feat: add proper README.md

README.md

@@ -1,47 +1,11 @@
 
-# Paper-Mate - your personal assistant for exploring arXiv papers
-
-### Run Paper Mate
-
-1. Clone the repository:
-
-```bash
-git clone https://github.com/mechark/paper-mate.git
-```
-
-2. Open the working directory:
-
-```bash
-cd paper-mate
-```
-
-3. Place the  ``vector_store`` directory inside the  ``/paper-mate``. Download vector_store <a href="https://drive.google.com/uc?export=download&id=1LhkfxMzpbhNNz0OLPt31nb8NYR0lekGB">here</a>
-4. Make sure Docker Engine is running, then build and start the containers:
-
-```bash
-docker compose up --build
-```
-
-You can set the language model you want to use via ``MODEL_NAME`` env variable (see other available variables in ``.env.example``). By default the project uses  ``llama3.2:3b`` model.
-
-🎉 Once <b>everything is up and running</b>, open http://localhost:8000 to checkout the setup!
-
-### Examples
-```
-1.
-> What is the NEMO paper all about?
-> NEMO proposes a system for extracting organization names from PubMed affiliation strings and normalizing them to a canonical organization name.
-The system achieves more than 98% f-score in extracting organization names, and it uses clustering based on local sequence alignment metrics and local learning based on finding connected components for normalization.
-
-2.
-> Do you know something about Indian system to help indians better understand each other? Because they may speak different languages. Can you name such systems? Mention paper names as well.
-> Yes, there are several systems and research papers that focus on helping Indians better understand each other by addressing the language barrier:
-
-"Anusaaraka: Overcoming the Language Barrier in India" (2001) - This system aims to build multilingual speech-to-speech machine translation systems connecting all Indian languages.
-
-MuRIL: Multilingual Representations for Indian Languages (2021) - This work focuses on improving multilingual language models to better represent and process Indian languages, which are often underrepresented in current models.
-
-Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification (2020) - While not specifically focused on machine translation, this paper discusses the importance of spoken language identification systems in a multilingual country like India to identify languages present in an audio sample.
-
-These systems and research papers aim to address the challenges posed by language diversity in India's education sector and promote inclusivity among Indians who speak different languages.
-```
+---
+title: Paper-Mate
+emoji: 📚
+colorFrom: purple
+colorTo: blue
+sdk: gradio
+sdk_version: "4.44.0"
+app_file: app.py
+pinned: false
+---