FeaturedRetrieval Augmented Generation
Think building your own Retrieval-Augmented Generation (RAG) system will give you a competitive edge? Think again. Companies are sinking months and hundreds of thousands of dollars into in-house AI projects, only to end up with sluggish, unsecure, and overpriced systems that can't hold a candle to existing solutions.
Read more
Vectara launches open-source Hallucination Evaluation Model (HEM) that provides a FICO-like score for grading how often a generative LLM hallucinates in Retrieval Augmented Generation (RAG) systems.
Vectara launches the open source Hughes Hallucination Evaluation Model (HHEM) and uses it to compare hallucination rates across top LLMs including OpenAI, Cohere, PaLM, Anthropic’s Claude 2 and more.
The top large language models along with recommendations for when to use each based upon needs like API, tunable, or fully hosted.
In RAG, retrieving the right facts from your data is crucial, and choosing the right embedding model to power your retrieval matters!
AI-powered search is everywhere – new projects, products and companies are appearing to solve age-old challenges. But how ‘good’ is an AI-powered search engine – and how can we measure this?
Hybrid search has the power to vastly improve in-app experience allowing users to find what they are looking for quickly, and allows tuning between semantic and lexical search
Learn about the benefits of Vectara’s new embedding model “Boomerang,” including how our version of Retrieval Augmented Generation (RAG), called Grounded Generation, is smarter than other systems
TL;DR In this blogpost we cover the importance of retrieval models for search and generative AI use-cases, and we announce the release of our new state-of-the-art multilingual retrieval model, named Boomerang, that is available for use in the Vectara platform. We compare performance numbers between Boomerang and several other embedding APIs and models and demonstrate Boomerang’s high quality retrieval and generalization capabilities. Finally we discuss real-life quality improvements seen by a Vectara design partner for their use-case.
How to properly chunk your text data to optimize performance of retrieval augmented generation
Connect our community channel.
Join our discussion channel.
Get news, company information.
Adopt best practices in projects.
Suggest your own ideas.
Ask your follow-up questions.
