MTS Web Services (MWS), part of the MTS group, announces a significant expansion of the functionality of the cloud-based b2b platform for working with artificial intelligence. More than 40 different models are now available in MWS GPT, including leading Open Source LLMs in various sizes.
Increasing the number of available LLMs provides customers with access to a single environment for model comparison and testing, which accelerates the implementation of AI in business processes. Now companies can immediately assess which model is better able to handle specific cases: document analysis, report generation, customer support, or automation of routine operations.
Speech-to-text conversion models allow you to create voice assistants, automate audio transcription, and obtain conversational analytics.
One of the key innovations is the support of multi-agent architectures in the low-code constructor, which opens up opportunities for automating multitasking scenarios. Users can set up complex scenarios where a single orchestrator agent manages several highly specialized assistants, each of which performs its function using connected tools.
In addition, ChatUI introduced RAG (from the English Retrieval-Augmented Generation, a method in the field of artificial intelligence that combines generative models with search engines for external data sources) and Vision (this is the ability of the model to understand and process images, not just text). Users can now upload documents and images, and the AI will analyze their contents and extract extracts from long texts, answer questions about instructions, or describe graphic materials.
"We see businesses increasingly adopting generative AI, but many companies are faced with the challenge of choosing the right model and the complexity of integration. With the MWS GPT update, we are giving customers a ready-made tool with a wide range of LLM, multi-agent capabilities, and simple low-code development. Now you don't have to spend months on tests and customization — you can immediately deploy AI assistants, voice interfaces and complex automated workflows, saving time and resources," commented Pavel Voronin, CEO of MWS.
FineTune is currently available to a limited number of clients on the platform. It provides additional training for a pre–trained language model based on a specific dataset in order to adapt it to specific user tasks or improve the quality of work in a specific area. In the future, it will be available to everyone. In the near future, there will also be functionality for working with images.
The MWS GPT platform is available both in the cloud (with fast scaling on the MWS GPU infrastructure) and on-premise. MWS specialists provide full support during the deployment of the platform.
Please note that this press release is based on materials provided by the company. AK&M Information Agency shall not be held liable for its contents, nor for the legal and other consequences of its publication.

