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.
Read moreCategories
Blog - page 9
All posts
Managing Vectara’s API Keys Programmatically
Vectara has had an ability to manage API keys via the Console, and even allowed indexing API keys for several months, but up until today, we’ve never released this functionality via public APIs.
Vectara RAG Hackathon
Learn how SomoSim improved their educational content search with Vectara’s trusted GenAI platform, enabling practitioners to more quickly, easily, and accurately find exactly what they are looking for, regardless of how they ask.
Conversational AI: The First Step to Interacting With Your Data
Conversational AI has absolutely transformed the way we interact with our data. If you are yet to experience this as a consumer or business user, then you’re in for a real awakening. Having a conversation with website data as a customer can simplify your decision making process while asking complex questions to your business data can help you find instant answers. These are two practical use cases for conversational AI that can be adopted off the shelf. Let us explain how this is possible.
Retrieval Augmented Generation (RAG) Done Right: Database Data
Ingesting data from your database into Vectara: a step by step guide.
Get Diverse Results and Comprehensive Summaries with Vectara’s MMR Reranker
Today, we’re incredibly excited to announce that we’re releasing a new “reranking” capability built into Vectara: one that’s focused on increasing the amount of diversity of the results near the top of the result list.
Why is Metadata Important in GenAI?
Today, we’re happy to announce that Vectara’s hybrid search capabilities have just gotten even stronger with the ability to apply updates to which metadata fields can have filters and what their data types are. This blog will walk through some common use cases and how you can use this new feature.
Customers Don’t Like Your Chatbot. Here’s How to Make Them Love It.
AI has raised the stakes for customer communications with your Brand. Are you hitting the mark? Or do you want to make sure your strategy isn’t a failure to launch. Learn what makes a smart chatbot
Measuring Hallucinations in RAG Systems
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.
Top Large Language Models (LLMs): GPT-4, LLaMA 2, Mistral 7B, ChatGPT, and More
The top large language models along with recommendations for when to use each based upon needs like API, tunable, or fully hosted.
Connect with
our Community!
- Join us on Discord
Discord.
Connect our community channel.
- Join us on Github
Github.
Join our discussion channel.
- Follow us on X / Twitter
X / Twitter.
Get news, company information.
- Follow us on LinkedIn
LinkedIn.
Adopt best practices in projects.
- Join us on Discuss
Discuss.
Suggest your own ideas.
- Write us on E-mail
E-mail.
Ask your follow-up questions.