Skip to main content
Hero Dark Pn The Embedding_Siyabasa API provides high-quality text embedding models specifically designed for the Sinhala language. Generate embeddings for Sinhala words, phrases, and sentences using our latest model UgannA_SiyabasaV2. These language-specific embeddings power advanced NLP tasks such as semantic search, text classification, and document clustering, delivering more accurate and context-aware results than traditional keyword-based approaches. Key features:
  • Language-specific: Optimized exclusively for Sinhala text
  • 300-dimensional embeddings: Rich semantic representations
  • FastText architecture: Proven performance for morphologically rich languages

​
What Are Embeddings?

Text embeddings are numerical representations—or vectors—of words and sentences. They capture the semantic relationships and contextual meaning of language, allowing machines to process and understand text in a way that’s similar to human comprehension. Models trained specifically on a single language provide a more nuanced and accurate understanding than broad, multilingual models.

​
Why Specialized Sinhala Embeddings Matter

While multilingual models exist, they often underperform for languages with unique linguistic characteristics like Sinhala. Our research shows that language-specific embeddings provide significantly better results for:
  • Semantic understanding of Sinhala’s rich morphology
  • Contextual accuracy in Sinhala sentence structures
  • Domain-specific applications tailored to Sinhala content

API Console