OSC & Vectara Collaborate on AI Search Engine Relevance Measurement

Vectara logo

OpenSource Connections logo

OpenSource Connections logo

Partnership demonstrates OSC and Vectara’s commitment to customers testing and tuning the performance of their own queries

We were delighted that Vectara allowed us to ‘open the hood’ of their AI-powered search and RAG platform…we’re also glad to say our open-source search workbench, Quepid, now works with Vectara!””

— Charlie Hull, Managing Consultant & Marketing Director at OSC

PALO ALTO, CALIFORNIA, UNITED STATES, October 26, 2023 /EINPresswire.com/ — Vectara, the Trusted Generative AI Product Platform, and OpenSource Connections (OSC), creators of Quepid, collaborate to provide third-party evaluation of search relevance and measurement. With an emphasis on secure, trustworthy, and transparent GenAI for enterprises, Vectara is keen on providing customers an objective evaluation of its new proprietary retrieval model, Boomerang, a key component in the RAG pipeline.

“We were delighted that Vectara allowed us to ‘open the hood’ of their AI-powered search and Retrieval Augmented Generation (RAG) platform to let us develop ways to assure the quality of search results it can produce. It’s been fascinating to explore the cutting edge of search & AI and we’re also glad to say our open-source search workbench, Quepid, now works with Vectara!” said OSC’s Charlie Hull, Managing Consultant & Marketing Director at OpenSource Connections.

The evaluation showed that Boomerang provided significant gains in relevance relative to USE-QA, one of the most popular and widely deployed embedding models for AI systems. More details on OSC’s blog titled “Learning to Measure AI-Powered Search with Vectara.”

“It was exciting to work with OpenSource Connections to validate the extensive testing that we had done internally before launching Boomerang,” said Shane Connelly, Head of Product at Vectara. “OSC used its extensive knowledge and background working with search users to provide us with valuable feedback on product gaps in addition to the model quality feedback. We’re now working to integrate these features into the platform.”

Vectara is the first native AI search engine integration into Quepid, allowing Vectara customers to benefit from Quepid by using it to test and tune the performance of their own queries.

About Vectara

Vectara is an end-to-end platform that empowers product builders to embed powerful Generative AI features into their applications with extraordinary results. Built on a solid hybrid-search core, Vectara delivers the shortest path to an answer or action through a safe, secure, and trusted entry point. Vectara is built for product managers and developers with an easily leveraged API that gives full access to the platform’s powerful features. Vectara’s “Grounded Generation” allows businesses to quickly, safely, and affordably integrate best-in-class conversational AI and question-answering into their application with zero-shot precision. Vectara never trains models on customer data, allowing businesses to embed generative AI capabilities without the risk of data or privacy violations. To learn more about Vectara, visit www.vectara.com. To learn how we’re empowering the ecosystem to co-build the art of possibility in GenAI, visit www.vectara.com/partnerships.

About OpenSource Connections

OpenSource Connections is a search/discovery/analytics firm focusing on software development and technology consulting, and creators and supporters of open source projects such as Quepid, the search relevancy toolbox.

Carly Bourne
[email protected]
Visit us on social media:

Originally published at https://www.einpresswire.com/article/663930164/osc-vectara-collaborate-on-ai-search-engine-relevance-measurement

Previous articleZippa Announces Its Consumer-led Content Marketing Services
Next articleArtificial Intelligence In Healthcare Diagnosis Market Size, Share, Revenue, Trends And Drivers For 2023-2032