Yasha Boroumand

Results 16 comments of Yasha Boroumand

storage::content_manager::consensus_manager: Failed to apply collection meta operation entry with user error: Bad request: There is no transfer for shard X from N to M

thanks for the quick reply. What is the recommended amount of shards with 3 nodes and 10M vectors? Maybe its also worth it to have a section about this in...

storage::content_manager::consensus_manager: Failed to apply collection meta operation entry with user error: Bad request: There is no transfer for shard X from N to M

there is a crawler which indexes documents that are associated to domains and urls. The sharding is done by `hash_fn(domainHost) % TOTAL_NUMBER_OF_SHARDS`. so, it is garuenteed that constant number of...

storage::content_manager::consensus_manager: Failed to apply collection meta operation entry with user error: Bad request: There is no transfer for shard X from N to M

@timvisee, can we add a metric to know which optimizer is working at a given time. As I understand from the docs, Qdrant uses three different optimizers 1. Vacuum Optimizer...

storage::content_manager::consensus_manager: Failed to apply collection meta operation entry with user error: Bad request: There is no transfer for shard X from N to M

As we investigated further, these are our findings: 1. The warnings happens after a spike in memory, after the spike, the qdrant node is trying to recover the shards and...

storage::content_manager::consensus_manager: Failed to apply collection meta operation entry with user error: Bad request: There is no transfer for shard X from N to M

We have considered quantization. We are not planning to use OpenAI or CohereAI Embedding models. We're rather using opensource models like [multi-lingual e5 Large](https://huggingface.co/intfloat/multilingual-e5-large). So, I'm not sure if it...

storage::content_manager::consensus_manager: Failed to apply collection meta operation entry with user error: Bad request: There is no transfer for shard X from N to M

We can safely close this. feel free to reopen if needed. the underlying problem was memory problems which binary quantization and offloading the vectors to disk are methods to mitigate...