# ed-donner/llm_engineering

Repo to accompany my mastering LLM engineering course

Repository: https://github.com/ed-donner/llm_engineering
Canonical: https://ross.abutalabs.com/products/llm_engineering
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-08-22T12:54:55+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 52
- inputs: {"age_days": 732, "days_push": 11, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7157, forks 7002 (observed 2026-08-28T04:09:56.280983+00:00)

## What it is
A companion repository of Jupyter Notebook exercises and projects for Ed Donner's 'Mastering LLM Engineering' course, an 8-week program covering building applications with large language models. It includes hands-on projects using tools like Ollama and Llama 3.2, progressing from basics to advanced LLM engineering techniques.

## Use cases
- learn llm engineering from scratch
- build projects with local llms using ollama
- follow an 8-week structured llm course
- practice building rag and agent applications
- get started with llama 3.2 on a home computer
- supplement a udemy course with runnable notebooks

## When to choose
- you want a structured, project-based path to learning LLM engineering
- you prefer hands-on Jupyter notebooks over reference documentation
- you want to run local models like Llama 3.2 with Ollama
- you are taking or considering the accompanying Udemy course

## When to avoid
- you need production-ready LLM tooling rather than educational material
- you want a maintained library with an API instead of course code
- you cannot run local models and lack API access to commercial LLMs

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, rag, agent-framework, prompt-engineering, machine-learning
- domain: large-language-models, artificial-intelligence, tutorials, education, developer-tools
- platform: python, cross-platform, self-hosted
- tags: course-materials, jupyter-notebooks, udemy-course, ollama, hands-on-projects, llm-engineering

## Member repositories
- ed-donner/llm_engineering (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:56.280983+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 2026-08-29T17:39:59.493519+00:00, confidence not recorded.
  - readme: https://github.com/ed-donner/llm_engineering (fetched 2026-08-28T04:09:56.280983+00:00, sha 0487bc25bd17)
- Data as of 2026-08-30T08:39:29.467469+00:00.