For the last few months, we’ve been doing occasional work on an approximate nearest neighbours (ANN) vector search tool, written in Python. It’s still not finished and there are many rough edges, but it comes with a working DynamoDB adaptor and hence operates out-of-memory, one our main requirements. On the down side, it isn’t as fast […]
At Lateral we use PostgreSQL to store documents for our visualiser. Each document consists of a text column and a JSON column with meta data inside such as a title, date and URL. We wanted to create a fast search experience for the visualiser that lets you search the full text of documents as well as their titles to quickly find a document to get Lateral recommendations for.