Latest Tutorials

Learn about the latest technologies from fellow newline community members!

  • React
  • Angular
  • Vue
  • Svelte
  • NextJS
  • Redux
  • Apollo
  • Storybook
  • D3
  • Testing Library
  • JavaScript
  • TypeScript
  • Node.js
  • Deno
  • Rust
  • Python
  • GraphQL
  • React
  • Angular
  • Vue
  • Svelte
  • NextJS
  • Redux
  • Apollo
  • Storybook
  • D3
  • Testing Library
  • JavaScript
  • TypeScript
  • Node.js
  • Deno
  • Rust
  • Python
  • GraphQL

From Prompt Engineering to Context Engineering: Better Patterns for Real AI Applications

Most failures in a real AI application trace back to missing or messy context, not a weak model. When a production system "hallucinates," the prompt wording is rarely the culprit. It's what the model could and couldn't see at inference time. That changes how we teach lead developers. Prompt…
Thumbnail Image of Tutorial From Prompt Engineering to Context Engineering: Better Patterns for Real AI Applications
Image of Author Dr. Dipen
Dr. Dipen
I am an AI/ML researcher with 150+ citations and 16 published research papers. I have three tier-1 publications, including Internet of Things (Elsevier), Biomedical Signal Processing and Control (Elsevier), and IEEE Access. In my research journey, I have collaborated with NASA Glenn Research Center, Cleveland Clinic, and the U.S. Department of Energy for various research projects. I am also an official reviewer and have reviewed over 100 research papers for Elsevier, IEEE Transactions, ICRA, MDPI, and other top journals and conferences. I hold a PhD from Cleveland State University with a focus on large language models (LLMs) in cybersecurity, and I also earned a master’s degree in informatics from Northeastern University.
•Last Updated:
00
Read Full Article

LoRA vs QLoRA for LLM Fine-Tuning: VRAM, Quality, and Deployment Costs

The LoRA vs QLoRA decision comes down to VRAM budget versus quality. LoRA keeps the base model in full precision and trains small adapter matrices on top. It needs more memory, but it recovers most of what full fine-tuning gives you. QLoRA quantizes the frozen model to 4-bit first, which is why it…
Thumbnail Image of Tutorial LoRA vs QLoRA for LLM Fine-Tuning: VRAM, Quality, and Deployment Costs
Image of Author Dr. Dipen
Dr. Dipen
I am an AI/ML researcher with 150+ citations and 16 published research papers. I have three tier-1 publications, including Internet of Things (Elsevier), Biomedical Signal Processing and Control (Elsevier), and IEEE Access. In my research journey, I have collaborated with NASA Glenn Research Center, Cleveland Clinic, and the U.S. Department of Energy for various research projects. I am also an official reviewer and have reviewed over 100 research papers for Elsevier, IEEE Transactions, ICRA, MDPI, and other top journals and conferences. I hold a PhD from Cleveland State University with a focus on large language models (LLMs) in cybersecurity, and I also earned a master’s degree in informatics from Northeastern University.
•Last Updated:
00
Read Full Article

I got a job offer, thanks in a big part to your teaching. They sent a test as part of the interview process, and this was a huge help to implement my own Node server.

This has been a really good investment!

Advance your career with newline Pro.

Only $40 per month for unlimited access to over 60+ books, guides and courses!

Learn More

What Supabase Is Used for in RAG Apps: pgvector, Auth, and Edge Functions for AI Builders

Watch: Supabase Edge Functions Explained by Supabase Supabase suits RAG apps needing pgvector, authentication, and serverless functions together. If you're teaching bootcamp students to build AI apps, it reduces early infrastructure work. One Postgres instance stores application data, embeddings,…
Thumbnail Image of Tutorial What Supabase Is Used for in RAG Apps: pgvector, Auth, and Edge Functions for AI Builders
Image of Author Dr. Dipen
Dr. Dipen
I am an AI/ML researcher with 150+ citations and 16 published research papers. I have three tier-1 publications, including Internet of Things (Elsevier), Biomedical Signal Processing and Control (Elsevier), and IEEE Access. In my research journey, I have collaborated with NASA Glenn Research Center, Cleveland Clinic, and the U.S. Department of Energy for various research projects. I am also an official reviewer and have reviewed over 100 research papers for Elsevier, IEEE Transactions, ICRA, MDPI, and other top journals and conferences. I hold a PhD from Cleveland State University with a focus on large language models (LLMs) in cybersecurity, and I also earned a master’s degree in informatics from Northeastern University.
•Last Updated:
00
Read Full Article

Stemming vs Lemmatization for LLM Pipelines: What Still Matters for RAG Search in 2025

This preprocessing choice happens before documents are indexed into the vector store. The two methods diverge in execution: one relies on algorithmic truncation rules, the other on grammatical rules to identify the base form of a word. This operational difference directly affects system design.…
Thumbnail Image of Tutorial Stemming vs Lemmatization for LLM Pipelines: What Still Matters for RAG Search in 2025
Image of Author Dr. Dipen
Dr. Dipen
I am an AI/ML researcher with 150+ citations and 16 published research papers. I have three tier-1 publications, including Internet of Things (Elsevier), Biomedical Signal Processing and Control (Elsevier), and IEEE Access. In my research journey, I have collaborated with NASA Glenn Research Center, Cleveland Clinic, and the U.S. Department of Energy for various research projects. I am also an official reviewer and have reviewed over 100 research papers for Elsevier, IEEE Transactions, ICRA, MDPI, and other top journals and conferences. I hold a PhD from Cleveland State University with a focus on large language models (LLMs) in cybersecurity, and I also earned a master’s degree in informatics from Northeastern University.
•Last Updated:
00
Read Full Article

Use local AI Inference. AMD Ryzen Halo vs DGxSpark

Watch: Is STRIX Better than SPARK? Now Launching w/new Software: AMD's Ryzen AI Halo Developer Workstation by Level1Techs Local AI inference means running models on hardware you own, not paying per token to a cloud API. Two workstations lead this space right now: the AMD Ryzen AI Halo at $3,999 and…
Image of Author Dr. Dipen
Dr. Dipen
I am an AI/ML researcher with 150+ citations and 16 published research papers. I have three tier-1 publications, including Internet of Things (Elsevier), Biomedical Signal Processing and Control (Elsevier), and IEEE Access. In my research journey, I have collaborated with NASA Glenn Research Center, Cleveland Clinic, and the U.S. Department of Energy for various research projects. I am also an official reviewer and have reviewed over 100 research papers for Elsevier, IEEE Transactions, ICRA, MDPI, and other top journals and conferences. I hold a PhD from Cleveland State University with a focus on large language models (LLMs) in cybersecurity, and I also earned a master’s degree in informatics from Northeastern University.
•Last Updated:
00
Read Full Article

Email Newsletter

Free tutorials and tips delivered every week.

Trusted by 100,000+ developers!

Popular Topics