46 posts tagged with "azure"

An amazing session from AKS product team about the new features of Azure Kubernetes Service at Microsoft Reactor Sydney tonight! It's an insightful presentation and demo from Justin on running open source LLMs in AKS using the AI toolchain operator (KAITO) - a perfect blend of AI and Kubernetes in action!

Fantastic opportunity to hear directly from the team. Great to see Simon and Jorge and the visiting product managers Brian and Kaysie for such an engaging event. Read more about KAITO: https://learn.microsoft.com/en-us/azure/aks/ai-toolchain-operator

Great pizzas too! 🍕

Lucky! 🍀 My AzureAI and CosmosDB hackathon project was a winner (honorable mentions) and featured on the Microsoft Azure Cosmos DB Dev Blogs ! A few weekends of hard work truly paid off! ✨

This AI hackathon had over 9,500 developers world-wide engaged with Azure Cosmos DB and Azure AI services, making it one of the most popular on Devpost, ranking in the top 0.2% of all Devpost hackathons. 🔥

📢 Checkout my "LEGO Robot AI" and other winner's projects in this blog: "Meet the Winners | Microsoft Developers Azure AI & Azure Cosmos DB Learning Hackathon".

We are back at Microsoft Brisbane office again for our second Azure AI App in a Day workshop.

Ready to build the next million-dollar app in just a day? 💡 We've just completed our second AzureAIAppInADay in Brisbane Microsoft office. Rakesh Lakshminarayana and I had so much fun leading the workshop, and we're glad to see more participants make it to the end - some of you without even a dev background! It's been amazing to keep the momentum going. A big thank you to Tricia Read and Ross Johnson.

In this workshop, we got hands-on with AI app development, RAG (Retrieval-Augmented Generation), prompt engineering and built a chatbot using CosmosDb for MongoDb. With the power of Azure and OpenAI, we're helping organizations bring their AI ideas to life!

Excited to see what incredible apps come next! Our Insight team is around to help.

I recently presented and co-hosted an Azure AI App in a Day workshop in Microsoft's Brisbane office, surrounded by 40+ developers who were just as excited as I am about learning AI and building innovative apps. It was an action-packed day, full of coding and collaboration, where we explored the possibilities of using AI in real-world applications. We dove deep into various Azure AI services, learning how to integrate machine learning models, natural language processing, and more into app innovations.

The workshop was not just about learning theory, we spent most of the time writing code together, which made it both engaging and practical. Everyone was there to push their limits and see how they could apply AI to solve real-world problems. There was a real sense of community and shared passion, which made the learning experience even more enjoyable.

During the session, I had the chance to share our own LEGO AI app with the group. This app, which we've built using several Azure AI services, helps students by providing them with AI-generated coding solutions for SPIKE Prime robots. It was great to show how AI can be used in education and robotics, two fields that are close to my passion. The feedback I received was incredibly positive. People were excited about how AI could be used in such practical, hands-on ways to empower the next generation of students and engineers.

Sharing the LEGO AI app also sparked some meaningful discussions. We talked about how AI can be integrated into everyday life, not just in high-tech or corporate environments, but in educational settings where students are learning to code, solve problems, and think critically. Developers were intrigued by the idea of using AI not only to build complex systems but also to inspire young minds. It was a reminder that AI has the potential to impact more than just technology - it can inspire creativity and learning in new ways.

One of the biggest takeaways from the workshop was the idea that the best AI app ideas often come from your passions. Whether it's education, robotics, or something completely different, finding an area you care about can lead to the most impactful and rewarding projects. When you're passionate about a subject, you naturally want to find better ways to improve or innovate, and that's where AI can really shine.

As I left the workshop, I was energized by all the new ideas floating around the room. It was a great reminder that AI is not just about data and algorithms. It's about creativity, innovation, and making life better in ways big and small. So, when you're looking for your next AI app idea, look to the passions in your life. You never know how AI might help turn your interests into something truly innovative.

In this FLL season, we decided to take our chatbot project to the next level. On top of helping us with coding for the LEGO SPIKE Prime, we wanted to explore if we could add all the season documents into the chatbot to help with research and navigating through the rules of the robot game. The idea was to make it easier for our team to access and understand the challenge, rules, and guidelines, all in one place, through a simple conversation with the bot.

To do this, we downloaded all the essential documents: PDFs, excel spreadsheets, PowerPoints from the FIRST LEGO League website. These documents contain all essential information about the Submerged season, including robot game rules, mission details, and field setup instructions. We then uploaded everything to our Azure storage account, which made it easy to connect the documents with our chatbot.

Using Azure, we linked the chatbot with the documents so it could answer questions related to the robot game rules and season guidelines. For example, if we needed to know what specific missions required or how points were awarded, we could ask the chatbot, and it would pull the information directly from the official documents.

The setup process on Azure turned out to be more straightforward than we anticipated using Azure AI Studio. Azure provides great tools for building, training, and deploying AI models, and we were able to get our chatbot running smoothly in a short amount of time. It was a valuable learning experience to see how cloud-based AI services like Azure work in real life. With this setup, our chatbot became a research assistant, helping us quickly reference complex rules and documents during our robot strategy sessions.

We are also keen on responsible AI during our learning. This season, we had sessions with students on AI bias and responsible AI use, which were critical in shaping how we approached this project. We taught the students that while AI can be incredibly powerful, it's also important to recognize its limitations. It's not just about getting the right answer; it's about understanding how the AI processes information and ensuring it's providing accurate and unbiased responses.

We talked about how bias can creep into AI models, especially when the data or documents they rely on are incomplete or misinterpreted. By being cautious and ensuring we used the chatbot as a support tool rather than the sole decision-maker, we are ready to explore AI's potential responsibly.

We're excited to continue using our chatbot for coding, research, and game strategy while keeping in mind the lessons we've learned about using AI. Our team is ready to dive into the Submerged season with confidence, knowing we have the tools and understanding to make the most of AI without losing sight of what's most important: learning, teamwork, and innovation.

In the new Submerged season of FIRST LEGO League (FLL), we are continuing our journey of using AI to help us learn, innovate, and make robotics more accessible to everyone. Our team took the initiative to build a chatbot using Microsoft Azure (with lots of helps from coaches) and publish an app that anyone can use, free of charge. This was a big step toward creating a more inclusive, cost-effective way for young engineers and coders to get the most out of AI.

One of the challenges we faced when using tools like ChatGPT is that they often require users to create an account, and there are costs associated with using advanced AI features. This creates a barrier for many students and teams who might not have access to these resources. To solve this, we built a free version of our chatbot that specifically focuses on the needs of FLL participants. We locked down the scope of the questions and answers so that they only relate to the official season documents and guides for the Submerged challenge, as well as coding instructions for the LEGO SPIKE Prime 3.

The chatbot is designed to be simple and focused, giving users clear, relevant information about the FLL challenge and the Python coding required for SPIKE Prime 3 robots. Whether a team needs help understanding the mission details or figuring out how to make their robot move in a specific way, our chatbot has the answers.

One of the key skills we emphasized this season is prompt engineering. The art of asking the right questions to get the best answers from an AI. While many people assume that AI automatically gives perfect responses, the truth is that how you ask a question can dramatically affect the quality of the answer you receive. We've been teaching our team and users of the chatbot how to frame their prompts clearly and concisely to get more accurate and useful information.

For example, instead of asking, "How do I code my robot?" a better prompt might be, "Write Python code to move my SPIKE Prime 3 robot forward for 5 seconds and stop." By being specific, users can get actionable responses that directly help with their projects.

This new chatbot, combined with prompt engineering techniques, empowers young engineers to not only rely on AI for quick solutions but also to better understand how to interact with technology in ways that enhance their learning experience. We're excited to see how teams use this tool during the Submerged season and how it helps them innovate and succeed. We hope to remove some of the barriers that traditionally come with using advanced AI tools and give every FLL team a chance to harness the power of AI for their robotic challenges.

I had the exciting opportunity to present a talk at the FIRST LEGO League (FLL) Australia season kickoff in August 2024, an event where young minds gather to prepare for a year full of innovation, teamwork, and, of course, robotics. My talk was titled, "ChatGPT, Write Python Code for My Robot, Please!", A topic that connected artificial intelligence, robotics, and education in a way that resonated with both the kids and mentors.

One of the most exciting things to prepare for this talk was building up a Python knowledge base specifically for the LEGO SPIKE Prime, the popular robotics kit used in FLL. SPIKE Prime uses a powerful hub and motors that can be programmed in Python. By leveraging ChatGPT's advanced language model and training it with SPIKE Prime's API and specifications, I was able to get it to generate Python code that effectively controls the robot's movements and sensors. This is a great option for kids (and even adults) who might struggle with the initial complexities of writing code from scratch.

For example, using simple natural language prompts like "write Python code to move the robot forward for 20 cm", ChatGPT can now produce highly accurate, ready-to-run Python scripts that control the motors of a LEGO robot.

During the presentation, I walked the audience through several real-world examples of how ChatGPT can assist in generating Python code for SPIKE Prime robots. I showed how, with minimal guidance, the AI could create scripts that made the robot move forward, turn, stop, and even detect objects using sensors. The kids were thrilled to see how a few simple prompts resulted in real-time robot movement, and their imaginations lit up at the possibilities of using AI to enhance their learning and problem-solving.

One key aspect of my talk was addressing the responsible use of AI as a learning tool. I emphasized how tools like ChatGPT should not be seen as a shortcut or replacement for understanding core concepts but rather as a tool to enhance learning. I encouraged the kids to experiment with the AI, ask it questions, and use it to break down complex problems, but to also remain curious about how the code works. This way, they could continue learning and developing their own skills while benefiting from the AI's assistance.

To make the talk even more engaging, I introduced two major figures in the tech world: Satya Nadella, CEO of Microsoft, and Sam Altman, CEO of OpenAI. I explained their roles in the development of AI and how their vision has contributed to making these cutting-edge technologies more accessible to everyone. The kids were fascinated to learn about the real people behind the tools they were interacting with and how AI is evolving to shape the future of not just robotics, but many industries.

The talk was super fun! The combination of showing how AI can be a practical, hands-on tool for robotics, while also discussing the broader implications of responsible AI use, made it a well-rounded experience. Watching the kids' excitement as they saw the robots come to life through AI-generated code was a highlight, and I hope they left feeling empowered to continue exploring the amazing world of robotics and AI.

Winner, Winner, Chicken Dinner! 🎉

I just received an email from the DevPost team, and guess what? My project is a winner in the Microsoft Azure OpenAI Hackathon! I'm beyond excited to share that my AI app made it to the top 4 places. What started as a quick experiment has turned into something truly rewarding!

It's incredible to think that this AI app, which I put together in a short time (a few long nights on the weendes), stood out among so many great projects. The voice interaction, speech output, and language translation features seem to have really struck a chord with the judges. I couldn't be happier with the outcome!

Now that the adrenaline of the win is starting to settle, I'm thinking about what's next. Winning is fantastic, but the real value lies in how we can take this project further and apply it in meaningful ways. One big question that's been on my mind: How can we use these AI tools to engage young students in coding and learning?

AI-powered apps, like the one I built, have the potential to transform education in meaningful ways. Imagine:

• AI tutors that help students understand coding concepts step-by-step, making complex topics more approachable.
• Interactive coding lessons where students can communicate with the bot using voice commands, making it more fun and less intimidating.
• Multilingual support to help non-native English speakers learn to code in their preferred language, breaking down barriers to entry.
• Instant feedback where students can ask the chatbot for coding help and get immediate answers, encouraging exploration and problem-solving.

There's so much potential to use AI to make learning more engaging, accessible, and fun. I'm excited to explore how I can turn this hackathon project into a real tool for education that sparks curiosity and creativity in young minds.

Onward to the next challenge! 🎉

The closing day of the Microsoft Azure OpenAI Hackathon is fast approaching, and I've just wrapped up Phase 2 of my project. It's been an exciting journey, and I've managed to add some really cool features that have made the chatbot even more powerful.

Here's what I've built on top of the base RAG chatbot using more Azure AI Services:

• Voice Interaction: The chatbot can now accept voice commands, making it more interactive and user-friendly, especially in hands-free scenarios. This adds a whole new level of accessibility to the project.
• Speech Output: In addition to text-based responses, the chatbot can now speak back the generated Python code or explanations. This is particularly useful for quick feedback or demonstrations.
• Language Translation: I integrated a translation feature, allowing the chatbot to understand and respond in multiple languages. Whether you're coding in English, Spanish, or any other supported language, the chatbot can assist, making it more versatile and globally accessible.

These enhancements have transformed the chatbot into a more intuitive AI assistant that doesn't just help with coding but also communicates naturally with the user. I'm really excited to see how it performs in the hackathon!

With everything built and ready, it's time to submit the project and see what kind of feedback we get. The hackathon has been a fantastic learning experience so far, and I'm eager to hear what others think of these new features. Let's put the project to the test and see how it stacks up against the competition! Fingers crossed! 🤞

In my latest experiment with AI-powered robotics, I decided to take all the API help specs from the Spike Prime 3 user guide and load them into Cosmos DB as a knowledge base. The goal was to use this data to generate better, more targeted Python code for Spike Prime robots using a LangChain RAG integration.

Here's the plan I followed:

1. Extracting API Data: I pulled all the relevant API definitions and code snippets from the Spike Prime user guide. This included functions related to movement, turning, and sensor control.
2. Cosmos DB as a Knowledge Base: I uploaded the extracted API documentation into Cosmos DB, setting it up as a searchable knowledge base. This would allow us to easily retrieve API definitions and related examples.
3. LangChain Integration: The idea was to use LangChain's search capabilities to query Cosmos DB. The chatbot would then fetch relevant Python API definitions and example code snippets directly from the knowledge base.
4. Generating Python Code: Once the relevant information was fetched, the chatbot would combine this with user input to generate Python code that could control the Spike Prime robot.

However, I ran into an unexpected issue: Despite having all the Spike Prime API information in Cosmos DB, the chatbot still ocassionally attempted to rely on external Python libraries from the internet instead of using the custom API definitions I had loaded. This led to code that wasn't compatible with the Spike Prime system, as those external libraries were not designed for LEGO robots.

This is a challenge I need to address. The chatbot is prioritizing internet-based solutions over the internal knowledge base, which defeats the purpose of having a custom-built, Spike Prime-specific AI assistant.

Next steps? I plan to tweak the LangChain logic to ensure the chatbot prioritizes fetching from Cosmos DB and only uses the API definitions we've provided. This will help ensure that the Python code generated is compatible with the Spike Prime robot. Stay tuned for updates on how I solve this!