Hi, team.
Hope you’re doing well. I wanted to share a quick note of thanks for everyone who attended our talk on WebML and Flutter Large Language Model integration. Thank you for sharing your time with us. I also wanted to share a sincere thank you to Leo Farias, CEO of Concepta, for sharing his insight into the Flutter community. We will make sure to share links to your Palm 2 API connector library for Flutter in this post.
This event really helped the community gain excitement for DevFest Florida conference in Oct 14.
For the community at large, here are a few links and videos that review ideas we discussed.
Flutter and Large Language Model integration
It was great to see Leo demo some of the power of the Google PaLM 2 API. During most of the talk, Leo unpacked the value that the Palm 2 API creates through its conversational AI capabilities. The PaLM 2 API is a REST API that allows developers to access the power of Google’s PaLM 2 large language model. PaLM 2 is a state-of-the-art LLM that excels at a wide range of tasks, including text generation, translation, question answering, and code generation. In one of my side projects, I’m using it to tag content.
Leo presented an impressive app that generates presentations. You simply specify a start prompt like “how do you plan a conference.” The system segmented the data into slide form and connected compelling images on each slide.
In general, I appreciated Leo encouraging us to view LLMs as tools to create structured data. Lots of innovation flows from that concept.
If you are interested in learning more from Leo, check out Leo’s next talk at DevFest Florida.
Links
– flutter.dev
– Get started with MakerSuite – YouTube
– leoafarias/palm_api_dart: A Dart client for interacting with the PaLM API, allowing developers to build generative AI applications. (github.com)
– Introducing PaLM 2, Google’s next generation large language model | Research Bytes – YouTube
– Create haikus about Google products with the PaLM API and Flutter
Exploring WebML
TensorFlow.js is a JavaScript library for training and deploying machine learning models in the web browser and in Node.js. It is built on top of the TensorFlow core library, and it provides a high-level API for working with tensors, layers, and models. TensorFlow.js can be used to build a wide variety of machine learning applications, including image classification, object detection, natural language processing, and more. TensorFlow.js is a powerful tool for building machine learning applications, and it is used by a wide variety of companies and organizations, including Google, Adobe, Microsoft, and Airbnb. Check out the following Google IO video to learn more.
Related code labs
- Teachable Machine
- Convert a Python SavedModel to TensorFlow.js format
- Make a smart webcam in JavaScript with a TensorFlow.js pre-trained Machine Learning model
- Getting Started (ml5js.org)
Join us for DevFest Florida – Oct 14
AI | Mobile | Web | Cloud | Community
DevFest Central Florida is a community-run one-day conference aimed to bring technologists, developers, students, tech companies, and speakers together in one location to learn, discuss and experiment with technology.
Leave a Reply