Do You Manage Peer Insights at Vespa.ai?
Access Vendor Portal to update and manage your profile.
We purchased the Enclave product which was really well-suited for us because it let us run the hosts in our own Google cloud account, and thus didn't require us to transfer any data out which was well-aligned with our security stance. It provided light-touch deployment and observability services that we lacked and helped us bootstrap quickly and with minimal investment. The Vespa search backend itself provided a good match to our requirements of near-real time hybrid search, combining nearest neighbor embedding search with attribute filters, in a distributed and highly scalable way. Our target installation comprised >12TB of memory across 24 hosts and held O(1B) vector embeddings.
Performance and reliability, support level from the team and the high level of customization of search pipelines it allows for.
The quality and efficiency of the product with the fact that we can very easily customize it to fit our needs.
Vespa, in a scalable deployment, presents a fairly complex architecture with a lot of tuning knobs and bells and whistles. It took several months to get familiar with them. The Vespa consultant was very instrumental in this. Feeding Vespa from BigQuery was harder than expected. Native extensions can only be written in Java which, without a native Java toolchain at our company, proved too challenging to pursue. The documentation is vast but could be better organized and have more contextual examples in places.
The learning curve is high and the surface area is large (special schema language, query language, grouping language, tensor framework etc). Not all features work in all contexts you would expect. There are gaps in documentation.
1. Pricing - Auto-scale is not working that well, deciding which instance will fit our needs the most, etc. 2. Application monitoring - its not easy to understand which logs are crucial and which are not, their monitoring dashboard is still Beta and not detailed enough in my opinion 3. Documentation - Have more examples and documentation about some technical implementations