# NirDiamant/RAG_Techniques

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Repository: https://github.com/NirDiamant/RAG_Techniques
Canonical: https://ross.abutalabs.com/products/rag_techniques
Homepage: https://diamant-ai.com
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: rag, tutorials, langchain, llama-index, llms, python, ai, llm, embeddings, nlp, openai, retrieval-augmented-generation, vector-database, agentic-rag, generative-ai, gpt, machine-learning, semantic-search
Last push: 2026-08-26T13:27:45+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 47, longevity 55
- inputs: {"age_days": 781, "days_push": 7, "days_rel": 140, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 29232, forks 3567 (observed 2026-08-28T04:11:53.186883+00:00)

## What it is
A community-driven collection of 42+ runnable Jupyter notebook tutorials covering Retrieval-Augmented Generation (RAG) techniques from foundational to advanced, built with tools like LangChain and Llama-Index. Each notebook explains the intuition, provides working code, and links references for building accurate, context-rich retrieval systems.

## Use cases
- learn how to build a rag pipeline from scratch
- improve retrieval accuracy for llm question answering over documents
- compare rag chunking and embedding strategies with runnable code
- implement agentic rag and query routing techniques
- evaluate rag systems with metrics like faithfulness and relevance
- find tutorials on semantic search with vector databases
- study production rag patterns before building a chatbot over my docs

## When to choose
- you want hands-on, notebook-based learning of RAG techniques with code you can run and adapt
- you need a broad survey from basic to cutting-edge RAG methods in one place
- you are prototyping a retrieval-augmented system and want reference implementations in LangChain or Llama-Index

## When to avoid
- you need a production-ready RAG framework or library to drop into your app rather than tutorials
- you want a non-Python or non-notebook-based solution
- you need a maintained software package with API stability guarantees - this is educational material, not a library

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, nlp, machine-learning, search-engine, vector-database, prompt-engineering
- domain: large-language-models, artificial-intelligence, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, langchain, llama-index, embeddings, semantic-search, agentic-rag, educational, retrieval-augmented-generation, natural-language-processing, search

## Member repositories
- NirDiamant/RAG_Techniques (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:53.186883+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 2026-08-29T16:53:08.798230+00:00, confidence not recorded.
  - readme: https://github.com/NirDiamant/RAG_Techniques (fetched 2026-08-28T04:11:53.186883+00:00, sha e93438ffd66e)
  - homepage: https://diamant-ai.com (fetched 2026-08-29T07:50:15.653051+00:00, sha b674eb24f089)
- Data as of 2026-08-30T08:39:29.467469+00:00.