LLM Inference Architecture

Building a Local LLM Inference API for Semantic Similarity

At whatisgoing.com, we needed a reliable way to extract named entities from multilingual news articles — especially Arabic news — where the same entity can appear in different linguistic forms. For example: “The Ukraine War” and “The Russian Invasion” both refer to the same geopolitical event — the ongoing conflict in Eastern Europe — yet share no overlapping words. Traditional keyword or similarity-based methods fail to capture such semantic equivalence. ...

October 5, 2025 · 6 min · Ahmed Magdy