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
NEW

5 Open-Source Stacks for Building AI Applications: LlamaIndex+Qdrant to DSPy+SQLite, Debug by Failure Mode

Choosing an open-source stack stopped being optional the moment a local Qdrant + LlamaIndex setup stalled on first retrieval. When you're building AI applications, every cold-start second compounds across users. Two failure modes keep showing up. Poor chunking splits context so no single chunk can…
Thumbnail Image of Tutorial 5 Open-Source Stacks for Building AI Applications: LlamaIndex+Qdrant to DSPy+SQLite, Debug by Failure Mode
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
NEW

Building AI applications: 5 moves from demo to deploy before wrong answers reach customers

Progressive rollout matters more than demo performance because AI systems fail quietly. You push a prompt change, tests pass, and a week later users report degraded answers with no exception thrown. Some research and analyst forecasts suggest many GenAI pilots and agentic AI projects stall before…
Thumbnail Image of Tutorial Building AI applications: 5 moves from demo to deploy before wrong answers reach customers
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
NEW

Fine-Tuning LLMs: When to Use SFT, RLHF, or DPO and How Quantization Affects Memory

Before we get into it, the short version: Two tables below show memory, quality, and hardware trade-offs across fine-tuning methods. First table covers general characteristics. Summary blocks after it explain when you'd pick each approach. Memory summary: Full fine-tuning updates every weight, so…
Thumbnail Image of Tutorial Fine-Tuning LLMs: When to Use SFT, RLHF, or DPO and How Quantization Affects Memory
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
NEW

How to Fine-Tune LLMs: LoRA vs Full Fine-Tuning Trade-offs

You can't pick how to fine-tune an LLM based on vague rules of thumb. The decision hinges on compute limits, task type, and how much accuracy you're willing to trade. Full fine-tuning updates every parameter in the model, giving you maximum task performance but requiring substantial GPU memory for…
Thumbnail Image of Tutorial How to Fine-Tune LLMs: LoRA vs Full Fine-Tuning Trade-offs
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
NEW

GPTQ vs AWQ on SageMaker: Faster AI Inference

Two formats, two bets about which weights matter. GPTQ compresses a trained model to 4 bits in a single pass. It quantizes one weight column at a time, then uses second-order sensitivity data to spread that rounding error across the weights it hasn't touched yet. AWQ goes another way. It finds the…
Thumbnail Image of Tutorial GPTQ vs AWQ on SageMaker: Faster AI Inference
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 200,000+ developers!

Popular Topics