Prerequisites (Must)

Alright, let's get the ball rolling! Let's kick things off by ensuring you have everything you need installed on your computer. And remember, persistence is crucial in this journey.

Nailing a new framework flawlessly from the get-go is as rare as acing a complex algorithm on the first try. And finding joy in debugging? That's like getting used to a 3 AM alarm—tough, but part of the process. 🤷‍♀️

The magic happens when, after persistence. That's when you'll see the true power of your skills and the impact you can create. Plus, the frameworks we're diving into are designed for production-grade applications, meaning the potential for real-world impact is enormous and genuinely empowering.

Are you geared up? Let's embrace this challenge with enthusiasm. 😊 These steps aren't just for today; they're your stepping stones to the exciting world of open-source contributions. So, let's get to it!

Git, Python and Pip

  • Python 3.10 or 3.11 should be installed on your machine. If not, you can Download Python here.
  • Pip: Comes pre-installed with Python 3.4+. It is the standard package manager for Python. You can check if it's downloaded by typing the below command in your terminal/command prompt.
pip --version
  • If Pip is not installed, you'll get an error. In that case, you need to download and install Pip to manage project packages.
  • Git should be installed on your machine. If you've installed XCode (or its Command Line Tools), Git may already be installed. To find out, open a Terminal or Command Prompt, and enter git --version. If it's not installed, refer to this documentation and install it.

This key is required if you plan to use OpenAI models for embedding and generation.

If you are less confident with using open-source alternatives, using Open AI models is a good starting point. You can also go for other platforms such as Replicate, Eden AI, Cohere (feel free to Google – the list is endless).

Images for Cloud Deployment

We highly recommend deploying your project on a public cloud platform to give it real-world industry experience.

You can start by getting the Pathway BYOL image from the AWS Marketplace. It's free and will make the AWS deployment process easier later on.

What if you don't have Open AI credits for building your RAG project?

  • You can either experiment by adding ~$3 of credits for a convenient start.
  • You can use other hosted LLM services such as:
    • Google Gemini: 2 months of unlimited access
    • Mistral.ai: 5€ free credit upon sign-up
    • Groq: Offers inference from open-source LLMs with rate limits
    • Together AI: Inference from various open-source LLMs, 25$ free credit upon sign-up
    • Replicate: Inference with a free trial, though exact free usage limits are unclear
  • You can build locally with open source models that do not require any API credits.

Great news – we'll be showing how you can build your projects in all the three cases!

If you're using Windows OS. Great! You have another reason to use Docker.

The frameworks ahead only support Unix-like systems (such as Linux, macOS, and BSD). But the good news is that you have an easy fix.

If you are a Windows user, you can use Windows Subsystem for Linux (WSL) or Dockerize the app to run as a container. The latter (using Docker) is a much stronger recommendation. It's a popular tool with a lot of available documentation and we've added an introductory section for your convenience ahead.

But what is Docker and why is it important to learn?

Think of Docker as a shipping container for your app. Just as a shipping container can hold all sorts of goods (clothes, electronics, etc.) and can be transported anywhere in the world, Docker bundles your app and everything it needs to run into a 'container.' This makes it easy to share and run your app on any computer – thus making it easy for your project's reviewers/contributors to run your projects should they wish to do so. 😄