What is rag_patterns?

honestsoul/rag_patterns — explained in plain English

Analysis updated 2026-05-18

★ 29PythonAudience · developerComplexity · 2/5Setup · easy

Mindmap

mindmap
  root((rag_patterns))
    What it does
      Teaches five RAG patterns
      Uses simulated models
      No API keys needed
    Tech stack
      Python
      NumPy
      NetworkX
    Use cases
      Learning RAG architectures
      Hybrid search study
      Knowledge graph prototyping
    Audience
      Developers
      AI learners
    Patterns
      Hybrid and graph RAG
      Agentic and corrective RAG
      Multimodal RAG

mindmap root((rag_patterns)) What it does Teaches five RAG patterns Uses simulated models No API keys needed Tech stack Python NumPy NetworkX Use cases Learning RAG architectures Hybrid search study Knowledge graph prototyping Audience Developers AI learners Patterns Hybrid and graph RAG Agentic and corrective RAG Multimodal RAG

What do people build with it?

USE CASE 1

Learn how hybrid, graph-based, agentic, corrective, and multimodal RAG pipelines are structured.

USE CASE 2

Study a from-scratch BM25 keyword search implementation alongside vector similarity search.

USE CASE 3

Use the graph-based script as a starting point for building a knowledge graph from entities and relationships.

What is it built with?

PythonNumPyNetworkX

How does it compare?

	honestsoul/rag_patterns	adityasharmadotai-hash/docs-reader-rag-agent	alekseiul/hermes-researcher-agent
Stars	29	29	29
Language	Python	Python	Python
Setup difficulty	easy	easy	moderate
Complexity	2/5	2/5	2/5
Audience	developer	vibe coder	researcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

Only numpy and networkx are required, no API keys since models and embeddings are simulated.

So what is it?

This repository is a teaching collection of five small Python scripts, each one showing a different way to wire up a Retrieval-Augmented Generation system. RAG, in plain terms, is the technique of looking things up from a document store and then handing those snippets to a language model so it can write a better answer. The five scripts are kept simple on purpose: nothing calls a real cloud model, no API keys are needed, and the embeddings and LLM responses are faked with deterministic random numbers. The point is to see the shape of each pipeline, not to measure quality. The first script, hybrid RAG, runs two searches at once over the same documents. One uses dense vector similarity (the kind powered by neural embeddings) and the other uses BM25, a classic keyword scoring method written from scratch here. The two ranked lists are merged with Reciprocal Rank Fusion and the top results go to the model. The second script builds a knowledge graph with the networkx library, where people, companies, technologies, and locations become nodes and verbs like founded or ceo_of become labelled edges. A query first extracts entities, then walks the graph a few hops to gather a subgraph, then summarises that subgraph before sending it to the model. The third script, agentic RAG, sets up a planner that picks tools to call (vector search, web search, or SQL), runs them in a loop until confidence is high enough, and then asks a reasoner agent to write the final answer. The fourth script, corrective RAG, scores the retrieved chunks and branches on the verdict: keep them, rewrite the query and try again, or fall back to a simulated web search. The fifth script is multimodal, mapping text chunks, image captions, and tables into one shared vector space and re-ranking by the modality the query asks for. Dependencies are just numpy and networkx.

Copy-paste prompts

Prompt 1

Explain how the hybrid RAG script combines vector search and BM25 with Reciprocal Rank Fusion.

Prompt 2

Walk me through how the knowledge graph RAG script builds and queries its graph.

Prompt 3

What does the corrective RAG script do when retrieved chunks score poorly?

Prompt 4

How does the multimodal RAG script combine text, image captions, and tables into one search space?

Frequently asked questions