vector-db-benchmark
vector-db-benchmark copied to clipboard
qdrant
Framework for benchmarking vector search engines
Encountered an unexpected 500 (Internal Server Error) while using the Qdrant vector benchmark tool on a remote qdrant setup. This happens when we want to run multiple experiments with different...
Would be a nice idea to include them. The Qdrant team will focus on this when releasing the next version of our benchmarks. But contributors are welcome anytime :)
Testing qdrant on 8 cores, 64GB of memory r6i.2xlalrge instance Here is the collection's configuration: ``` { "params":{ "vectors":{ "size":96 "distance":"Euclid" } "shard_number":1 "replication_factor":1 "write_consistency_factor":1 "on_disk_payload":true } "hnsw_config":{ "m":16 "ef_construct":128...
This PR: - Updates the milvus version from 2.3.1 to 2.4.1 (Release date: May 6, 2024) - Fixes json logging numeric/text issue on docker composes of milvus
The following PR allows the client implementations to report memory usage metrics at the end of import stage. It can also be used to add extra info on the post...
The bellow changes aim to: - Ease the OpenSearch integration, while also reusing as much as possible the connection creation steps. - Add support for anonymous auth on opensearch client...
Ideally we should handle it and retry/fallback. ### Sample error at query time: ``` 6038it [01:17, 77.75it/s] Experiment opensearch-m-16-ef-128 - glove-100-angular interrupted multiprocessing.pool.RemoteTraceback: """ Traceback (most recent call last): File...
The dependency `weaviate-client` got an (for us) breaking change: A refactoring of the underlying implementation of the WeaviateClient to use the WeaviateAsyncClient under-the-hood scheduling the necessary coroutines to run in...
Two optimizations in search: 1. It takes different time to load query data from .hdf5 data file or .tgz data file. Therefore, preloading the query vector into memory can eliminate...
