Features
GPU-accelerated KNN and ANN vector search
In-database embedding generation (multiple models)
LLM text generation (Llama, Mistral, Mixtral)
Summarization and translation tasks
Supervised learning: regression, classification, clustering
Fine-tune LLMs on custom data
HNSW and IVFFlat indexing
Data preprocessing: splitting and chunking
SQL API for all ML operations
Python and JavaScript SDKs
Colocate data and compute for low latency
Open-source deployment (self-hosted)
Cloud service with managed GPUs
Privacy and security (on-premises option)
Integrates with PyTorch, TensorFlow, Hugging Face
Domain-specific SLLM training on customer data
On-premises or dedicated EU-cloud deployment
Compliance with GDPR and EU AI Act
Collaborative evaluation tools for client teams
PhariaFiles for enterprise file processing
Tokenizer-free model TFree-HAT 7B
Alpha-MoE megakernel for faster tensor-parallel inference
Theoretical inference model for DeepSeek hardware
Secure handling of sensitive documents (90% faster search)
40% faster RFQ processing via AI agents
End-to-end support from ideation to deployment
Integration with internal knowledge worker workflows
