Viktor Zeman

Update: with python 3.8 is application not crashing

As workaround I request status and check if are set at least some parameters elastic returns in response. To check just http response code is not enough, because it doesn't...

for now we are using and extending langchain library

@jasonmhead you can use Manifest to run your own model locally https://langchain.readthedocs.io/en/latest/modules/llms/integrations/manifest.html

Tested with latest version 0.3.1

Qdrant crash with this message minimum once a day. When this event happens we see following: 2 of 3 nodes has 100% CPU overpowered (even logs are not shown) and...

Today qdrant crashed ~23:35, here is the grafana charts if it helps: 

version 1.7.4, we are going to try changing some configurations first try will be to decrease memmap to 10k We update you in case we find any combination of settings,...

Update: qdrant didn't crash more than 24 hours with following configuration: ``` "memmap_threshold": 4000, "indexing_threshold": 8000, ``` (We changed vector size to 1024 recently and we have 2.4M vectors) Even...

happens in our cluster as well: ``` WARN storage::content_manager::consensus_manager: Failed to send message to http://urlslab-qdrant-1.urlslab-qdrant-headless:6335/ with error: Error in closure supplied to transport channel pool: status: Cancelled, message: "Timeout expired",...