Refactor vector parameter tests to use SQL commands for schema creation

- Updated test cases in `test_vector_params_verification.py` to replace schema creation methods with SQL commands for creating vertex types and properties.
- Modified test cases in `test_vector_sql.py` to utilize SQL commands for creating vertex types and properties, ensuring consistency across tests.
- Improved index verification by querying the schema directly via SQL instead of relying on schema methods.

Author: tae898

.github/workflows/test-python-bindings.yml

@@ -126,7 +126,7 @@ jobs:
           - '3.11'
           - '3.12'
           - '3.13'
-          # - '3.14'  # Temporarily disabled to reduce wheel storage usage
+          - '3.14'
         # Temporarily limit to four platforms (skip macOS x86_64, Windows ARM64)
         # platform: ['linux/amd64', 'linux/arm64', 'darwin/amd64', 'darwin/arm64', 'windows/amd64', 'windows/arm64']
         platform: ['linux/amd64', 'linux/arm64', 'darwin/arm64', 'windows/amd64']
@@ -433,7 +433,6 @@ jobs:
             echo "**Package**: arcadedb-embedded" >> $GITHUB_STEP_SUMMARY
             echo "" >> $GITHUB_STEP_SUMMARY
             echo "ℹ️ **Note**: Some platform/Python combinations are excluded from testing:" >> $GITHUB_STEP_SUMMARY
-            echo "- Python 3.14 is temporarily disabled to reduce wheel storage usage" >> $GITHUB_STEP_SUMMARY
             echo "- Windows ARM64 (no GitHub-hosted runners available)" >> $GITHUB_STEP_SUMMARY
             echo "- macOS x86_64 (temporarily disabled)" >> $GITHUB_STEP_SUMMARY
           else

.github/workflows/test-python-examples.yml

@@ -25,7 +25,7 @@ on:
         description: "Glob pattern(s) for examples to run (space-separated, relative to bindings/python/examples)."
         required: false
         type: string
-        default: "0[1-7]_*.py"
+        default: "0[1-9]_*.py 1[0-6]_*.py"
       build-version:
         description: "Override package version (PEP 440) for build.sh"
         required: false
@@ -37,10 +37,10 @@ on:
       examples:
         description: "Glob pattern(s) for examples to run (space-separated, relative to bindings/python/examples)."
         required: false
-        default: "0[1-7]_*.py"
+        default: "0[1-9]_*.py 1[0-6]_*.py"
 
 env:
-  EXAMPLES: ${{ inputs.examples || '0[1-7]_*.py' }}
+  EXAMPLES: ${{ inputs.examples || '0[1-9]_*.py 1[0-6]_*.py' }}
 
 permissions:
   contents: read
@@ -135,7 +135,7 @@ jobs:
           - '3.11'
           - '3.12'
           - '3.13'
-          # - '3.14'  # Temporarily disabled to reduce wheel storage usage
+          - '3.14'
         # Temporarily limit to four platforms (skip macOS x86_64, Windows ARM64)
         # platform: ['linux/amd64', 'linux/arm64', 'darwin/amd64', 'darwin/arm64', 'windows/amd64', 'windows/arm64']
         platform: ['linux/amd64', 'linux/arm64', 'darwin/arm64', 'windows/amd64']
@@ -247,20 +247,15 @@ jobs:
             python3 download_data.py movielens-small
           fi
 
-          if echo "$examples" | grep -qE '(^|[[:space:]])(08_stackoverflow_tables_oltp|09_stackoverflow_tables_olap|10_stackoverflow_graph_oltp|11_stackoverflow_graph_olap|14_stackoverflow_hybrid_queries)\.py([[:space:]]|$)'; then
-            echo "📥 Downloading Stack Overflow Small dataset..."
-            python3 download_data.py stackoverflow-small --no-vectors
+          if echo "$examples" | grep -qE '(^|[[:space:]])(07_stackoverflow_tables_oltp|08_stackoverflow_tables_olap|09_stackoverflow_graph_oltp|10_stackoverflow_graph_olap|13_stackoverflow_hybrid_queries)\.py([[:space:]]|$)'; then
+            echo "📥 Downloading Stack Overflow Tiny dataset (no vectors)..."
+            python3 download_data.py stackoverflow-tiny --no-vectors
           fi
 
-      - name: Download datasets
-        shell: bash
-        run: |
-          uv pip install --system tqdm py7zr lxml
-          cd bindings/python/examples
-          echo "📥 Downloading MovieLens Small dataset..."
-          python3 download_data.py movielens-small
-          echo "📥 Downloading Stack Overflow Small dataset..."
-          python3 download_data.py stackoverflow-small --no-vectors
+          if echo "$examples" | grep -qE '(^|[[:space:]])(11_vector_index_build|12_vector_search)\.py([[:space:]]|$)'; then
+            echo "📥 Downloading Stack Overflow Tiny dataset (with vectors)..."
+            python3 download_data.py stackoverflow-tiny
+          fi
 
       - name: Install timeout command (macOS only)
         if: matrix.platform == 'darwin/amd64' || matrix.platform == 'darwin/arm64'
@@ -279,9 +274,6 @@ jobs:
       - name: Run all examples
         id: run_examples
         shell: bash
-        env:
-          # Increase JVM heap for large CSV imports (example 04)
-          ARCADEDB_JVM_ARGS: "-Xmx8g -Xms8g"
         run: |
           cd bindings/python/examples
 
@@ -323,21 +315,92 @@ jobs:
                 example_args="--dataset movielens-small --export"
                 example_name="$example (movielens-small dataset with export)"
                 timeout_duration=900  # 15 minutes
+                example_jvm_args="-Xmx8g -Xms8g"
                 ;;
               "05_csv_import_graph.py")
-                example_args="--dataset movielens-small --method java --import-jsonl ./exports/movielens_small_db.jsonl.tgz --export"
-                example_name="$example (movielens-small dataset, embedded java method, import/export)"
+                example_args="--dataset movielens-small --method sql --import-jsonl ./exports/movielens_small_db.jsonl.tgz --export"
+                example_name="$example (movielens-small dataset, embedded sql method, import/export)"
                 timeout_duration=900  # 15 minutes
+                example_jvm_args=""
                 ;;
               "06_vector_search_recommendations.py")
                 example_args="--import-jsonl ./exports/movielens_graph_small_db.jsonl.tgz"
                 example_name="$example (vector search, import from JSONL)"
                 timeout_duration=900  # 15 minutes
+                example_jvm_args=""
+                ;;
+              "07_stackoverflow_tables_oltp.py")
+                example_args="--dataset stackoverflow-tiny --db arcadedb_sql --threads 1 --transactions 1000 --batch-size 500 --mem-limit 2g --run-label ci07"
+                example_name="$example (stackoverflow-tiny, arcadedb_sql, minimal oltp)"
+                timeout_duration=900
+                example_jvm_args=""
+                ;;
+              "08_stackoverflow_tables_olap.py")
+                example_args="--dataset stackoverflow-tiny --db arcadedb_sql --threads 1 --batch-size 500 --query-runs 1 --query-order fixed --mem-limit 2g --run-label ci08"
+                example_name="$example (stackoverflow-tiny, arcadedb_sql, minimal olap)"
+                timeout_duration=900
+                example_jvm_args=""
+                ;;
+              "09_stackoverflow_graph_oltp.py")
+                example_args="--dataset stackoverflow-tiny --db arcadedb_cypher --threads 1 --transactions 1000 --batch-size 500 --mem-limit 2g --run-label ci09"
+                example_name="$example (stackoverflow-tiny graph oltp, arcadedb cypher, minimal)"
+                timeout_duration=900
+                example_jvm_args=""
+                ;;
+              "10_stackoverflow_graph_olap.py")
+                example_args="--dataset stackoverflow-tiny --db arcadedb_cypher --threads 1 --batch-size 500 --query-runs 1 --query-order fixed --mem-limit 2g --run-label ci10"
+                example_name="$example (stackoverflow-tiny graph olap, arcadedb cypher, minimal)"
+                timeout_duration=900
+                example_jvm_args=""
+                ;;
+              "11_vector_index_build.py")
+                example_args="--backend arcadedb_sql --dataset stackoverflow-tiny --threads 1 --mem-limit 2g --batch-size 500 --max-connections 16 --beam-width 100 --quantization NONE --run-label ci11_arcadedb_sql"
+                example_name="$example (vector build, arcadedb_sql backend, minimal)"
+                timeout_duration=1200
+                example_jvm_args=""
+                ;;
+              "12_vector_search.py")
+                db_path=$(find ./my_test_databases -maxdepth 1 -type d -name 'backend=arcadedb_sql_dataset=stackoverflow-tiny_*run=ci11_arcadedb_sql' | head -n 1)
+                if [ -z "$db_path" ]; then
+                  echo "❌ Missing build output for 12_vector_search.py. Ensure 11_vector_index_build.py ran first." | tee -a $results_file
+                  failed=$((failed + 1))
+                  echo ""
+                  continue
+                fi
+                example_args="--backend arcadedb_sql --dataset stackoverflow-tiny --db-path $db_path --overquery-factors 1 --k 10 --query-limit 100 --query-runs 1 --query-order fixed --threads 1 --mem-limit 2g --run-label ci12_arcadedb_sql"
+                example_name="$example (vector search, arcadedb_sql backend, minimal)"
+                timeout_duration=1200
+                example_jvm_args=""
+                ;;
+              "13_stackoverflow_hybrid_queries.py")
+                example_args="--dataset stackoverflow-tiny --batch-size 500 --encode-batch-size 64 --top-k 5 --candidate-limit 100 --min-reputation 100 --infer-sample-limit 5000 --run-label ci13"
+                example_name="$example (hybrid pipeline, tiny + minimal limits)"
+                timeout_duration=1800
+                example_jvm_args=""
+                ;;
+              "14_lifecycle_timing.py")
+                example_args="--runs 1 --table-records 2000 --graph-vertices 500 --vector-records 500 --vector-dimensions 32 --query-runs 10 --jvm-heap 4g"
+                example_name="$example (lifecycle benchmark, minimal)"
+                timeout_duration=900
+                example_jvm_args=""
+                ;;
+              "15_import_database_vs_transactional_table_ingest.py")
+                example_args="--rows-per-table 2000 --tables 2 --columns 6 --string-size 32 --batch-size 500 --async-parallel 1 --parallel 1 --heap-size 4g --work-dir ./my_test_databases/import_vs_txn_dummy_ci"
+                example_name="$example (table ingest benchmark, minimal)"
+                timeout_duration=1200
+                example_jvm_args=""
+                ;;
+              "16_import_database_vs_transactional_graph_ingest.py")
+                example_args="--vertices 2000 --edges 4000 --vertex-int-props 3 --vertex-str-props 2 --edge-int-props 1 --edge-str-props 1 --string-size 32 --batch-size 500 --async-parallel 1 --parallel 1 --heap-size 4g --work-dir ./my_test_databases/import_vs_txn_graph_ci"
+                example_name="$example (graph ingest benchmark, minimal)"
+                timeout_duration=1200
+                example_jvm_args=""
                 ;;
               *)
                 example_args=""
                 example_name="$example"
                 timeout_duration=900  # 15 minutes default
+                example_jvm_args=""
                 ;;
             esac
 
@@ -348,11 +411,23 @@ jobs:
             echo "----------------------------------------"
 
             # Run the example with appropriate parameters
-            if $TIMEOUT_CMD $timeout_duration python "$example" $example_args > "$log_file" 2>&1; then
+            if [ -n "$example_jvm_args" ]; then
+              if ARCADEDB_JVM_ARGS="$example_jvm_args" JAVA_TOOL_OPTIONS="" _JAVA_OPTIONS="" $TIMEOUT_CMD $timeout_duration python "$example" $example_args > "$log_file" 2>&1; then
+                exit_code=0
+              else
+                exit_code=$?
+              fi
+            else
+              if ARCADEDB_JVM_ARGS="" JAVA_TOOL_OPTIONS="" _JAVA_OPTIONS="" $TIMEOUT_CMD $timeout_duration python "$example" $example_args > "$log_file" 2>&1; then
+                exit_code=0
+              else
+                exit_code=$?
+              fi
+            fi
+            if [ $exit_code -eq 0 ]; then
               echo "✅ PASSED: $example_name" | tee -a $results_file
               passed=$((passed + 1))
             else
-              exit_code=$?
               if [ $exit_code -eq 124 ]; then
                 echo "⏱️  TIMEOUT: $example_name (exceeded $((timeout_duration/60)) minutes)" | tee -a $results_file
                 failed=$((failed + 1))

bindings/python/Dockerfile.build

@@ -16,6 +16,7 @@ ARG TARGET_PLATFORM=linux-x64
 # When set to 1, prefer jars provided in bindings/python/local-jars/lib from the build context.
 # If no local jars are present, the build fails fast to avoid silently falling back.
 ARG USE_LOCAL_JARS=0
+ARG LOCAL_JARS_HASH=none
 
 # Stage 1: Use prebuilt ArcadeDB image to obtain compiled JARs
 # JARs are filtered based on jar_exclusions.txt in later stages
@@ -31,6 +32,7 @@ RUN yum -y install findutils binutils && yum clean all
 
 ARG TARGET_PLATFORM
 ARG USE_LOCAL_JARS
+ARG LOCAL_JARS_HASH
 
 WORKDIR /build
 
@@ -41,6 +43,9 @@ COPY --from=java-builder /home/arcadedb/lib /build/upstream-jars/
 # Optionally bring in locally built jars from the repo (bindings/python/local-jars/lib)
 COPY bindings/python/local-jars/lib/ /build/local-jars/
 
+# Make local-jar content changes part of Docker's cache key for this stage.
+RUN echo "LOCAL_JARS_HASH=${LOCAL_JARS_HASH}"
+
 # Select jar source: local when requested and available; otherwise fall back to upstream image
 RUN if [ "$USE_LOCAL_JARS" = "1" ]; then \
             if [ -d /build/local-jars ] && [ "$(ls -1 /build/local-jars | wc -l)" -gt 0 ]; then \
@@ -73,27 +78,41 @@ RUN echo "🗑️  Removing excluded JARs..." && \
 # We exclude jboss/wildfly JARs because they have broken module descriptors that fail analysis.
 # We also do NOT provide a classpath, forcing jdeps to ignore all missing dependencies (intra-jar or external).
 RUN echo "🔍 Analyzing JARs with jdeps..." && \
-    DETECTED_MODULES=$(find /build/jars -name "*.jar" | grep -v "jboss" | grep -v "wildfly" | grep -v "smallrye" | xargs jdeps --print-module-deps --ignore-missing-deps --multi-release 25 | grep -v "Warning" | tr ',' '\n' | grep -v "Warning" | grep -v ":" | grep -v "/" | sort -u | paste -sd "," -) && \
-    REQUIRED_MODULES="${DETECTED_MODULES},jdk.zipfs,jdk.unsupported" && \
+    JMODS_DIR="${JAVA_HOME}/jmods" && \
+    if [ ! -d "$JMODS_DIR" ]; then JMODS_DIR="${JAVA_HOME}/lib/jmods"; fi && \
+    DETECTED_MODULES=$(find /build/jars -name "*.jar" | grep -v "jboss" | grep -v "wildfly" | grep -v "smallrye" | xargs jdeps --print-module-deps --ignore-missing-deps --multi-release 25 | tr ',' '\n' | sed 's/^ *//;s/ *$//' | grep -E '^[a-zA-Z0-9_.]+$' | sort -u | paste -sd "," -) && \
+    if [ -d "$JMODS_DIR" ]; then \
+        AVAILABLE_MODULES=$(find "$JMODS_DIR" -name "*.jmod" -printf "%f\n" | sed 's/\.jmod$//' | sort -u | paste -sd "|" -) ; \
+        FILTERED_MODULES=$(echo "${DETECTED_MODULES}" | tr ',' '\n' | sed '/^$/d' | grep -E "^(${AVAILABLE_MODULES})$" | sort -u | paste -sd "," -) ; \
+    else \
+        FILTERED_MODULES="${DETECTED_MODULES}" ; \
+    fi && \
+    if [ -n "${FILTERED_MODULES}" ]; then \
+        REQUIRED_MODULES="${FILTERED_MODULES},java.se,jdk.management,jdk.zipfs,jdk.unsupported,jdk.incubator.vector" ; \
+    else \
+        REQUIRED_MODULES="java.se,jdk.management,jdk.zipfs,jdk.unsupported,jdk.incubator.vector" ; \
+    fi && \
     echo "🔨 Building minimal JRE for platform: ${TARGET_PLATFORM}" && \
-    echo "📦 Detected modules: ${DETECTED_MODULES}" && \
+    echo "📦 Detected modules (raw): ${DETECTED_MODULES}" && \
+    echo "📦 Detected modules (filtered): ${FILTERED_MODULES}" && \
     echo "📦 Final modules list: ${REQUIRED_MODULES}" && \
     echo "📦 Required modules:" && \
     echo "$REQUIRED_MODULES" | tr ',' '\n' | sed 's/^/   - /' && \
-    JMODS_DIR="${JAVA_HOME}/jmods" && \
-    if [ ! -d "$JMODS_DIR" ]; then JMODS_DIR="${JAVA_HOME}/lib/jmods"; fi && \
     if [ -d "$JMODS_DIR" ]; then \
         echo "" ; \
         echo "🔨 Running jlink..." ; \
-        jlink \
+        if ! jlink \
             --module-path "$JMODS_DIR" \
             --add-modules "${REQUIRED_MODULES}" \
             --ignore-signing-information \
             --strip-debug \
             --no-man-pages \
             --no-header-files \
             --compress zip-9 \
-            --output /build/jre ; \
+            --output /build/jre ; then \
+            echo "❌ jlink failed" ; \
+            exit 1 ; \
+        fi ; \
         echo "" ; \
         echo "✅ JRE build complete!" ; \
     else \