Final additions

.github/workflows/check.yml

@@ -0,0 +1,14 @@
+name: Check file size
+on:
+  pull_request:
+    branches: [main]
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check large files
+        uses: ActionsDesk/[email protected]
+        with:
+          filesizelimit: 10485760 # 10MB, huggingface limit

.github/workflows/main.yml

@@ -0,0 +1,18 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://Rom89823974978:[email protected]/spaces/Rom89823974978/MDA main

README.md

@@ -1,9 +1,32 @@
 ---
-title: EU Explorer (MDA Assignment)      # the display name of your Space
-emoji: 🤖                         # a single emoji that represents your app
-colorFrom: purple                 # one of: red, yellow, green, blue, indigo, purple, pink, gray
-colorTo: indigo                   # another one from the same list, for the gradient
-sdk: docker                       # since you’re using a Dockerfile
-app_port: 4444                    # (optional) if your Docker container listens on a port other than 7860
-pinned: false                     # whether to pin this Space in your profile
+title: EU Explorer (MDA Assignment)   
+emoji: 🤖                         
+colorFrom: purple                 
+colorTo: indigo                   
+sdk: docker                       
+app_port: 4444                    
+pinned: false
 ---
+
+# Interactive Retrieval-Augmented Generation for Semantic Exploration of Horizon Europe Research Data
+
+**A Cloud-Native Web Application for Multilingual Question Answering and Research Trend Analysis**
+
+This project presents a scalable, cloud-native system that leverages Retrieval-Augmented Generation (RAG) to provide semantic access to the Horizon Europe research project database (CORDIS). Combining dense and sparse retrieval methods with advanced multilingual language models, the system enables users to ask natural language questions and receive document-grounded answers, complete with citations.
+
+The backend, built using FastAPI and integrated with tools like FAISS, Whoosh, and LangChain, supports both semantic and keyword search, hybrid retrieval, and re-ranking. A user-facing web application and chatbot interface make the system interactive and intuitive, allowing researchers, policymakers, and the public to explore EU-funded research projects in an intelligent, multilingual, and conversational manner.
+
+## Table of Contents
+
+- [Overview](#overview)
+- [Dataset: Horizon Europe Projects](#dataset-horizon-europe-projects)
+- [Features](#features)
+- [System Architecture](#system-architecture)
+- [Technologies Used](#technologies-used)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [Web Application](#web-application)
+  - [API Endpoints](#api-endpoints)
+- [Retrieval-Augmented Generation Pipeline](#retrieval-augmented-generation-pipeline)
+- [Limitations and Future Work](#limitations-and-future-work)
+