Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (10.0%) to scientific vocabulary

Scientific Fields

Sociology Social Sciences - 87% confidence
Artificial Intelligence and Machine Learning Computer Science - 62% confidence
Last synced: 4 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: DebjyotiRay
  • Language: Python
  • Default Branch: main
  • Size: 17 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 8 months ago · Last pushed 5 months ago
Metadata Files
Readme Citation

README.md

Biomedical QA System with PubMed Citation Integration

A biomedical question answering system that provides answers with relevant scientific citations from PubMed.

Features

  • Answer biomedical questions with LLM-powered responses
  • Automatically retrieve relevant PubMed citations to support answers
  • Entity-based query optimization for improved citation relevance
  • Fallback to OpenAI GPT models when needed

Quick Start

  1. Install dependencies: bash pip install -r requirements.txt

  2. Set up your API keys in a .env file: OPENAI_API_KEY=your_openai_api_key NCBI_API_KEY=your_ncbi_api_key

  3. Run in interactive mode: bash python main.py --interactive

  4. Or ask a single question: bash python main.py --question "What genes are associated with Parkinson's disease?"

System Components

  • QA Handler: Coordinates the question answering process
  • Citations Module: Retrieves relevant scientific publications from PubMed
  • Model Module: Manages language model interaction and fallback mechanisms
  • Entity Extraction: Identifies biomedical entities for better search results

Documentation

See the docs directory for: - System architecture diagram - Training guide for fine-tuning models

Testing

Run the test script to verify the system is working properly: bash python biomed_qa_system_final/test_direct_fallback_live.py

Configuration

The system can be customized through the config.json file, including: - PubMed citation parameters - Model selection and configuration - Fallback model settings

Owner

  • Login: DebjyotiRay
  • Kind: user

Citation (citations.log)


      

GitHub Events

Total
  • Member event: 1
  • Push event: 2
  • Create event: 5
Last Year
  • Member event: 1
  • Push event: 2
  • Create event: 5

Dependencies

requirements.txt pypi
  • matplotlib >=3.6.0
  • networkx >=3.0.0
  • numpy >=1.22.0
  • openai >=1.0.0
  • pandas >=1.5.0
  • peft >=0.4.0
  • pytest >=7.0.0
  • python-dotenv >=1.0.0
  • python-json-logger >=2.0.0
  • requests >=2.30.0
  • torch >=2.0.0
  • transformers >=4.30.0
uv.lock pypi
  • pdnet 0.1.0