VOOZH about

URL: https://huggingface.co/Biomed-imaging-lab/NeuroRAG

⇱ Biomed-imaging-lab/NeuroRAG · Hugging Face

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

NeuroRAG

AI Assistant for Neurobiologists

Table of Contents

Overview

NeuroRAG is a cutting-edge open-source project designed to revolutionize language processing in the fields of neurobiology, medicine, and psychology. By seamlessly integrating advanced language models and graph-based operations, NeuroRAG empowers users to effortlessly grade documents, evaluate answers, and rewrite queries for enhanced information retrieval. Ideal for researchers, educators, and AI enthusiasts seeking to unlock the full potential of language processing technologies.

👁 The NeuroRAG system architecture
The NeuroRAG system architecture. Diagram shows the multi-agent workflow: query input → routing → retrieval → filtering → ensemble answer generation with multiple LLMs, including hallucination and relevance checks. (a) - Query Transformation Chains; (b) - HyDE; (c) - Retrievers; (d) - Routing llm; (e) - Document grader chain; (f) - Ensembling of LLMs; (g) - Validation chain

Results (evaluation on biomedical datasets in QA task)

Datasets GPT4-o Mistral Large Llama3.3 70B BioMistral NeuroRAG
Medical Genetics 0.9500 0.8600 0.9400 0.9400 0.9600
College Biology 0.9167 0.9514 0.9236 0.9306 0.9722
College Medicine 0.8382 0.82664 0.7977 0.7861 0.8728

Accuracy on Biological MMLU Datasets.

Metrics GPT4-o Mistral Large Llama3.3 70B BioMistral NeuroRAG
CosSim 0.6005 0.6008 0.6015 0.4953 0.6346
BLEU 0.0233 0.0183 0.0122 0.0018 0.0166
ROUGE-1 0.2973 0.2963 0.2570 0.2349 0.2738
ROUGE-L 0.1601 0.1542 0.1471 0.2082 0.1744

Perfromance metrics (Cosine Similarity, BLEU, ROUGE-1, ROUGE-L) on the MEDIQA Dataset with String Answers.

Features

Project Structure

Project Index

Getting Started

Prerequisites

Before getting started with NeuroRAG, ensure your runtime environment meets the following requirements:

  • Programming Language: Python
  • Package Manager: Pip

Installation

Install NeuroRAG using one of the following methods:

Build from source:

  1. Clone the NeuroRAG repository:
❯ git clone https://github.com/Biomed-imaging-lab/NeuroRAG
  1. Navigate to the project directory:
❯ cd NeuroRAG
  1. Install the project dependencies:

Using pip   👁 Image

❯ pip install -r requirements.txt

Usage

Run NeuroRAG streamlit app using the following command:

❯ docker build -t neurorag-app .

❯ docker run -p 8501:8501 --add-host=host.docker.internal:host-gateway -e HTTP_PROXY="http://host.docker.internal:2080" -e HTTPS_PROXY="http://host.docker.internal:2080" -e OLLAMA_HOST="http://host.docker.internal:11434" -e NO_PROXY="localhost,127.0.0.1,host.docker.internal" neurorag-app

Contributing

License

This project is protected under the Apache License 2.0 License. For more details, refer to the LICENSE file.

Authors

Vladimir Skvortsov1, Ivan Zolin1, 2, Vyacheslav Chukanov1, Ekaterina Pchitskaya1

  1. Laboratory of Biomedical Imaging and Data Analysis, Institute of Biomedical Systems and Biotechnology, Peter the Great St. Petersburg Polytechnic University
  2. ITMO University
Downloads last month

-

Downloads are not tracked for this model. How to track

Model tree for Biomed-imaging-lab/NeuroRAG

Finetuned
(1)
this model

Datasets used to train Biomed-imaging-lab/NeuroRAG