Hey everyone! I’m thrilled to share an update on the course I’ve been creating for you. In case you missed it, I’m launching a series of courses focused on solving real-world problems using AI-powered apps. The ultimate goal? To help you become full-stack AI developers, ready to tackle the challenges of 2024 and beyond. **Progress Update: What’s New** In this first progress update, I’m excited to show off some of the new features you’ll learn to build in the course. These aren’t just any features—these are the kinds of tools that will give you a solid foundation as an AI developer. I’ve also implemented a few core AI and full-stack concepts that are absolute must-knows for anyone serious about AI development. **Demo & Next Steps** During the update, I also dive into a live demo where you can see these new features in action. Plus, I’ll cover some of the major enhancements I’m planning to build out next, so you know exactly what’s coming your way. I’m so pumped for you to see what we’ve been working on, and I can’t wait to hear what you think! If you have questions about anything in the video or the course as a whole, please drop a comment down below and I'll be happy to help! Cheers, Brandon 🧑‍💻🥂 P.S. If you missed the original course announcement and overview, you can watch it here: Click here to watch overview P.P.S. Here's the link to the course inside of the Skool community. Click here to view course

🚀 Exciting News! 🚀 I'm thrilled to introduce my latest open-source project: CrewAI Visualizer! 🎉CrewAI Visualizer is all about simplifying AI crew management with a user-friendly interface based on CrewAI package. As someone deeply passionate about AI and its potential, I wanted to create a tool that makes it easy for anyone to create and manage AI teams without the need for coding skills. 🛠️ Tech Stack: Built using a powerful tech stack, including PostgreSQL, Prisma, Next.js, GraphQL, node-calls-python to execute Python code from Node.js, and the CrewAI Python package to leverage the framework's capabilities in addition to Gemini as LLM. 🔍 Main Features: - Intuitive UI: Designed for ease of use, allowing you to focus on building your AI crews effortlessly. - Role-Based Agent Design: Customize agents with specific roles, goals, and tools, giving you full control over your team composition. - Task Management: Define tasks and assign them dynamically, ensuring smooth workflow management and efficient task execution. - Sequential and Hierarchical Processes: Choose between sequential or hierarchical processes for task execution, providing flexibility to adapt to different workflow needs. - Save Output: Track output for future reference or analysis, enabling you to monitor progress and outcomes over time. 🚀 Future Plans: In the pipeline: - Adding more tools for agents from the LangChain community or creating new useful tools internally. - Expanding LLM options to include ChatGPT and support for local LLMs, providing users with a broader range of AI capabilities. 🌟 I'm continuously working to improve CrewAI Visualizer and add new features, so your feedback and contributions are invaluable. If you're interested in checking out the project, feel free to visit the GitHub repository, give it a star, and maybe even contribute to it! CrewAI GitHub Repo: https://github.com/Eng-Elias/CrewAI-Visualizer

If you want to make sure you're not spending tons of $$$ with GPT4. Below is a conversation I had with Peplexity AI regarding monitoring how much you will be spending @ OpenAI. ================================================ To implement OpenAI's tiktoken library directly to count tokens in Python, you can follow a simple example based on the information provided in the OpenAI Cookbook . The tiktoken library is a fast, open-source tokenizer designed by OpenAI for efficiently counting tokens, which is crucial for managing usage and costs when working with OpenAI's API. Installation First, ensure you have tiktoken installed. If not, you can install it using pip: bash pip install tiktoken Counting Tokens with tiktoken Here's a basic example of how to use tiktoken to count the number of tokens in a given text string: python from tiktoken import Tokenizer # Initialize the tokenizer tokenizer = Tokenizer() # Your text input text = "This is a sample text to tokenize." # Tokenize the text and count the tokens tokens = tokenizer.tokenize(text) token_count = len(tokens) print(f"Token count: {token_count}") This code snippet initializes the tiktoken tokenizer, tokenizes a given text string, and then counts the number of tokens by measuring the length of the resulting list of tokens. Important Notes - The tiktoken library supports various encodings used by OpenAI models. Make sure to choose the appropriate encoding for the model you are working with. The default tokenizer should work well for general purposes. - Token counts are crucial for understanding how much text you can send to OpenAI's API in a single request and for estimating costs, as OpenAI's pricing is based on the number of tokens processed. By following this simple example, you can integrate token counting into your applications, helping you to monitor and manage your usage of OpenAI's API more effectively. Hope this helps out...

To help make sure you're weekend if filled with fun and AI, I just published a new CrewAI YouTube tutorial for you! In this tutorial, you will see how I used the lastest version of CrewAI to automate my YouTube video creation process. Here's what you will learn by watching this video: - How to automate manual processes with CrewAI - How to use CewAI v0.19.0 latest features - How to build custom tools for your Crew - A sneak peak into my YouTube video creation process After you watch this new tutorial, I'm confident you'll be able to automate tasks in your own life using CrewAI. Or, if you're feeling entrepreneurial, I'm sure you can start a side hustle where you automate tasks for local businesses! Also, here's a link to the source code so you can tweak the code for your own projects. ​https://github.com/bhancockio/automate-youtube-with-crewai I can't wait for you to watch this tutorial and hear what you think about it! [IMPORTANT] If you get stuck or have any questions about this video, please drop your comments down below.

Where can I find the video or link from yesterday’s meeting?