CoolFace
Apppublic

kamil-pytlak/SFSeeker

sourceHugging Facemitupdated 3y agoView on Hugging Face
0likes
App README

<h1 align="center"> <br> <img src="img/logo.jpg" alt="SFSeeker logo" width="250"> <br> Sci-Fi Seeker <br> </h1>

<h4 align="center">An AI assistant with a semantic engine/question writing tutor in Sci-Fi Stack Exchange service<br>built on top of <a href="https://streamlit.io/" target="_blank">Streamlit</a>.</h4>

<p align="center"> <a href="#features">Features</a> • <a href="#how-to-use">How To Use</a> • <a href="#contact">Contact</a> • <a href="#credits">Credits</a> • <a href="#license">License</a> </p>

[image]

<p align="center"> SF Seeker is an AI assistant designed for Sci-Fi Stack Exchange, utilizing an all-MiniLM-L6-v2 language model. It helps users improve their question-writing skills and find similar questions on the Sci-Fi Stack Exchange website. This tool leverages a database of 71,013 questions to locate semantically similar questions, reducing the likelihood of creating duplicate threads. Additionally, SF Seeker is in the process of developing a feature that identifies words in questions that affect the likelihood of receiving answers, assisting users in formulating more precise inquiries. This feature uses a model trained with gradient reinforcement based on TF-IDF features. </p>

Features

  • —🔎 Based on a database of 71,013 questions, it searches for the most semantically similar questions to the one entered by the user. This supports the process of fiding the same/similar questions already asked and prevents the creation of duplicate threads.
  • —👨‍⚕️ [IN PROGRESS] Indicates words in a question that have a negative and positive effect on the chance of getting an answer. It supports the process of arranging more precise questions. A model based on gradient reinforcement learned using TF-IDF features was used.

How To Use

There are two ways to use this app:

  1. 1.Via the website https://huggingface.co/spaces/kamil-pytlak/SFSeeker
  2. 2.Locally by cloning the repository (using git or by downloading it directly from the website), install the dependencies from the configuration file Pipfile and launch the app locally using a browser.
bash
# Clone this repository
$ git clone https://github.com/kamilpytlak/SFSeeker

# Go into the repository
$ cd SFSeeker

# Install pipenv (in case it's not installed) and, run pipenv shell and install dependencies
$ pip install pipenv
$ pipenv shell
$ pipenv install

# Ensure that the streamlit package was installed successfully.
$ streamlit hello

# Finally, run the app locally
$ streamlit run ./main.py

Contact

If you have any problems, ideas or general feedback, please don't hesitate to contact me at kam.pytlak@gmail.com. I'd really appreciate it!

Credits

This software uses the following open source packages:

License

MIT

GitHub @kamilpytlak &nbsp;&middot;&nbsp; LinkedIn kamil-pytlak