1 / 10
🔍

Information Retrieval

Google Search Engine Version 2.0

Discover news articles from 1987 with advanced search capabilities

Main Features

⌨️
Search By Text
🎙️
Search By Voice
📷
Search By Image
✨
Summarization
⚙️
Advanced Filters

Documents

📰

Reuters News Articles

18,594

Documents Indexed

Workflow: ETL Pipeline & Search Pipeline

📊
Extract
  • XML → JSON
  • EDA
  • Advanced Analysis
  • Reporting
🪄
Transform
  • Preprocessing
  • Clustering
  • Data Mining
  • Entity Extraction
  • Geo Extraction
  • Encoding
  • Postprocessing
💾
Load
  • JSON Export
  • Index Mapping
  • Bulk Indexing
⌨️
Search: Text
  • Autocompletion
  • Semantic + Exact
  • Reranking
🎙️
Search: Voice
  • Record Audio
  • ASR Processing
  • Text Search
📷
Search: Image
  • OCR/Captioner
  • Text Extraction
  • Text Search
✨
Summarization
  • Generate Summary
  • Points of Interest
  • Groundness Score
  • Debug Details

Search: Text (Hybrid)

⌨️ Text Search

  • ✍️ Autocompletion
  • 🧠 Semantic Search
  • 🎯 Exact Search
  • ⭐ Quality Reranking
  • 🔀 Cross Encoder Reranking
📋 Results: Top 20 Documents

Search: Voice (ASR)

🎙️Voice Search

  • 🎤 Recording Voice (Bytes)
  • 🔊 Convert to WAV
  • 🤖 ASR Processing
  • 📝 Text Generation
  • 🕵️‍♀️ Inverse Normalization Check
  • 🔄 NeMo Curator (if needed)
  • ➡️ Route to Text Search
📋 Results: Top 20 Documents

Search: Image (OCR / Caption)

📷 Image Search

  • 📸 Browse Image
  • 🧐 Paddle Model Analysis
  • 📄 Document → OCR Text Extraction
  • 🌄 Normal Image → Captioner Model
  • 🕵️‍♀️ Inverse Normalization Check
  • 🔄 NeMo Curator (if needed)
  • ➡️ Route to Text Search
📋 Results: Top 20 Documents

Advanced Filtration

📅 Date
🌍 Geographic References
🔑 Keyword
🌐 Domain
📚 Content Type
🏷️ Topics
📍 Places
🏢 Organizations
👥 People
💱 Exchanges
🃏 Identities
🧭 Geographic Points
📋 Results: Top 20 Documents

Summarization

✨ AI Summarization

  • 📥 Input: Retrieved Documents
  • 📝 Generate Summary (Overview)
  • ⭐ Points of Interest
  • ✅ Groundness Score
  • 🐛 Debugging Details
Output: Comprehensive Summarization & Points of Interest

Friendly UI

🎨 User Interface

📄 Document Card 1
📄 Document Card 2
📄 Document Card 3
📄 Document Card 4
📄 Document Card 5
📄 ... (Top 20 Total)

✨ AI Summarization

  • Overview
  • Key Points
  • Groundness Score
  • Debug Details

Project Management

🎯 Tasks

🪄 ETL Pipeline
📊 Data Analysis
⌨️ Search By Text
📷 Search By Image
🎙️ Search By Voice
✨ Summarization
🌐 Backend
🎨 Frontend

🏆 Team

  • 🎖️ Ismael Mousa
  • 🎖️ Mohammed Ali
  • 🎖️ Yazan Ashour
  • 🎖️ Mohammed Amad