# langchain-ai/rag-from-scratch

Repository: https://github.com/langchain-ai/rag-from-scratch
Canonical: https://ross.abutalabs.com/products/rag-from-scratch
Language: Jupyter Notebook
License Family: other
Last push: 2025-06-26T03:16:10+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 28, release rhythm 35, longevity 67
- inputs: {"age_days": 946, "days_push": 433, "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 9196, forks 2176 (observed 2026-08-28T04:10:28.824226+00:00)

## What it is
A set of Jupyter notebooks and an accompanying YouTube video playlist from LangChain that teach retrieval-augmented generation (RAG) from first principles, covering indexing, retrieval, and generation. It is educational material rather than a production library.

## Use cases
- learn how rag works from scratch
- understand indexing and retrieval for llms
- tutorial on building retrieval augmented generation pipelines
- study rag techniques with worked notebooks
- ground llm answers in external documents

## When to choose
- you want to learn RAG concepts step by step with runnable notebooks
- you prefer video-plus-code learning material
- you are prototyping RAG pipelines with LangChain

## When to avoid
- you need a production-ready RAG framework to drop into an app
- you want a maintained software library with API stability guarantees
- you need a license-clear dependency for commercial use

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, llm-inference, machine-learning
- domain: large-language-models, tutorials, artificial-intelligence
- platform: python
- tags: jupyter-notebooks, educational, video-course, langchain, retrieval-augmented-generation

## Member repositories
- langchain-ai/rag-from-scratch (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.824226+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 2026-08-29T17:23:19.325055+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/rag-from-scratch (fetched 2026-08-28T04:10:28.824226+00:00, sha 0edbef94346f)
- Data as of 2026-08-30T08:39:29.467469+00:00.