
Vectara recognized for model development and AI knowledge management
Read more
Vectara recognized for model development and AI knowledge management
Read more
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

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.

Table Data Understanding enables you to query and analyze table data from PDFs. Extract specific cell values, rows, or entire tables for easier data access. Perfect for use cases across finance, research, and more.

Using UDF-based reranking for fine-grained control over your search results with Vectara

Overview The best RAG systems utilize many different types of models (embedding model, generative LLM) to achieve the best, and highest quality results. When you build a small RAG POC,…

Vectara adds new powerful capabilities to allow rerankers to be “chained” together to give you a balance of business rules and neural reranking

How to add Observability to your Vectara AI Assistants and Agents with Arize Phoenix
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.
