Get the latest tech news
Vectara raises $25M as it launches Mockingbird LLM for enterprise RAG applications
Vectara is rolling out a new purpose built large language model for enterprise RAG that could also help enable AI agent workflows.
The Vectara platform integrates multiple elements to enable a RAG pipeline, including the company’s Boomerang vector embedding engine. “We are releasing a new launch language model called Mockingbird which has been trained and fine tuned specifically to be more honest in how it comes up with conclusions and to stick to the facts as much as possible,” Amr Awadallah, co-founder and CEO of Vectara told VentureBeat in an exclusive interview. Vectara’s platform also provides explanations for the results and includes security features to protect against prompt attacks, which are important for regulated industries.
Or read this on Venture Beat
