Shadowgraph
About
Sign in

dinhanhx/gpu-friendly-rag

A very GPU-friendly implementation

0

stars

2

commits

Python

primary language

Oct 29, 2024

updated

nlp
python
retrieval-augmented-generation

README

A very GPU-friendly RAG implementation

A simple RAG tool for asking things related to a pdf file (in this project, it's about Don Quixote)

This project demonstrates how things can be implemented with GPU-friendly database and models. It uses

I use a NVIDIA A30 GPU to run this.

Setup

Python 3.10, miniconda

Install required packages, please see setup.sh for extra information

bash setup.sh

Run

It is strongly advised to reach each .py file before running any command. By doing so, you get to understand the project more.

At root project, to setup the vector database

python setup_db.py

At root project, to query something then have a language model answer

python rag.py

Great researcher/developer-friendly RAG frameworks

Contributors

dinhanhx

2 commits

Similar repos

NovaSearch-Team/RAG-Retrieval

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

1,129

shared topics

zbilgeozkan/rot-rag-project

The RoT RAG Project implements a Python-based RAG pipeline. Documents are ingested and split into…

0

shared topics

rasyosef/rag-with-phi-2-and-langchain

Retrieval Augmented Generation demo using Microsoft's phi-2 LLM and langchain

19

shared topics

cy0307/lm-rag-pipeline

Model

0

dkyol/RAG

RAG Pipeline implementation. Read in academic Journal to query

0

KRLabsOrg/verbatim-rag

Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT…

203

shared topics

stanford-oval/storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report…

31,218

shared topics

Flowerf19/RAG

RAG system for PDF documents: hybrid retrieval (semantic + BM25), query enhancement, and…

0

Languages

Python

91.9%

Shell

8.1%

dinhanhx/gpu-friendly-rag

A very GPU-friendly implementation

0

stars

2

commits

Python

primary language

Oct 29, 2024

updated

nlp
python
retrieval-augmented-generation

README

A very GPU-friendly RAG implementation

A simple RAG tool for asking things related to a pdf file (in this project, it's about Don Quixote)

This project demonstrates how things can be implemented with GPU-friendly database and models. It uses

I use a NVIDIA A30 GPU to run this.

Setup

Python 3.10, miniconda

Install required packages, please see setup.sh for extra information

bash setup.sh

Run

It is strongly advised to reach each .py file before running any command. By doing so, you get to understand the project more.

At root project, to setup the vector database

python setup_db.py

At root project, to query something then have a language model answer

python rag.py

Great researcher/developer-friendly RAG frameworks

Similar repos

NovaSearch-Team/RAG-Retrieval

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

1,129

shared topics

zbilgeozkan/rot-rag-project

The RoT RAG Project implements a Python-based RAG pipeline. Documents are ingested and split into…

0

shared topics

rasyosef/rag-with-phi-2-and-langchain

Retrieval Augmented Generation demo using Microsoft's phi-2 LLM and langchain

19

shared topics

cy0307/lm-rag-pipeline

Model

0

dkyol/RAG

RAG Pipeline implementation. Read in academic Journal to query

0

KRLabsOrg/verbatim-rag

Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT…

203

shared topics

stanford-oval/storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report…

31,218

shared topics

Flowerf19/RAG

RAG system for PDF documents: hybrid retrieval (semantic + BM25), query enhancement, and…

0

Contributors

dinhanhx

2 commits

Languages

Python

91.9%

Shell

8.1%