Quite useful tutorial! Thanks for bringing it. A few questions that come to my mind: 1- How could I get rid of proprietary image in docker? I bet it is possible to get our existing PG instance and just drop in the necessary extensions and should work as well, but just want to confirm. 2- It looks easy to delegate to the PG extension to communicate with ollama and get the embedings, however I see to many roundrtrips in that approach. For a programmatic system that would have to do tens of thousands runs a day, how this perform? Is there a more "straight" way to pull embeddings from ollama and query PG?
Thank you, clear and straightforward.
great , looking forward learning how to utilize Timescale DB for our AI start-up !
Awesome! That's great to hear. Please let us know how it goes, or if you have any questions. 😁
Quite useful tutorial! Thanks for bringing it.
A few questions that come to my mind:
1- How could I get rid of proprietary image in docker? I bet it is possible to get our existing PG instance and just drop in the necessary extensions and should work as well, but just want to confirm.
2- It looks easy to delegate to the PG extension to communicate with ollama and get the embedings, however I see to many roundrtrips in that approach. For a programmatic system that would have to do tens of thousands runs a day, how this perform? Is there a more "straight" way to pull embeddings from ollama and query PG?
Nice tutorial!
Thanks!!