Picture by Writer | Canva
# Introduction
That is the second article in my newbie venture collection. In case you haven’t seen the primary one on Python, it’s value trying out: 5 Enjoyable Python Initiatives for Absolute Learners.
So, what’s generative AI or Gen AI? It’s all about creating new content material like textual content, photos, code, audio, and even video utilizing AI. Earlier than the massive language and imaginative and prescient fashions period, issues have been fairly totally different. However now, with the rise of basis fashions like GPT, LLaMA, and LLaVA, all the pieces has shifted. You may construct inventive instruments and interactive apps with out having to coach fashions from scratch.
I’ve picked these 5 initiatives to cowl a little bit of all the pieces: textual content, picture, voice, imaginative and prescient, and a few backend ideas like fine-tuning and RAG. You’ll get to check out each API-based options and native setups, and by the top, you’ll have touched all of the constructing blocks utilized in most fashionable Gen AI apps. So, Let’s get began.
# 1. Recipe Generator App (Textual content Technology)
Hyperlink: Construct a Recipe Generator with React and AI: Code Meets Kitchen
We’ll begin with one thing easy and enjoyable that solely makes use of textual content era and an API key, no want for heavy setup. This app enables you to enter a number of fundamental particulars like components, meal sort, delicacies choice, cooking time, and complexity. It then generates a full recipe utilizing GPT. You’ll discover ways to create the frontend type, ship the info to GPT, and render the AI-generated recipe again to the consumer. Right here is one other superior model of identical thought: Create an AI Recipe Finder with GPT o1-preview in 1 Hour. This one has extra superior immediate engineering, GPT-4, ideas, ingredient substitutions, and a extra dynamic frontend.
# 2. Picture Generator App (Steady Diffusion, Native Setup)
Hyperlink: Construct a Python AI Picture Generator in 15 Minutes (Free & Native)
Sure, you possibly can generate cool photos utilizing instruments like ChatGPT, DALL·E, or Midjourney by simply typing a immediate. However what if you wish to take it a step additional and run all the pieces regionally with no API prices or cloud restrictions? This venture does precisely that. On this video, you’ll discover ways to arrange Steady Diffusion by yourself laptop. The creator retains it tremendous easy: you put in Python, clone a light-weight net UI repo, obtain the mannequin checkpoint, and run an area server. That’s it. After that, you possibly can enter textual content prompts in your browser and generate AI photos immediately, all with out web or API calls.
# 3. Medical Chatbot with Voice + Imaginative and prescient + Textual content
Hyperlink: Construct an AI Voice Assistant App utilizing Multimodal LLM Llava and Whisper
This venture isn’t particularly constructed as a medical chatbot, however the use case suits nicely. You communicate to it, it listens, it could possibly have a look at a picture (like an X-ray or doc), and it responds intelligently combining all three modes: voice, imaginative and prescient, and textual content. It’s constructed utilizing LLaVA (a multimodal vision-language mannequin) and Whisper (OpenAI’s speech-to-text mannequin) in a Gradio interface. The video walks by means of setting it up on Colab, putting in libraries, quantizing LLaVA to run in your GPU, and stitching all of it along with gTTS for audio replies.
# 4. Nice-Tuning Fashionable LLMs
Hyperlink: Nice tune Gemma 3, Qwen3, Llama 4, Phi 4 and Mistral Small with Unsloth and Transformers
To this point, we’ve been utilizing off-the-shelf fashions with immediate engineering. That works, however if you’d like extra management, fine-tuning is the following step. This video from Trelis Analysis is without doubt one of the greatest on the market. Due to this fact, as a substitute of suggesting a venture that merely swaps a fine-tune mannequin, I needed you to focuse on the precise technique of fine-tuning a mannequin your self. This video exhibits you the right way to fine-tune fashions like Gemma 3, Qwen3, Llama 4, Phi 4, and Mistral Small utilizing Unsloth (library for quicker, memory-efficient coaching) and Transformers. It’s lengthy (about 1.5 hours), however tremendous value it. You’ll study when fine-tuning is smart, the right way to prep datasets, run fast evals utilizing vLLM, and debug actual coaching points.
# 5. Construct Native RAG from Scratch
Hyperlink: Native Retrieval Augmented Technology (RAG) from Scratch (step-by-step tutorial)
Everybody loves an excellent chatbot, however most crumble when requested about stuff outdoors their coaching information. That’s the place RAG is helpful. You give your LLM a vector database of related paperwork, and it pulls context earlier than answering. The video walks you thru constructing a totally native RAG system utilizing a Colab pocket book or your individual machine. You’ll load paperwork (like a textbook PDF), cut up them into chunks, generate embeddings with a sentence-transformer mannequin, retailer them in SQLite-VSS, and join all of it to an area LLM (e.g. Llama 2 by way of Ollama). It’s the clearest RAG tutorial I’ve seen for rookies, and when you’ve completed this, you’ll perceive how ChatGPT plugins, AI search instruments, and inner firm chatbots actually work.
# Wrapping Up
Every of those initiatives teaches you one thing important:
Textual content → Picture → Voice → Nice-tuning → Retrieval
In case you’re simply stepping into Gen AI and wish to really construct stuff, not simply play with demos, that is your blueprint. Begin from the one which excites you most. And bear in mind, it is okay to interrupt issues. That’s the way you study.
Kanwal Mehreen Kanwal is a machine studying engineer and a technical author with a profound ardour for information science and the intersection of AI with drugs. She co-authored the book “Maximizing Productiveness with ChatGPT”. As a Google Technology Scholar 2022 for APAC, she champions range and educational excellence. She’s additionally acknowledged as a Teradata Range in Tech Scholar, Mitacs Globalink Analysis Scholar, and Harvard WeCode Scholar. Kanwal is an ardent advocate for change, having based FEMCodes to empower girls in STEM fields.
