6 Hard Problems Scaling Vector Search
rockset.com
6 Hard Problems Scaling Vector Search
Building a web search engine from scratch in two months with 3 billion neural embeddings
blog.wilsonl.in
This snippet from the Lex Fridman interview with Aravind Srinivas makes me bullish about Perplexity.
This is great (and technical) insight from a CEO.
There’s insane amount of domain knowledge you need to work on this and it takes a lot of time to build up towards a highly really good... See more
Traditional (SQL) databases rely primarily on keyword-based searches to retrieve information. These searches match the exact words or phrases in your query to the text stored in the database. While effective for many applications, this method has limitations when it comes to understanding context or finding relevant information that doesn’t include... See more
Femke Plantingax.com
VECTOR DATABASES ARE THE WRONG ABSTRACTION. Here’s a better way: introducing pgai Vectorizer, a new open-source PostgreSQL tool that automatically creates and syncs embeddings with source data, just like a database index.
❌ Why vector databases fail
Vector databases treat embeddings as independent data,... See more