🌍 Cross-Lingual Document Retrieval

Powered by LiquidAI/LFM2-ColBERT-350M

Find semantically similar documents across different languages.

Supported Languages: English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish

🔍 Enter your query

Number of results to retrieve

1 12

📚 Document corpus

🤖 Technology (16 docs): AI, Quantum Computing
🌍 Environment (16 docs): Climate, Biodiversity
⚡ Energy (8 docs): Renewable Sources
🏥 Health (16 docs): Medicine, Mental Wellness
💼 Business (16 docs): Digital Economy, Startups
📖 Education (8 docs): Online Learning
🎭 Culture (8 docs): Global Connectivity
🚀 Science (8 docs): Space Exploration

📊 Search Summary

Examples

🔍 Enter your query	Number of results to retrieve

How it works: This demo uses the LiquidAI/LFM2-ColBERT-350M model with late interaction retrieval. The model encodes both queries and documents into token-level embeddings, enabling fine-grained matching across languages with high speed and accuracy.