🤖 AI-Powered Document Search & RAG Chat

Real transformer models running in your browser with Transformers.js

📊 Documents: 3 | 🤖 AI Models: Not loaded | 🧠 Embedding Model: Not loaded
🚀 Real AI Models! This system uses actual transformer models via Transformers.js.

🧠 Models Being Loaded:

Embedding Model: Xenova/all-MiniLM-L6-v2 (384-dimensional sentence embeddings)

Q&A Model: Xenova/distilbert-base-cased-distilled-squad (Question Answering)

LLM Model: Auto-selected GPT-2 or DistilGPT-2 (Transformers.js 3.0.0)

Size: ~100MB total (cached after first load)

Performance: CPU inference, ~2-8 seconds per operation

Status: ⏳ Loading library...

⚠️ First Load: Model downloading may take 1-2 minutes depending on your internet connection. Models are cached for subsequent uses.
🤖 Real AI Chat! Ask questions and get answers from actual transformer models.
💡 Try asking:
• "What is artificial intelligence?"
• "How does space exploration work?"
• "What are renewable energy sources?"
• "Explain machine learning in simple terms"
3
🚀 Pure LLM Chat! Chat with a language model (GPT-2 or Llama2.c) running in your browser.
💡 Try these prompts:
• "Tell me a story about space exploration"
• "Explain machine learning in simple terms"
• "Write a poem about artificial intelligence"
• "What are the benefits of renewable energy?"
100
0.7
🔮 Real semantic search! Using transformer embeddings to find documents by meaning.
5
📚 Expand your knowledge base! Upload files or paste text with real AI embeddings.

📁 Upload Files

📄
Drop files here or click to select
Supports: .md, .txt, .json, .csv, .html, .js, .py, .xml
OR

✏️ Manual Entry

🧪 Test the system to verify AI models are working correctly.