std-training VS askai

It's well established that interrupts are a tough concept to grasp for the embedded beginner. Add to that when doing it in Rust the complexity of dealing with mutable static variables. This is because working with shared variables and interrupts is inherently unsafe if proper measures are not taken. When looking at how to do interrupts using the esp-idf-hal I first resorted to the Embedded Rust on Espressif book. Interrupts are covered under the Advanced Workshop in section 4.3, and to be honest, I was taken aback a little at what could be an additional level of complexity for a beginner. Without too much detail, this is because the book resorts to using lower-level implementations. For those interested, by that, I mean FFI interfaces to FreeRTOS which I will be creating a separate post about later.

Relative to the esp-idf-hal , as far as material goes, there exists training material that is open sourced by Ferrous systems. The training material takes a bit of a different approach where it starts with high-level IoT exercises followed by low-level control. Additionally, the training is based on the awesome Rust ESP board hardware.

Yes! The training developed with Ferrous Systems (https://esp-rs.github.io/std-training/) contains several examples, and you can find many community projects in https://github.com/esp-rs/awesome-esp-rust#projects

Good places to get started with std Rust on ESP include the Rust on ESP book, Embedded Rust on Espressif by Ferrous Systems. There's also the Awesome ESP Rust GitHub repository that contains a lot of useful material and project examples.

Embedded Rust on Espressif (Ferrous Systems training)

I must admit I've never used it for anything but tutorials yet (kids resulted in a lot of personal projects shelved), but Rust has an amazing and rapidly developing embedded ecosystem. A good starting point to get an impression of it might be training materials from Ferrous Systems 1, 2 (feel free to pay for the training itself if you feel like it's worth it for you of course). There is an embedded working group for Rust, Knurling project to improve tooling and even an attempt of Rust standard certified for safety-critical application.

I’ve been super curious about both Rust and ESP. It seems like Espressif is interested enough to commission a Rust dev board (ESP32-C3-DevKit-RUST-1) and training using it.

https://github.com/esp-rs/esp-rust-board/

https://github.com/ferrous-systems/espressif-trainings

We'll use several interesting technologies to achieve this: Strapi CMS to take care of the content management and backend, Astro which is a great new technology for quickly creating blazing fast frontend apps, and ChatGPT to provide the article summaries.

I was confused why https://chat.openai.com suddenly redirects to https://chatgpt.com which results in connection refused. Turns out chatgpt.com is in many blocklists (e.g. Pi-Hole) due to it being a potentially unsafe Domain before OpenAI acquiring it. So heads up if you use Pi-Hole / AdGuard etc.!

This API allows you to interact with ChatGPT programmatically, and I've built some cool agents on top of it. Check out the code and let me know what you think! :

ChatGPT unofficial API :

This project is a Node.js application that interacts with the ChatGPT conversational AI model using Puppeteer, a Node.js library for automating web browsers.

Files chatgptv1.js: This file contains the main logic for the ChatGPT bot, including methods for initializing the browser, sending messages, receiving replies, and handling errors.

bart.js: This file contains a function that uses the Cloudflare API to summarize the conversation history when an error occurs, in order to resume the conversation.

twochatbotsconv.js: This file is simple use of the API , which creates two instances of the ChatGPT class, initiates a conversation between them, and saves the conversation history to a file.

.env: This file contains the API token for the Cloudflare API, which is used in the bart.js file.

Dependencies :

puppeteer: A Node.js library for automating web browsers. fs: The built-in file system module in Node.js. winston: A logging library for Node.js. crypto: The built-in cryptography module in Node.js. axios: A popular HTTP client library for Node.js. dotenv: A zero-dependency module that loads environment variables from a .env file.

Usage:

Install the dependencies by running npm install in your project directory. Create a .env file in the project directory and add your Cloudflare API token:

API_TOKEN=YourfreeCloudFlareAPIToken In your code, create a new instance of the ChatGPT class and use the sendMessage and getReply methods to interact with the ChatGPT model:

const ChatGPT = require('./chatgptv1');

const chatgpt = new ChatGPT(); await chatgpt.initializeBrowser();

await chatgpt.sendMessage('Hello, ChatGPT!'); const reply = await chatgpt.getReply(); console.log(reply);

await chatgpt.closeBrowser(); If an error occurs during the conversation, the handleError method will attempt to save the conversation history and resume the conversation using the summarized context.

Before Running :

run Google chrom in the debug mode using 9220 port , run : google-chrome-stable --remote-debugging-port=9222

Customization :

You can customize the behavior of the ChatGPT bot by passing options to the ChatGPT constructor:

chatbotUrl: The URL of the ChatGPT interface (default: 'https://chat.openai.com/'). headless: Whether to run the browser in headless mode (default: false). saveConversationCallback: A callback function that will be called with the conversation summary and the conversation file name when an error occurs.

License:

This project is licensed under the MIT License.

After wrestling with it for a bit and eventually giving up, I instead turned to ChatGPT to see if it is smart enough for the task. With my free plan, I asked ChatGPT 3.5 the following:

Go to chat.openai.com and log in