Powering Data Apps with Enterprise Search

RavenPack uses Vespa for Retrieval-Augmented Generation (RAG) within their Bigdata.com platform, trusted by business and financial professionals worldwide. Vespa streamlines infrastructure, enabling efficient billion-scale vector deployments while managing the complexities of search and retrieval. By offloading these challenges to Vespa, RavenPack focuses on delivering innovative solutions that meet the evolving needs of its users, driving unparalleled efficiency, scalability, and performance in their platform.

Danswer uses Vespa as it’s vector database. Vespa is tightly integrated with Danswer’s core features and is used for storing and retrieving document embeddings. It serves as both a vector database and search engine for Danswer. The system architecture involves documents being pulled and processed via connectors, then persisted in Vespa (and Postgres for relational data) which run in containers within your system. Vespa is crucial for Danswer’s functionality, and it may we difficult to replace it with other vector databases.

Perplexity.ai leverages Vespa Cloud as its web search backend, utilizing a hybrid approach that combines multi-vector and text search. Vespa supports advanced multi-phase ranking, ensuring more accurate and relevant search results.