LLMs, and training models via prompt engineering. However, each hurdle was a valuable learning experience, marking just the beginning of my journey into GenAI. Proud to share the culmination of hard work and innovation, and eager to witness how it transforms gaming experiences! ✨ Know more about project insight by reading my Blog on Medium: https://lnkd.in/d_2a_YZ5 ✨ Link to the Project: https://lnkd.in/dj8Ez_k9 #ArtificialIntelligence #GenAI #MachineLearning #GameRecommender #TechInnovation #AI #ML #Gaming #DataScience #RAG #VectorDB #LLM

🚀 Day 14 of #100DaysofNoCode 💯 It's a WRAP for build weekend. 👏🏼👏🏼👏🏼 It's been an amazing journey, and incredibly rewarding to wrap up my Task Tracker and share it with the world. Build Weekend may be over, but the journey continues. Here's what I've been working on... Airtable Base: https://lnkd.in/derTdQJH #100DaysofNoCode #100DaysofAI #NoCode #AI #BuildWeekend

Lately, I've been thinking about the future of web app development. Will no-code become as powerful as traditional development? Or will AI-powered dev assistants replace everything? 🤖 🎥 Watch my thoughts on this here:

Doesn't it sound cool to take a photo as input to an LLM, which then generates a story about it and produces an audio narration of the story? fabio matricardi walks you through the steps to achieve this by creating a Python-Streamlit app. https://lnkd.in/eNatauBX

Build a basic LLM app in minutes! Powered by LangChain, Ollama (Llama 3.2), and Streamlit – it’s a simple and private app. Great for beginners. Ready to build your own? Check out my blog. #LargeLanguageModels #LangChain #Streamlit #Ollama

<<ARTIFACTS-Edit your results- Anthropic is also introducing a new feature called Artifacts. With Artifacts, you’ll be able to see and interact with the results of your Claude requests: if you ask the model to design something for you, it can now show you what it looks like and let you edit it right in the app>>

I just launched CanYouMeet.us Here is the short pitch: Avoid group email/text chaos for event scheduling. Use CanYouMeet.us to let participants suggest dates/times in natural language. AI finds the best time/date that match the preferences for most (if not all) participants. It’s totally free.