# hamzafarooq/building-llm-applications-from-scratch

Code and Slides

Repository: https://github.com/hamzafarooq/building-llm-applications-from-scratch
Canonical: https://ross.abutalabs.com/products/building-llm-applications-from-scratch
Language: Jupyter Notebook
License Family: other
Last push: 2025-05-25T21:09:47+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 23, release rhythm 35, longevity 81
- inputs: {"age_days": 1146, "days_push": 465, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2390, forks 647 (observed 2026-08-28T04:06:43.340505+00:00)

## What it is
Open-sourced course materials (code and slides) for building LLM-powered applications from scratch, covering transformer architecture, retrieval-augmented generation, fine-tuning, and deployment. It includes 29 lessons and 6 real-world projects taught to professionals at Stanford, UCLA, and other institutions.

## Use cases
- learn to build llm applications from scratch
- understand transformer architecture in depth
- implement rag without langchain
- fine-tune and deploy open-source llms
- learn search and retrieval fundamentals for ai apps
- study course materials for building llm-powered systems

## When to choose
- you want a structured, instructor-led curriculum on LLM application development
- you want to understand retrieval systems and RAG at a foundational level rather than using pre-built frameworks
- you have Python and basic ML knowledge and want hands-on projects

## When to avoid
- you are a complete beginner without Python or ML background
- you want a production-ready library or framework rather than educational material
- you need a maintained software dependency - this is course content, not a tool

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, rag, llm-training, nlp, search-engine
- domain: large-language-models, machine-learning, tutorials, education
- platform: python
- tags: course-materials, jupyter-notebooks, transformer-architecture, fine-tuning, open-source-llms, slides, retrieval-augmented-generation, natural-language-processing

## Member repositories
- hamzafarooq/building-llm-applications-from-scratch (main) score 39

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:43.340505+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:34:29.925757+00:00, confidence not recorded.
  - readme: https://github.com/hamzafarooq/building-llm-applications-from-scratch (fetched 2026-08-28T04:06:43.340505+00:00, sha eac750484c4d)
- Data as of 2026-08-30T08:39:29.467469+00:00.