With the recent technological advancement in LLM’s, embedding generation and RAGS, there is immense interest in using this technology to solve problems like Semantic Search, Chat Bots, Code Graph, Knowlegde graph.
This has led to the development of Data Management systems which can deal with large scale generation, storage and search capability for these vector embeddings.
This talk is targeted towards technical audience interested in details of Vector Search state of the art algorithms and challenges associated with building data management system for it.
The talk will start with motivation about why RAGS compare it with traditional Search engine. Followed by introduction to basic mathematical constructs and popular algorithms. Talk will then delve into the state of art Vector Databases and then segue into the challenges associated with building those systems and open problems. Talk will touch upon the integration challenges related to building end to end application in this space.
The talk will conclude with a peek into the possible future.
I work on the effort to build Native Vector Database support in Microsoft SQL Server.
{{ gettext('Login to leave a comment') }}
{{ gettext('Post a comment…') }}{{ errorMsg }}
{{ gettext('No comments posted yet') }}