Webinar: deploying a knowledge-based chatbot with RAG in production
Join our hands-on webinar to explore the deployment of a knowledge-based chatbot using RAG in a production environment.
This implementation leverages open-source technologies and is powered by NVIDIA® H100 Tensor Core GPUs. We will also discuss integration with Kubernetes, Cuda, Triton Server, TensorRT, Milvus, PyTorch, and Llama2.
May 16, Thursday, 17:00 (GMT+2)
For who
CTO, technical managers, product managers, ML engineers, MLOps engineers, and anyone who is looking for solutions alternative to classic LLMs.
When
May 16, Thursday, 17:00 (GMT+2). We’ll finish around 18:00 after a Q&A part.
Where
Zoom. You will receive the link after registration.
During this session, we will cover:
- Techniques for deploying RAG in a production setting using open source tools.
- The foundational architecture of RAG, customized for efficient scalability in production environments.
- A live demonstration of the chatbot deployment, emphasizing practical deployment strategies and operational considerations.
Boris Popov, CSA
Boris Popov, CSA
Boris is an IT specialist with 18 years of experience in the tech industry, specializing in scalable, secure cloud infrastructures.
Currently he is focusing on development of an advanced ML platform to boost business efficiency.
His expertise includes .NET, Java, Python, Kubernetes, and Databases, among others.
