
Vectara recognized for model development and AI knowledge management
Read more
Vectara recognized for model development and AI knowledge management
Read more
Vectara's Intelligent Query Rewriting (Tech Preview) improves RAG search accuracy by separating queries into their natural language and filter expression components.

In the era of generative AI, trust and transparency are essential—especially for enterprises in regulated industries where AI hallucinations can have serious consequences. Vectara’s Enterprise RAG platform prioritizes explainability with citation-backed responses, advanced observability tools, and chat history search, ensuring AI-driven insights are verifiable and reliable.

DeepSeek has shaken the AI industry with its release of Deepseek-R1, but it turns out that Deepseek-R1 has a hallucination problem.

How Enterprise RAG has evolved and what we can expect to see next...

A Typescript-native interface for Vectara, simplifying Integration for Developers

With Vectara's new Knee Reranking, you can automatically improve result quality and reduce GenAI latency

Vectara’s Hughes Hallucination Evaluation Model (HHEM) now supports 8 languages, expanding from English, German, and French to include Portuguese, Spanish, Arabic, Chinese - Simplified, and Korean.

A Python-native interface for Vectara, built for developers.

Hello Vectara community! Today, we’re very happy to announce another new feature in Vectara: the ability to update the metadata of documents after they’ve been indexed. This has been one of the most requested features in Vectara by our users. In this blog, we’ll walk you through how it works, why it’s been so requested, and what you can do with Vectara now.
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.
