Included 512, 1024, 2048 and 3072 dbpedia dims datasets.

DOCKER_README.md

@@ -58,7 +58,7 @@ docker run --rm redis/vector-db-benchmark:latest run.py --describe datasets
 # Basic Redis benchmark (requires local Redis)
 docker run --rm -v $(pwd)/results:/app/results --network=host \
   redis/vector-db-benchmark:latest \
-  run.py --host localhost --engines redis-default-simple --dataset random-100
+  run.py --host localhost --engines redis-default-simple --datasets random-100
 ```
 
 ## Features
@@ -78,12 +78,12 @@ docker run --rm -v $(pwd)/results:/app/results --network=host \
 ### Redis 8.2 with RediSearch
 ```bash
 # Start Redis 8.2 with built-in vector support
-docker run -d --name redis-test -p 6379:6379 redis:8.2-rc1-bookworm
+docker run -d --name redis-test -p 6379:6379 redis:8.2-bookworm
 
 # Run benchmark
 docker run --rm -v $(pwd)/results:/app/results --network=host \
   redis/vector-db-benchmark:latest \
-  run.py --host localhost --engines redis-default-simple --dataset glove-25-angular
+  run.py --host localhost --engines redis-default-simple --datasets glove-25-angular
 ```
 
 
@@ -103,18 +103,18 @@ docker run --rm redis/vector-db-benchmark:latest run.py --describe engines
 # Quick test with small dataset
 docker run --rm -v $(pwd)/results:/app/results --network=host \
   redis/vector-db-benchmark:latest \
-  run.py --host localhost --engines redis-default-simple --dataset random-100
+  run.py --host localhost --engines redis-default-simple --datasets random-100
 
 # Comprehensive benchmark with multiple configurations
 docker run --rm -v $(pwd)/results:/app/results --network=host \
   redis/vector-db-benchmark:latest \
-  run.py --host localhost --engines "*redis*" --dataset glove-25-angular
+  run.py --host localhost --engines "*redis*" --datasets glove-25-angular
 
 # With Redis authentication
 docker run --rm -v $(pwd)/results:/app/results --network=host \
   -e REDIS_AUTH=mypassword -e REDIS_USER=myuser \
   redis/vector-db-benchmark:latest \
-  run.py --host localhost --engines redis-default-simple --dataset random-100
+  run.py --host localhost --engines redis-default-simple --datasets random-100
 ```
 
 ### Results Analysis

README.md

@@ -112,13 +112,13 @@ For testing with Redis, start a Redis container first:
 
 ```bash
 # Start Redis container
-docker run -d --name redis-test -p 6379:6379 redis:8.2-rc1-bookworm
+docker run -d --name redis-test -p 6379:6379 redis:8.2-bookworm
 
 # Run benchmark against Redis
 
 docker run --rm -v $(pwd)/results:/app/results --network=host \
   redis/vector-db-benchmark:latest \
-  run.py --host localhost --engines redis-default-simple --dataset random-100
+  run.py --host localhost --engines redis-default-simple --datasets random-100
 
 # Or use the convenience script
 ./docker-run.sh -H localhost -e redis-default-simple -d random-100
@@ -221,14 +221,14 @@ Run the benchmark:
 
 ```bash
 # Basic usage examples
-python run.py --engines redis-default-simple --dataset random-100
-python run.py --engines redis-default-simple --dataset glove-25-angular
-python run.py --engines "*-m-16-*" --dataset "glove-*"
+python run.py --engines redis-default-simple --datasets random-100
+python run.py --engines redis-default-simple --datasets glove-25-angular
+python run.py --engines "*-m-16-*" --datasets "glove-*"
 
 # Docker usage (recommended)
 docker run --rm -v $(pwd)/results:/app/results --network=host \
   redis/vector-db-benchmark:latest \
-  run.py --host localhost --engines redis-default-simple --dataset random-100
+  run.py --host localhost --engines redis-default-simple --datasets random-100
 
 # Get help
 python run.py --help

datasets/datasets.json

@@ -972,13 +972,53 @@
     "vector_count": 100000,
     "description": "Image embeddings"
   },
+  {
+    "name": "dbpedia-openai-1M-512-angular",
+    "vector_size": 512,
+    "distance": "cosine",
+    "type": "h5",
+    "path": "dbpedia-openai-1M-512-angular/dbpedia_openai_1M",
+    "link": "http://benchmarks.redislabs.s3.amazonaws.com/vecsim/dbpedia/dbpedia-openai-1M-text-embedding-3-large-512d.hdf5",
+    "vector_count": 1000000,
+    "description": "Knowledge embeddings"
+  },
+  {
+    "name": "dbpedia-openai-1M-1024-angular",
+    "vector_size": 1024,
+    "distance": "cosine",
+    "type": "h5",
+    "path": "dbpedia-openai-1M-1024-angular/dbpedia_openai_1M",
+    "link": "http://benchmarks.redislabs.s3.amazonaws.com/vecsim/dbpedia/dbpedia-openai-1M-text-embedding-3-large-1024d.hdf5",
+    "vector_count": 1000000,
+    "description": "Knowledge embeddings"
+  },
   {
     "name": "dbpedia-openai-1M-1536-angular",
     "vector_size": 1536,
     "distance": "cosine",
-    "type": "tar",
+    "type": "h5",
     "path": "dbpedia-openai-1M-1536-angular/dbpedia_openai_1M",
-    "link": "https://storage.googleapis.com/ann-filtered-benchmark/datasets/dbpedia_openai_1M.tgz",
+    "link": "http://benchmarks.redislabs.s3.amazonaws.com/vecsim/dbpedia/dbpedia-openai-1M-text-embedding-3-large-1536d.hdf5",
+    "vector_count": 1000000,
+    "description": "Knowledge embeddings"
+  },
+  {
+    "name": "dbpedia-openai-1M-2048-angular",
+    "vector_size": 2048,
+    "distance": "cosine",
+    "type": "h5",
+    "path": "dbpedia-openai-1M-2048-angular/dbpedia_openai_1M",
+    "link": "http://benchmarks.redislabs.s3.amazonaws.com/vecsim/dbpedia/dbpedia-openai-1M-text-embedding-3-large-2048d.hdf5",
+    "vector_count": 1000000,
+    "description": "Knowledge embeddings"
+  },
+  {
+    "name": "dbpedia-openai-1M-3072-angular",
+    "vector_size": 3072,
+    "distance": "cosine",
+    "type": "h5",
+    "path": "dbpedia-openai-1M-3072-angular/dbpedia_openai_1M",
+    "link": "http://benchmarks.redislabs.s3.amazonaws.com/vecsim/dbpedia/dbpedia-openai-1M-text-embedding-3-large-3072d.hdf5",
     "vector_count": 1000000,
     "description": "Knowledge embeddings"
   },

run.py

@@ -1,7 +1,11 @@
 import fnmatch
 import traceback
+import warnings
 from typing import List
 
+# Suppress the pkg_resources deprecation warning from stopit
+warnings.filterwarnings("ignore", message="pkg_resources is deprecated", category=UserWarning)
+
 import stopit
 import typer