pguso/rag-from-scratch
Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.
This project helps software developers understand and implement Retrieval-Augmented Generation (RAG) systems. It breaks down the process of turning unstructured text documents into numerical representations, storing them efficiently, and then using a query to retrieve the most relevant information. Developers can use this to build applications that provide highly accurate, context-aware answers from custom knowledge bases using local language models, rather than relying on external APIs.
1,239 stars. Actively maintained with 3 commits in the last 30 days.
Use this if you are a software developer looking to deeply understand RAG, build RAG systems from scratch with local components, and avoid black-box implementations or cloud APIs.
Not ideal if you are an end-user simply looking for a ready-to-use application to query your documents, or if you prefer using managed RAG services and high-level SDKs.
Stars
1,239
Forks
135
Language
JavaScript
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/pguso/rag-from-scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
microsoft/RAG_Hack
Hack Together: RAG Hack | Register, Learn, Hack
intersystems-community/iris-vector-rag
Enterprise RAG pipelines with native IRIS vector search. 6 production implementations with RAGAS...
huangjia2019/rag-project01-framework
[RAG训练营] u.geekbang.org/subject/airag/1009927 这是我用Cursor自行制作的RAG Framework，好处是可以掌控RAG每一个环节的教学细节。
fivetran/dbt_unified_rag
Fivetran dbt package designed to generate an end model and Cortex Search Service (for Snowflake...
BUAADreamer/EasyRAG
Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛...