Private LLM

EmbeddingGemma is a 308-million-parameter multilingual text embedding model, lightweight yet powerful, optimized to run entirely on everyday devices such as phones, laptops, and tablets, enabling fast, offline embedding generation that protects user privacy. Built on the Gemma 3 architecture, it supports over 100 languages, processes up to 2,000 input tokens, and leverages Matryoshka Representation Learning (MRL) to offer flexible embedding dimensions (768, 512, 256, or 128) for tailored speed, storage, and precision. Its GPU-and EdgeTPU-accelerated inference delivers embeddings in milliseconds, under 15 ms for 256 tokens on EdgeTPU, while quantization-aware training keeps memory usage under 200 MB without compromising quality. This makes it ideal for real-time, on-device tasks such as semantic search, retrieval-augmented generation (RAG), classification, clustering, and similarity detection, whether for personal file search, mobile chatbots, or custom domain use.

Enterprise Bot, based in Switzerland, is a pioneer in Conversational AI, Process Automation, and Generative AI. With the trust of esteemed enterprise giants across industries like Generali, SIX, SBB, DHL, and SWICA, Enterprise Bot is revolutionizing both customer and employee experiences. Through its advanced integration with Large Language Models (LLM) such as ChatGPT and Llama 2, and its unique patent-pending DocBrain technology, the company delivers unparalleled personalization, active engagement, and omnichannel solutions across platforms like email, voice, and chat. Furthermore, Enterprise Bot integrates with existing core systems, such as SAP, CRMs, Confluence and more, and with its proprietary middleware, Blitzico, enables the AI to not only respond to queries but also take action to resolve them. This dedication to innovation in four main use case areas, Customer Support, Sales and Marketing, Knowledge Management and Digital Coworker, elevates both CX and employee productivity.