FeaturedSemiconductor
The highly-technical vocabulary of the semiconductor industry requires models with specialized training, provided with direct access to rich, multimodal data and complex documents.
Read moreFeaturedSemiconductorCategories
Blog - page 12
All posts
Correcting Hallucinations in Large Language Models
In this blog post, we share the results of our initial experiments aimed at correcting hallucinations generated by Large Language Models (LLMs). Our focus is on the open-book setting, which encompasses tasks such as summarization and Retrieval-Augmented Generation (RAG).
You’re Not an Engineer. Why Should You Care About RAG?
Before we tackle the question at hand, let me provide some background on my journey to Vectara and how I reached this conclusion
Introducing Vectara Portal
A no-code environment for chat with your documents, powered by Vectara
Introducing User-Defined Functions for Vectara
Today, we’re incredibly excited to announce user-defined sorting functions for Vectara!
Introducing Vectara-Agentic
Enabling advanced RAG applications with Vectara Agentic
HHEM 2.1: A Better Hallucination Detection Model and a New Leaderboard
The upgraded HHEM-2.1 outperforms both GPT-3.5-Turbo and GPT-4 for hallucination detection and is powering our updated HHEM leaderboard.
Power & Precision: Enhancing Operational GenAI with Retrieval-Augmented Generation from Vectara
Discover how Vectara’s Retrieval-Augmented Generation (RAG) capabilities elevate Incorta’s Nexus platform, enabling organizations to effectively harness the power of GenAI with precise and contextually relevant data.
The Natural Diversity of Vectara: A Reflection of Our Culture
Thank you to some of our local employees and investors for attending our July team building lunch.
Mockingbird is a RAG-Specific LLM that Beats GPT 4, Gemini 1.5 Pro in RAG Output Quality
In response to growing enterprise concerns over data security and the quality of retrieval-augmented generation (RAG), Vectara is proud to introduce Mockingbird, an LLM fine-tuned specifically for RAG. Mockingbird achieves the world’s leading RAG output quality and hallucination mitigation, making it perfect for enterprise RAG and autonomous agent use cases.