Add smaller dataset

qdrant · Aug 8, 2024 · db74bc7 · db74bc7
1 parent 3e6cdc3
commit db74bc7
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 2 deletions.
diff --git a/.github/workflows/manual-benchmark.yaml b/.github/workflows/manual-benchmark.yaml
@@ -52,14 +52,15 @@ jobs:
  bash -x tools/setup_ci.sh
 
  declare -A DATASET_TO_ENGINE
- DATASET_TO_ENGINE["random-768-10-tenants"]="qdrant-all-on-disk-scalar-q"
+# DATASET_TO_ENGINE["random-768-10-tenants"]="qdrant-all-on-disk-scalar-q"
+ DATASET_TO_ENGINE["random-768-10-tenants-100k"]="qdrant-all-on-disk-scalar-q"
 
  set +e
 
  for dataset in "${!DATASET_TO_ENGINE[@]}"; do
  export ENGINE_NAME=${DATASET_TO_ENGINE[$dataset]}
  export DATASETS=$dataset
- export CONTAINER_MEM_LIMIT=400mb
+ export CONTAINER_MEM_LIMIT=100mb
 
  # Benchmark the dev branch:
  export QDRANT_VERSION=ghcr/dev

diff --git a/datasets/datasets.json b/datasets/datasets.json
@@ -348,6 +348,18 @@
  },
  "tenants": [ "a" ]
  },
+ {
+ "name": "random-768-10-tenants-100k",
+ "vector_size": 768,
+ "distance": "cosine",
+ "type": "tar",
+ "link": "https://storage.googleapis.com/ann-filtered-benchmark/datasets/random_keywords_100k_768_vocab_10.tgz",
+ "path": "random-768-10-tenants/random_keywords_100k_768_vocab_10",
+ "schema": {
+ "a": "keyword"
+ },
+ "tenants": [ "a" ]
+ },
  {
  "name": "random-100-match-kw-small-vocab-no-filters",
  "vector_size": 256,