Back to archive

Thread

3 tweets

1
After spending some time with it, it really is pretty versatile, and also has capabilities for full text search, and now apparently vector search. But I also experienced some short-comings: - for batch processing, it's still better to go with Spark/DuckDB/roll your own
2
@rorcde - full text search is there, but using something like elasticsearch gives you a lot more configurability. - same probably holds for vector search.
3
@rorcde Still, if your data is already in there and you want to add some a bit more advanced retrieval capability, it definitely beats setting up a whole additional system and migrating and syncing your data!