How to Relearn LLMs & RAG in 2026: A 7-Step Roadmap with Free Resources

Bashiri Smith · Facebook reel · 2026-09-23 · 1:54 · 7,126 views · Open on Facebook

Topics: Start Here: Roadmaps & Strategy, Retrieval-Augmented Generation (RAG), Embeddings & Vector Databases · Level: beginner

Summary

Bashiri Smith lays out the order he would follow to relearn LLMs and RAG and become an AI engineer in 2026. There are seven steps: LLM fundamentals, prompt engineering, LLM APIs, embeddings and semantic search, vector databases, basic RAG, document processing and chunking, and advanced or hybrid retrieval. For each step he names a free video plus a course, often from DeepLearning.AI. He finishes with a checkpoint project and a pitch for his Skool community.

Key points

• Step 1, LLM fundamentals: watch Andrej Karpathy's LLM video, then take the Hugging Face LLM Course.
• Step 2, prompt engineering: 'prompt engineering is dead', but you still need to know how to talk to LLMs. Watch the Tech With Tim video, then take a DeepLearning.AI course.
• Start working with LLM APIs right away: watch an OpenAI API video, take a DeepLearning.AI course, and use a reference guide for other providers.
• Step 3, embeddings and semantic search: watch StatQuest's word embeddings video, then take a DeepLearning.AI course.
• Step 4, vector databases: watch IBM's intro video, then take DeepLearning.AI's 'Vector Databases: from Embeddings to Applications'.
• Step 5, basic RAG: watch freeCodeCamp's 2.5-hour RAG video, then take a DeepLearning.AI LangChain course.
• Step 6, document processing and chunking: watch Greg Kamradt's '5 Levels of Text Splitting for Retrieval', then take a DeepLearning.AI course. Step 7, advanced retrieval: watch Venelin's 15-minute hybrid retrieval video, then take 'Advanced Retrieval for AI'.
• Finish with a checkpoint project that covers LLM fundamentals, choosing a model provider, prompting, embeddings and RAG architecture. You should be able to explain why you made each design choice.

Resources mentioned

• [1hr Talk] Intro to Large Language Models (Andrej Karpathy) · video · youtube.com · free
  A video by Andrej Karpathy that introduces how large language models work.
  Also in: 6 Free Videos to Move from Software Engineer to AI Engineer (Bashiri Smith on Facebook · notes)
• Hugging Face LLM Course · course · huggingface.co · free
  Hands-on course on transformers, tokenizers and fine-tuning.
  Also in: AI Engineer Roadmap for 2026 in 60 Seconds (Bashiri Smith on Facebook · notes)
• Prompt Engineering Full Course (Tech With Tim) · video · youtube.com · free
  A Tech With Tim video on how to prompt LLMs well.
• ChatGPT Prompt Engineering for Developers · course · deeplearning.ai · free
  A DeepLearning.AI short course on prompt engineering. Free with a DeepLearning.AI account during its platform beta; certificates are paid.
• OpenAI with Python: A Step-by-Step Guide for Beginners (George Shakan) · video · youtube.com · free
  A video tutorial on starting to build with the OpenAI API (creator and title not shown).
• OpenAI API · tool · platform.openai.com · paid · recommended by both Bashiri Smith & Melvin Vivas
  OpenAI API documentation, including function calling and structured outputs.
  Also in: Livestream: Building a React Native ChatGPT App with Cursor and OpenAI (Melvin Vivas on X · notes), GPT-Live-1: OpenAI's Full-Duplex Voice Model for Voice Agents in the API (Melvin Vivas on X · notes), The 3 Levels of AI Engineering: LLM Apps → Production → Agentic Systems (Bashiri Smith on Facebook · notes), GPT Image 2 Adds Transparent Background Support in the OpenAI API (Melvin Vivas on X · notes) and 4 more
• Building Systems with the ChatGPT API · course · deeplearning.ai · free
  A DeepLearning.AI course on building with LLM APIs. Free with a DeepLearning.AI account during its platform beta; certificates are paid.
• OpenAI, Claude & Gemini API Tutorial in Python (Machine Learning Plus) · article · machinelearningplus.com · free
  A reference guide for working with LLM APIs from providers other than OpenAI (the exact source isn't shown).
• Word Embedding and Word2Vec, Clearly Explained!!! (StatQuest with Josh Starmer) · video · youtube.com · free
  StatQuest's visual explanation of word embeddings and how Word2Vec learns them.
  Also in: 6 Free Videos to Move from Software Engineer to AI Engineer (Bashiri Smith on Facebook · notes)
• Understanding and Applying Text Embeddings (DeepLearning.AI) · course · deeplearning.ai · free
  A DeepLearning.AI course on embeddings and semantic search. Free with a DeepLearning.AI account during its platform beta; certificates are paid.
• What is a Vector Database? Powering Semantic Search & AI Applications (IBM Technology) · video · youtube.com · free
  An IBM video introducing vector databases.
• Vector Databases: from Embeddings to Applications (DeepLearning.AI) · course · deeplearning.ai · free
  A DeepLearning.AI short course on how vector databases work and how to build applications with them. Free with a DeepLearning.AI account during its platform beta; certificates are paid.
• RAG from Scratch (freeCodeCamp) · video · youtube.com · free
  A freeCodeCamp video about two and a half hours long on building basic RAG (the exact title isn't shown).
  Also in: 6 Free Videos to Move from Software Engineer to AI Engineer (Bashiri Smith on Facebook · notes)
• LangChain Chat with Your Data · course · deeplearning.ai · free
  A DeepLearning.AI course on building RAG with LangChain. Free with a DeepLearning.AI account during its platform beta; certificates are paid.
• LangChain · tool · github.com · free · recommended by both Bashiri Smith & Melvin Vivas
  Open-source framework with ready-made integrations and common interfaces for connecting LLMs, embedding models, vector stores and tools.
  Also in: SWE-to-AI Engineer Plan for 2027: LLMs, RAG, Agents, Evals, Job Search (Bashiri Smith on Facebook · notes), Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers (Bashiri Smith on Facebook · notes), Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), LangChain vs. LangGraph Explained with One RAG Chatbot (Bashiri Smith on Facebook · notes) and 3 more
• 5 Levels of Text Splitting for Retrieval (Greg Kamradt) · video · youtube.com · free
  A video by Greg Kamradt that walks through chunking and text-splitting strategies for RAG, from simple to advanced.
• Preprocessing Unstructured Data for LLM Applications · course · deeplearning.ai · free
  A DeepLearning.AI course on document processing and chunking. Free with a DeepLearning.AI account during its platform beta; certificates are paid.
• Build Production-Ready Retrieval RAG Pipeline in LangChain | Hybrid Search (BM25), Re-ranking & HyDE (Venelin Valkov) · video · youtube.com · free
  A 15-minute video by Venelin Valkov on hybrid retrieval and advanced retrieval tactics.
• Advanced Retrieval for AI with Chroma (DeepLearning.AI) · course · deeplearning.ai · free
  A DeepLearning.AI short course on advanced retrieval techniques that improve RAG results. Free with a DeepLearning.AI account during its platform beta; certificates are paid.
• DeepLearning.AI · website · deeplearning.ai · free
  The gold-standard ML fundamentals course; you can audit it for free.
  Also in: Software Engineer to AI Engineer: Job Boards, Stack, Projects and Learning Sites (Bashiri Smith on Facebook · notes), 90-Day Plan to Land an AI Engineering Job: Benchmark, Learn, Build (Bashiri Smith on Facebook · notes)
• BASWE.Ai Engineer (Skool community) · community · skool.com · paid
  The creator's paid community and program, with an AI learning roadmap (including the full ops and evaluation track), daily calls with engineers and recruiters, resume and portfolio help, and a job-search pipeline.
  Also in: Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers (Bashiri Smith on Facebook · notes), Pointer to Bashiri Smith's Complete AI Engineer Roadmap for 2026 (Bashiri Smith on Facebook · notes), Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), How to Evaluate a RAG Pipeline: Retrieval vs. Generation (Interview Answer) (Bashiri Smith on Facebook · notes) and 76 more

Try this

• Work through the topics in order: LLM fundamentals, prompt engineering, LLM APIs, embeddings and semantic search, vector databases, basic RAG, chunking, then advanced or hybrid retrieval.
• For each topic, watch the recommended video first, then take the matching course.
• Start working with LLM APIs early, beginning with the OpenAI API, then try other providers.
• Build a checkpoint project once you've covered every topic.
• Be ready to explain why you chose your models and your retrieval pipeline design.
• A checkpoint project: an end-to-end RAG app where you choose the models, build the retrieval pipeline (embeddings, vector database, chunking, hybrid retrieval), and explain why you made each choice.