Merge pull request #3975 from manticoresoftware/test/add-knn-tests-for-auto-embeddings

test: add KNN tests for OpenAI and Voyage auto-embeddings

Author: PavelShilin89

test/clt-tests/mcl/auto-embeddings-openai-remote.rec

@@ -120,3 +120,24 @@ Test API key environment variable handling
 if [ -n "$OPENAI_API_KEY" ] && [ "$OPENAI_API_KEY" != "dummy_key_for_testing" ]; then echo "API key is available for testing"; else echo "API key not available - using dummy for error testing"; fi
 ––– output –––
 #!/(API key is available for testing|API key not available - using dummy for error testing)/!#
+––– comment –––
+Test KNN search with text query parameter (auto-embeddings approach)
+––– input –––
+mysql -h0 -P9306 -e "SELECT id, knn_dist() FROM test_openai_remote WHERE knn(embedding, 3, 'machine learning and artificial intelligence')\G"
+––– output –––
+*************************** 1. row ***************************
+        id: %{NUMBER}
+knn_dist(): #!/[0-9]+\.[0-9]+/!#
+*************************** 2. row ***************************
+        id: %{NUMBER}
+knn_dist(): #!/[0-9]+\.[0-9]+/!#
+––– comment –––
+Test KNN search with additional filtering
+––– input –––
+mysql -h0 -P9306 -e "SELECT COUNT(*) as count FROM test_openai_remote WHERE knn(embedding, 5, 'technology and AI') AND id > 0"
+––– output –––
++-------+
+| count |
++-------+
+|     2 |
++-------+

test/clt-tests/mcl/auto-embeddings-voyage-remote.rec

@@ -120,3 +120,24 @@ Test API key environment variable handling
 if [ -n "$VOYAGE_API_KEY" ] && [ "$VOYAGE_API_KEY" != "dummy_key_for_testing" ]; then echo "API key is available for testing"; else echo "API key not available - using dummy for error testing"; fi
 ––– output –––
 #!/(API key is available for testing|API key not available - using dummy for error testing)/!#
+––– comment –––
+Test KNN search with text query parameter (auto-embeddings approach)
+––– input –––
+mysql -h0 -P9306 -e "SELECT id, knn_dist() FROM test_voyage_remote WHERE knn(embedding, 3, 'machine learning and artificial intelligence')\G"
+––– output –––
+*************************** 1. row ***************************
+        id: %{NUMBER}
+knn_dist(): #!/[0-9]+\.[0-9]+/!#
+*************************** 2. row ***************************
+        id: %{NUMBER}
+knn_dist(): #!/[0-9]+\.[0-9]+/!#
+––– comment –––
+Test KNN search with additional filtering
+––– input –––
+mysql -h0 -P9306 -e "SELECT COUNT(*) as count FROM test_voyage_remote WHERE knn(embedding, 5, 'technology and AI') AND id > 0"
+––– output –––
++-------+
+| count |
++-------+
+|     2 |
++-------+