Fixing test Cases

Signed-off-by: Varun Jain <[email protected]>
opensearch-project · Jan 10, 2024 · 494d972 · 494d972
1 parent 781551c
commit 494d972
Show file tree

Hide file tree

Showing 7 changed files with 63 additions and 9 deletions.
diff --git a/qa/restart-upgrade/src/test/java/org/opensearch/neuralsearch/bwc/NeuralSparseSearchIT.java b/qa/restart-upgrade/src/test/java/org/opensearch/neuralsearch/bwc/NeuralSparseSearchIT.java
@@ -34,7 +34,7 @@ public class NeuralSparseSearchIT extends AbstractRestartUpgradeRestTestCase {
     public void testSparseEncodingProcessor_E2EFlow() throws Exception {
         waitForClusterHealthGreen(NODES_BWC_CLUSTER);
         if (isRunningAgainstOldCluster()) {
-            String modelId = uploadTextEmbeddingModel();
+            String modelId = uploadSparseEncodingModel();
             loadModel(modelId);
             createPipelineProcessor(modelId, PIPELINE_NAME);
             createIndexWithConfiguration(
@@ -84,13 +84,15 @@ private void validateTestIndex(String modelId) throws Exception {
         Map<String, Object> response = search(getIndexNameForTest(), boolQueryBuilder, 1);
         Map<String, Object> firstInnerHit = getFirstInnerHit(response);
 
-        assertEquals("1", firstInnerHit.get("_id"));
+        assertEquals("0", firstInnerHit.get("_id"));
         float minExpectedScore = computeExpectedScore(modelId, testRankFeaturesDoc1, TEXT_1);
         assertTrue(minExpectedScore < objectToFloat(firstInnerHit.get("_score")));
     }
 
-    private String uploadTextEmbeddingModel() throws Exception {
-        String requestBody = Files.readString(Path.of(classLoader.getResource("processor/UploadModelRequestBody.json").toURI()));
+    private String uploadSparseEncodingModel() throws Exception {
+        String requestBody = Files.readString(
+            Path.of(classLoader.getResource("processor/UploadSparseEncodingModelRequestBody.json").toURI())
+        );
         return registerModelGroupAndGetModelId(requestBody);
     }
 

diff --git a/qa/restart-upgrade/src/test/resources/processor/SparseIndexMappings.json b/qa/restart-upgrade/src/test/resources/processor/SparseIndexMappings.json
@@ -7,7 +7,7 @@
   "mappings": {
     "properties": {
       "passage_embedding": {
-        "type": "knn_vector"
+        "type": "rank_features"
       },
       "passage_text": {
         "type": "text"

diff --git a/qa/restart-upgrade/src/test/resources/processor/UploadSparseEncodingModelRequestBody.json b/qa/restart-upgrade/src/test/resources/processor/UploadSparseEncodingModelRequestBody.json
@@ -0,0 +1,10 @@
+{
+    "name": "tokenize-idf-0915",
+    "version": "1.0.0",
+    "function_name": "SPARSE_TOKENIZE",
+    "description": "test model",
+    "model_format": "TORCH_SCRIPT",
+    "model_group_id": "%s",
+    "model_content_hash_value": "b345e9e943b62c405a8dd227ef2c46c84c5ff0a0b71b584be9132b37bce91a9a",
+    "url": "https://github.com/opensearch-project/ml-commons/raw/main/ml-algorithms/src/test/resources/org/opensearch/ml/engine/algorithms/sparse_encoding/sparse_demo.zip"
+  }
diff --git a/qa/rolling-upgrade/src/test/java/org/opensearch/neuralsearch/bwc/NeuralSparseSearchIT.java b/qa/rolling-upgrade/src/test/java/org/opensearch/neuralsearch/bwc/NeuralSparseSearchIT.java
@@ -40,7 +40,7 @@ public void testSparseEncodingProcessor_E2EFlow() throws Exception {
         waitForClusterHealthGreen(NODES_BWC_CLUSTER);
         switch (getClusterType()) {
             case OLD:
-                String modelId = uploadTextEmbeddingModel();
+                String modelId = uploadSparseEncodingModel();
                 loadModel(modelId);
                 createPipelineProcessor(modelId, PIPELINE_NAME);
                 createIndexWithConfiguration(
@@ -109,13 +109,15 @@ private void validateTestIndexOnUpgrade(int numberOfDocs, String modelId) throws
         Map<String, Object> response = search(getIndexNameForTest(), boolQueryBuilder, 1);
         Map<String, Object> firstInnerHit = getFirstInnerHit(response);
 
-        assertEquals("1", firstInnerHit.get("_id"));
+        assertEquals("0", firstInnerHit.get("_id"));
         float minExpectedScore = computeExpectedScore(modelId, testRankFeaturesDoc1, TEXT);
         assertTrue(minExpectedScore < objectToFloat(firstInnerHit.get("_score")));
     }
 
-    private String uploadTextEmbeddingModel() throws Exception {
-        String requestBody = Files.readString(Path.of(classLoader.getResource("processor/UploadModelRequestBody.json").toURI()));
+    private String uploadSparseEncodingModel() throws Exception {
+        String requestBody = Files.readString(
+            Path.of(classLoader.getResource("processor/UploadSparseEncodingModelRequestBody.json").toURI())
+        );
         return registerModelGroupAndGetModelId(requestBody);
     }
 

diff --git a/...upgrade/src/test/resources/processor/PipelineForSparseEncodingProcessorConfiguration.json b/...upgrade/src/test/resources/processor/PipelineForSparseEncodingProcessorConfiguration.json
@@ -0,0 +1,13 @@
+{
+    "description": "An sparse encoding ingest pipeline",
+    "processors": [
+      {
+        "sparse_encoding": {
+          "model_id": "%s",
+          "field_map": {
+            "passage_text": "passage_embedding"
+          }
+        }
+      }
+    ]
+  }
diff --git a/qa/rolling-upgrade/src/test/resources/processor/SparseIndexMappings.json b/qa/rolling-upgrade/src/test/resources/processor/SparseIndexMappings.json
@@ -0,0 +1,17 @@
+{
+    "settings": {
+      "default_pipeline": "%s",
+      "number_of_shards": 3,
+      "number_of_replicas": 1
+    },
+    "mappings": {
+      "properties": {
+        "passage_embedding": {
+          "type": "rank_features"
+        },
+        "passage_text": {
+          "type": "text"
+        }
+      }
+    }
+}
diff --git a/qa/rolling-upgrade/src/test/resources/processor/UploadSparseEncodingModelRequestBody.json b/qa/rolling-upgrade/src/test/resources/processor/UploadSparseEncodingModelRequestBody.json
@@ -0,0 +1,10 @@
+{
+    "name": "tokenize-idf-0915",
+    "version": "1.0.0",
+    "function_name": "SPARSE_TOKENIZE",
+    "description": "test model",
+    "model_format": "TORCH_SCRIPT",
+    "model_group_id": "%s",
+    "model_content_hash_value": "b345e9e943b62c405a8dd227ef2c46c84c5ff0a0b71b584be9132b37bce91a9a",
+    "url": "https://github.com/opensearch-project/ml-commons/raw/main/ml-algorithms/src/test/resources/org/opensearch/ml/engine/algorithms/sparse_encoding/sparse_demo.zip"
+}