trying to get the datasets recognized

Author: MarkWolters

.github/workflows/run-bench.yml

@@ -64,7 +64,7 @@ jobs:
           # Use the jar-with-dependencies which includes all required dependencies
           java ${{ matrix.jdk >= 20 && '--enable-native-access=ALL-UNNAMED --add-modules=jdk.incubator.vector' || '' }} \
             ${{ matrix.jdk >= 22 && '-Djvector.experimental.enable_native_vectorization=true' || '' }} \
-            -jar jvector-examples/target/jvector-examples-*-jar-with-dependencies.jar io.github.jbellis.jvector.example.AutoBenchYAML --output bench-results.json
+            -jar jvector-examples/target/jvector-examples-*-jar-with-dependencies.jar io.github.jbellis.jvector.example.AutoBenchYAML --output bench-results.json ${{ inputs.benchmark_config != '' && inputs.benchmark_config || 'jvector-examples/yaml-configs/default.yml' }}
 
       - name: Upload Bench Results
         uses: actions/upload-artifact@v4

jvector-examples/src/main/java/io/github/jbellis/jvector/example/AutoBenchYAML.java

@@ -44,22 +44,22 @@ public class AutoBenchYAML {
      */
     private static List<String> getAllDatasetNames() {
         List<String> allDatasets = new ArrayList<>();
-        
+
         // neighborhood-watch-100k datasets
-//        allDatasets.add("ada002-100k");
-//        allDatasets.add("cohere-english-v3-100k");
-//        allDatasets.add("openai-v3-small-100k");
-//        allDatasets.add("gecko-100k");
-//        allDatasets.add("openai-v3-large-3072-100k");
-//        allDatasets.add("openai-v3-large-1536-100k");
-//        allDatasets.add("e5-small-v2-100k");
-//        allDatasets.add("e5-base-v2-100k");
-//        allDatasets.add("e5-large-v2-100k");
-//
-//        // neighborhood-watch-1M datasets
-//        allDatasets.add("ada002-1M");
-//        allDatasets.add("colbert-1M");
-        
+        allDatasets.add("ada002-100k");
+        allDatasets.add("cohere-english-v3-100k");
+        allDatasets.add("openai-v3-small-100k");
+        allDatasets.add("gecko-100k");
+        allDatasets.add("openai-v3-large-3072-100k");
+        allDatasets.add("openai-v3-large-1536-100k");
+        allDatasets.add("e5-small-v2-100k");
+        allDatasets.add("e5-base-v2-100k");
+        allDatasets.add("e5-large-v2-100k");
+
+        // neighborhood-watch-1M datasets
+        allDatasets.add("ada002-1M");
+        allDatasets.add("colbert-1M");
+
         // ann-benchmarks datasets
         allDatasets.add("glove-25-angular.hdf5");
         allDatasets.add("glove-50-angular.hdf5");
@@ -71,7 +71,7 @@ private static List<String> getAllDatasetNames() {
         // Large files not yet supported:
         // allDatasets.add("deep-image-96-angular.hdf5");
         // allDatasets.add("gist-960-euclidean.hdf5");
-        
+
         return allDatasets;
     }
 
@@ -159,4 +159,4 @@ public static void main(String[] args) throws IOException {
         mapper.writerWithDefaultPrettyPrinter().writeValue(new File(outputPath), results);
         System.out.println("Benchmark results written to " + outputPath);
     }
-}
+}