July 11, 2023, 3:30 p.m. | Venelin Valkov

Venelin Valkov www.youtube.com

Learn how to build a customer support chatbot that incorporates custom knowledge from an FAQ help center. With the assistance of an open-source LLM and free embeddings through LangChain, you'll learn how to construct a chatbot capable of delivering real-time responses (with streaming) on a single GPU (T4). We'll evaluate the chatbot's response quality by testing it with various questions.

Discord: https://discord.gg/UaNPxVD6tv
Prepare for the Machine Learning interview: https://mlexpert.io
Subscribe: http://bit.ly/venelin-subscribe

Join this channel to get access to the perks …

build center chatbot construct customer customer support embeddings faq free gpu knowledge knowledge base langchain learn llm real-time responses streaming support through

More from www.youtube.com / Venelin Valkov

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Senior Software Engineer, Generative AI (C++)

@ SoundHound Inc. | Toronto, Canada