Rag All Techniques: learn text-based RAG methods

Understand the project

Practical overview

Use it when you want to inspect or adapt notebook-level implementations of text RAG techniques, especially document processing and retrieval choices.

Learners studying RAG pipelines and retrieval methods.
Developers adapting notebook examples into text-document question-answering prototypes.

Study a basic RAG pipeline from text ingestion through response generation.
Compare approaches to chunking, retrieval context, query transformation and reranking.
Adapt readable notebook implementations for a text-based RAG prototype.

Before you choose

The GitHub repository is public and reports an MIT license.

The notebooks and comments are in Chinese.
The repository focuses on text-based RAG and does not implement multimodal RAG.
The described stack includes OpenAI, NumPy and PyMuPDF; the project is a repository of examples rather than a hosted application.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Follow the repository’s described stages for a basic text-document RAG implementation.

Text data to load and preprocess.
Python libraries used by the repository include OpenAI and NumPy; PyMuPDF is also listed among its libraries.

A basic workflow that uses retrieved text as context for response generation.

The repository describes text-based RAG and says it does not implement multimodal RAG.
The implementation and comments are in Chinese.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 14 October 2026
Original website title: liu673/rag-all-techniques · Official homepage title · retained in its source language