Nicholas-Schaub

icon indicating an email [email protected]

icon company National Center for the Advancement of Translational Science icon location Rockville, MD icon location Neuromaterials Scientist ⮕ Artificial Intelligence

Results 32 comments of Nicholas-Schaub

Very slow when using chroma with a 4096-dimension embedding model after adding more than 10000 records

We are experiencing a similar issue. We are embedding academic abstract data, and after ~500k records, ingestion has slowed down by more than a factor of 2. This is going...

Very slow when using chroma with a 4096-dimension embedding model after adding more than 10000 records

It seems to me that much of this slowdown is likely caused by the constant pickling and unpickling of data.