https://github.com/kanugurajesh/learnrag
Implementation of all rag types
https://github.com/kanugurajesh/learnrag
docker docker-compose llama3 ollama python3 qdrant
Last synced: 2 months ago
JSON representation
Implementation of all rag types
- Host: GitHub
- URL: https://github.com/kanugurajesh/learnrag
- Owner: kanugurajesh
- Created: 2025-09-07T03:21:39.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-10-03T05:23:53.000Z (9 months ago)
- Last Synced: 2025-10-03T07:16:52.151Z (9 months ago)
- Topics: docker, docker-compose, llama3, ollama, python3, qdrant
- Language: Python
- Homepage:
- Size: 24.4 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# RAG
```
rag-collection/
│── README.md # Overview of repo + explanations
│── requirements.txt # Common dependencies
│── utils/ # Shared code: embedding utils, vector DB wrapper, evaluation metrics
│
├── 01-vanilla-rag/ # Classic retrieval + generation
│ ├── app.py
│ ├── retriever.py
│ └── README.md
│
├── 02-rag-with-reranker/ # Retriever + reranker
│ ├── app.py
│ └── README.md
│
├── 03-conversational-rag/ # Multi-turn chat + query rewriting
│ ├── app.py
│ └── README.md
│
├── 04-self-rag/ # LLM decides retrieval strategy
│ ├── app.py
│ └── README.md
│
├── 05-hyde/ # Hypothetical document embeddings
│ ├── app.py
│ └── README.md
│
├── 06-fid/ # Fusion-in-decoder style
│ ├── app.py
│ └── README.md
│
├── 07-adaptive-rag/ # Dynamic retrieval
│ ├── app.py
│ └── README.md
│
├── 08-graph-rag/ # Graph-based retrieval
│ ├── app.py
│ └── README.md
│
├── 09-multihop-rag/ # Step-by-step retrieval reasoning
│ ├── app.py
│ └── README.md
│
├── 10-tool-augmented-rag/ # SQL/API + vector DB hybrid
│ ├── app.py
│ └── README.md
│
└── 11-experimental/ # New ideas (memory, clustering, generative fusion, etc.)
├── memory-rag/
├── clustered-rag/
└── generative-fusion-rag/
```