Closed brian316 closed 16 hours ago
In 0.12 we used very conservative parallelism for http embedding backend - thus the slowness is somewhat expected. Could you share the scale of your github repositories? (e.g # of lines + # of files).
Filing https://github.com/TabbyML/tabby/issues/2495 to track the logging improvement.
One thing you might try is to turn on RUST_LOG=debug
inside of container, which should gives you more information on the progress.
Just FYI we also worked on some concurrency improvement to make the indexing faster - if interested, consider give 0.13.0-rc4
a try to see if it improve situation for you.
0.13.0 is now released - this situation should be significantly improved, feel free to reopen the issue if you still encounter slowness in indexing.
ill have to check it thanks!
Describe the bug Indexing takes 1+ hour. I am using open ai
Text-embedding-3-small
for my embeddings. Also the logs are so dry I don't get any useful information. is there any way i can turn on better logging i don't see anything in the docs.Information about your version Version 0.12.0
Information about your GPU
Additional context My system:
My docker-compose file
the only logs i get are not that useful
Open AI dashboard shows some usage but lots of downtime![image](https://github.com/TabbyML/tabby/assets/3878246/8bc61f63-ddfa-4969-b721-b97bb1062bc9)
Running on windows 11. shows low to no usage![image](https://github.com/TabbyML/tabby/assets/3878246/a56ee083-f248-4412-a9e2-d9a8c702b704)