Google PaLM AI technology Top Builders

Explore the top contributors showcasing the highest number of Google PaLM AI technology app submissions within our community.

PaLM 2: Google's Revolutionary Large Language Model

PaLM 2 is a groundbreaking large language model developed by Google, setting extraordinary standards in the realm of artificial intelligence. Outperforming its predecessors and other LLMs in various aspects, PaLM 2 showcases unparalleled capabilities in complex reasoning, multilingual translation, and coding expertise.

General
Release date	TBA
Author	Google
Type	Large Language Model

Experience PaLM 2: Where Unparalleled Performance Meets Responsible Innovation

We have collected the best PaLM 2 resources to help you explore the capabilities and potential applications of Google's cutting-edge large language model. Unleash the power of PaLM 2 with these valuable resources and see for yourself the future of artificial intelligence.

PaLM 2 Links

Explore curated libraries and resources to help you build outstanding projects with PaLM 2, Google's transformative large language model.

PaLM 2 Documentation - Dive into the in-depth technical report of PaLM 2, providing valuable insights into its development and capabilities.
PaLM 2 Overview - Discover the key features, capabilities, and evolution of PaLM 2, Google's groundbreaking large language model.
PaLM 2 Developer Guide - Access a comprehensive guide to using Google's generative AI models like PaLM 2, offering a plethora of support and resources for developers.

Edit on Github

Google PaLM AI technology Hackathon projects

Discover innovative solutions crafted with Google PaLM AI technology, developed by our community members during our engaging hackathons.

Pyropulse

Pyroplus presents a comprehensive solution to address the urgent challenges of wildfire management. Integrating IoT technology, AI algorithms, drones, and eco-friendly chemical materials, our system detects wildfires early using air quality sensors, analyzes data in real-time to guide response efforts, and employs drones for aerial surveillance and strategic firefighting. Our innovative chemical material, composed of cellulose, colloidal silica, sodium nitrite, and ammonium chloride, swiftly extinguishes fires while minimizing environmental impact. By combining cutting-edge technology with sustainable practices, Pyroplus aims to revolutionize wildfire management, protect ecosystems, and safeguard communities from the devastating effects of wildfires. Our LLM agent plays a pivotal role in enhancing public awareness and offering crucial instructions for fire protection. With a focus on preventing human-caused fires, which account for a staggering 95% of incidents, our agent acts as a proactive guide. Through informative content and clear directives, it empowers individuals with the knowledge needed to prevent wildfires, fostering a community-driven approach to fire safety.

Jamie 2 point 0

Mobile Version of Jamie 1: https://lablab.ai/event/gemini-ai-hackathon/jamie The user experience more suitable for target Audience Non : Tech Savy people / My mom. * App reachable on your phone with 1 click * UI iterated upon about 5 times. Tested the UI on my mom a couple times. A simple button seems most effective. Inserting images was overkill in terms of UI from Jamie 1.0 * Audio Input, Output * Implements Bard (PALM API 2) for responses. Made a basic version with just audio input and output voice assistant. That we can now work on further to provide better answers according to use cases e.g. navigation, product usage (tv, microwave, etc). Next we want to improve the responses with more accurate and shorter answers. This may involve web scraping data ourselves.

Zenna chatbot

The Zenna Conversational Chatbot project aims to create a user-friendly AI assistant using Google Vertex AI's Palm 2 Foundational model chat-bison. Zenna focuses on providing helpful and uplifting information through verbal interactions, incorporating speech-to-text and text-to-speech for natural language interactions. It utilizes TruLens evaluations and complex prompt design to ensure thoughtful responses, acknowledge knowledge gaps, and prevent unintended harm. The ultimate goal is to develop an empathetic human-like advisor through beta testing to enhance conversational abilities and emotional intelligence before public release. And a Beta feature that will also enable it to summarize website through links through the langchain technology.

TruSentment

TruSentiment is a team focused on leveraging observable AI to extract accurate business insights from complex financial texts. By integrating powerful language models with customizable relevance and grounding feedback, we enhance the credibility and precision of sentiment analysis on sources like 10-K filings. Our rigorous evaluation and comparison methods spotlight model strengths while illuminating opportunities for continuous improvement. Whether assessing risks, gauging market outlook, or decoding regulatory documents, TruSentiment enables financial enterprises to make decisions with confidence based on AI that users can understand and trust.

The GPT Report Card App

🚀 The GPT Report Card App is an absolute powerhouse in the world of AI metrics tools! 🌐✨ Utilizing a cutting-edge blend of technologies, it's not just an app—it's a true marvel! 🌟 🔍 True Lens technology takes LLM (Large Language Models) and Advance LLM metrics to a whole new level. Perfect for testing, training, customizing, optimizing, and automating your AI models! 🤖💡 🔄 Enter LangSmith and LangChain, a dynamic Python framework that revolutionizes agent training. Tailor your models with precision through customization, optimization, and automation. The future of AI development is here! 🐍💻 🦙 But wait, there's more! Mixed with the Llama Index, this app incorporates short-term memory functionality and database injection for seamless operation. And that's not all—the app even focuses on self-improvement! 🔄🧠 🔒 Vector database technology ensures permanent memory storage and trained memory retention. Your AI models will never forget, ensuring consistent and reliable performance. 📚🧠 📊 Supporting a whopping 5 main categories for testing and training LLMs—Text, Code, Image, Agent, and Audio/LLM—this app covers all bases, making it the ultimate tool for AI enthusiasts and professionals alike! 📝💻🎨🎙️ In a nutshell, the GPT Report Card App is a game-changer, bringing together a symphony of technologies to make AI metrics more powerful and accessible than ever before! 🚀🔥

Term Aware Guard

Rarely people read the whole data corpus of terms of service when they sign up for companies and we came with a solution: The primary objective of Term Aware Guard is to simplify the readability of Terms and Conditions, providing a summarized version and ensuring that users are well-informed about data privacy beforehand. It is a web app with built with Next.js using GCP for hosting and Firebase for storing the companies the user has signed up for. The web app uses Python environment REST API hosted on Digital Ocean for the backend. We use Google Vertex AI PaLM2 on text-bison002 model for inference, a large language model with impressive capabilities. Terms and conditions of companies change constantly, and fine tuning the model everytime that happens could be very costly and inefficient, for that we found a solution. We use Retrieval augmented generation(RAG) to enhance the model's summarization capabilities and to get the context of the latest updated version ToS of companies. The model is evaluated with the help of TruLens to measure its quality with feedback and metrics. We used Apify for gathering the data by web scrapping and Pinecone as a vector store where RAG gets context from.