> ## Documentation Index
> Fetch the complete documentation index at: https://developers.remeinium.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# UgannA_SiyabasaV2

> Our flagship model represents a significant advancement in Sinhala language AI

### **Core Specifications**

* **Architecture**: FastText-based embeddings
* **Dimensions**: 300-dimensional vector space
* **Training Data**: Clean Sinhala corpus optimized for linguistic accuracy
* **Vocabulary**: \~500k Comprehensive coverage of Sinhala lexicon

### **Key Capabilities**

<Columns cols={2}>
  <Card title="Word Embeddings" icon="text-size">
    Generate dense vector representations for individual Sinhala words
  </Card>

  <Card title="Sentence Embeddings" icon="align-left">
    Create contextual embeddings for full Sinhala sentences
  </Card>

  <Card title="Semantic Search" icon="chart-scatter">
    Find semantically similar words and phrases
  </Card>

  <Card title="Similarity Analysis" icon="diagram-project">
    Compute cosine similarity between text elements
  </Card>

  <Card title="Document Processing" icon="file-doc">
    Semantic search in Documents (.txt, .csv, .tsv)
  </Card>
</Columns>

### Language-Specific Optimization

* Trained exclusively on high-quality Sinhala text Corpus. Dataset available at Huggingface: [**CleanSinhalaTextCorpus**](https://huggingface.co/datasets/Remeinium/CleanSinhalaTextCorpus)
* Optimized for Sinhala's grammatical structures
* Handles Sinhala compound words and morphology effectively

## Model Details

| Property                                                           | Description                                      |
| :----------------------------------------------------------------- | :----------------------------------------------- |
| **Model**                                                          | Embedding\_Siyabasa API<br />`UgannA_SiyabasaV2` |
| **Supported data types**<br />Input<br />Output                    | <br />Text<br />Text embeddings                  |
| **Token limits**<br />Input token limit<br />Output dimension size | <br />1000<br />300                              |
| **Version**<br />Model<br />API                                    | <br />V\_2.0<br />V\_1.0                         |
| **Latest update**                                                  | August 2025                                      |
| **Language**                                                       | `Sinhala` only                                   |