Evaluating RAG quality can be complex. open-rag-eval provides a flexible and extensible framework to measure the performance of your RAG system, helping you identify areas for improvement.

Sankofa, which means “to retrieve" in the Twi language of Ghana, is a browser extension created by Vectara, allowing you to Chat with your browser history.

Vectara Portal enables any Vectara user to generate an AI assistant without having to code, powered by our trusted and secure end-to-end RAG platform.

Vectara-agentic is a Python library that helps to build safe and trusted Agentic RAG with Vectara. It supports Agentic RAG workflows, powered by Vectara, while abstracting away most of the nitty-gritty details.

vectara-ingest demonstrates how to crawl datasets and ingest them into Vectara. Includes several types of crawlers like website, RSS, Jira, Notion, or Docusarurus, and you can add your own crawler very easily to handle other data sources.

An open source implementation of a bot that can respond to user questions from Slack, Discord by utilizing Vectara RAG - vectara/ragtime