Skip to content

Harshit0722/MediTalk

Repository files navigation

MediTalk

Fine-tuned a large language model in order to apply it on a medical QnA dataset to make a medical question answering chatbot.

Features

Quick and Accurate Responses:

Get prompt and precise answers to your medical questions, eliminating the need for time-consuming research.

Comprehensive Medical Knowledge:

Access a vast database of medical resources and evidence-based practices to ensure reliable information.

Symptom Analysis:

Describe your symptoms, and MediTalk will provide insights and recommendations based on the information provided.

User-Friendly Interface:

Enjoy a seamless user experience with an intuitive and easy-to-use chatbot interface.

Collaboration with Experts:

MediTalk has been developed in collaboration with healthcare professionals and experts to ensure accuracy and quality.

Operation

Since we are in a very early development phase, hence, API is still in continuous improvement,

Run the notebook: MediTalk_(fine_tuned_execution) Put your question in the tokenizer input value in the first line of code in the third code block (cell)

Note: Please ensure that you install Python 3.7 or above on your system and use a GPU-based runtime environment.

Update:-

The first API is developed using Streamlit. Just follow these simple steps:- Open MediTalk_execution_using_st & run the code Follow the URL, copy your IP provided in the last step & using it as a passkey for the local tunnel services. Enjoy the web app interface

Contributing

We welcome contributions to enhance MediTalk and make it even more valuable to users. To contribute, please follow these steps:

Fork the repository. Create a new branch: git checkout -b feature/your-feature Make your changes and commit them: git commit -m 'Add some feature' Push to the branch: git push origin feature/your-feature Submit a pull request. Please ensure that your contributions align with the project's coding conventions and follow good software development practices.

License

This project is licensed under the BSD-3 license. Hence, it is free and open source.

Contact

If you have any questions, suggestions, or feedback, please feel free to reach out to us at sharma.harshit22701@gmail.com

Stay tuned for a functioning API and other updates very soon... Enjoy using MediTalk!

About

Fine-tuned a large language model in order to apply it on a medical QnA dataset to make a medical question answering chatbot.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors