Smensink

Changing embedding parameters

1

is there any way to change embedding context/ chunk size? i'm using ollama and the terminal has n_ctx=2048 when the model i'm using supports up to 4096

qdrant RAM usage (?allow quantisation and memmap)

5

hello, I am attempting to create a qdrant database with a large collection of medical guidelines. Unfortunately although the raw text is only 800MB the database rapidly grows to 15+...

i'm having trouble figuring out how to increase the context length when using ollama as a llm source, it's stuck on the default 2048

failed to delete connector: key error

2

2024-06-01 17:15:53 background-1 | [2024-06-01 07:15:52,044: ERROR/MainProcess] Failed to run connector_deletion due to "XXXXXXXX" 2024-06-01 17:15:53 background-1 | Traceback (most recent call last): 2024-06-01 17:15:53 background-1 | File "/app/danswer/background/celery/celery.py", line...