alt Hacker NewsThe whole embedding thing which converts “tokens” to vectors, which you then store in a vector database so that you can later query by vector distance, seems to be LLM specific technology, no? As far as I know the vectors look a lot like the weights in a LLM itself which is why the vector search also works with some level of intelligence.
Replies
nilirl • today at 10:28 AM
Sure and that's a new technique for indexing and querying.
Where's the new design tension? Indexes always had to be monitored for freshness and queries have always needed cleaning or parsing.
KaseyKim • today at 11:12 AM
right, it is the foundation of machine learning.
ewidar • today at 10:34 AM
not really, vectorising text/books is old school ML by this point.
at least to me that seems the same as https://en.wikipedia.org/wiki/Word2vec for e.g.
➕ show 2 replies
Vector embeddings predate LLMs. They have been used as far back as the early 2000s. They are a general machine learning technique, rather than LLM specific