The Azure OpenAI service was better than the direct OpenAI one for inferene purposes because it was more closer to our servers and had a much better latency
After evaluating a bunch of Vector DBs to be our internal vector DB, we finally closed on QDrant because it was the one that scaled the best and had the best price performance ratio
What more can be said about them that has not been said before. They are the leaders in this space of LLM and we have been using all the models since 3.5 launched a year above
