Tested in: Integrated with AETHON’s Virtual Lab platform for cross-domain dataset Q&A interaction.
Hard metrics:
30+ languages supported with automatic detection (no configuration required)
RSA-2048 per-token encryption on the VirtualLab channel
10-turn conversation history maintained per session
Top-3 document retrieval via pgvector cosine similarity (threshold 0.55, 384-dim embeddings)
Voice input supported via Whisper STT (WebM audio → transcription → LLM response)
2 integrated platforms: VirtualLab (live), NCSRD (in progress)
Open Source License:
Current licenses of VL: MIT License, BSD-3-Clause, CC0-1.0, GPL
Current licenses of USAL’s chatbot component: Apache 2.0
Commercial Streams: Virtual Lab SaaS subscriptions; Custom integration SLAs;
Proprietary Strategy: Software & Content Copyright
Open Source License:
Current licenses of VL: MIT License, BSD-3-Clause, CC0-1.0, GPL
Current licenses of USAL’s chatbot component: Apache 2.0
Commercial Streams: Virtual Lab SaaS subscriptions; Custom integration SLAs;
Proprietary Strategy: Software & Content Copyright