Vectara, a conversational GenAI search and discovery platform, has released an all-new “Grounded Generation” capability that eliminates hallucinations in order to empower developers to build conversational AI products more easily and rapidly. This technology allows businesses to ask questions about their data and returns a natural language summary based on facts that are retrieved and cited to the company’s source data set. Vectara’s Hybrid Search also uses a combination of semantic search, Boolean, and exact keyword matching to improve search efficacy. Unlike other API providers, Vectara does not train its models on its customers’ data, and the client-configurable data retention enables organisations to discard the original documents and text after they have been indexed so that no residual data from the company remains in the index. The company raised $28.5m in seed funding to expand its strategic differentiators, superior information retrieval, and ease of use, and established a new board of advisers including Matei Zaharia, co-founder and chief technologist at Databricks. Vectara was founded on the prediction that within five years, every company will move beyond search to LLM-powered conversations with owned data assets, and the company is aiming to dominate the $51.8bn market for LLM applications.
Source link
“According to an official source, the US EPA shows no worry over the possibility of renewable diesel exceeding the Renewable Fuel Standard (RFS) mandates.”
The US Environmental Protection Agency (EPA) is currently not concerned about the recent increase in supply of biomass-based diesel, which...