feat: add Vertica adapter support (#2141)

devin-ai-integration[bot] · haritamar · web-flow · commit 4566cc2f3266 · 2026-03-12T15:28:20.000+02:00
* feat: add Vertica adapter support - Add dbt-vertica as optional dependency in pyproject.toml - Add Vertica transient error patterns for automatic retry - Add Vertica Docker service to e2e test docker-compose - Add Vertica profile to test profiles template - Add Vertica to CI workflow matrix (test-warehouse + test-all-warehouses) - Handle dbt-vertica install with --no-deps (pins dbt-core~=1.8) Co-Authored-By: Itamar Hartstein <haritamar@gmail.com> * fix: prevent dbt-core downgrade when installing elementary with vertica The dbt-vertica package pins dbt-core~=1.8. Installing elementary with the [vertica] extra would re-resolve dbt-vertica's deps and downgrade dbt-core, breaking package-lock.yml parsing and protobuf compat. Fix: install elementary without the adapter extra for Vertica (dbt-vertica is already present via --no-deps), and explicitly install vertica-python. Co-Authored-By: Itamar Hartstein <haritamar@gmail.com> * fix: address CodeRabbit review feedback - Remove 'no transaction in progress' from Vertica transient patterns (it's a transaction-state notice, not a transient connection error) - Hardcode dbt-data-reliability-ref to 'vertica-compat' for the Vertica matrix entry until PR #963 merges into master Co-Authored-By: Itamar Hartstein <haritamar@gmail.com> * chore: update dbt-data-reliability ref to merged master commit PR #963 has been merged to master (2ab66fbe). Update: - packages.yml/package-lock.yml: point to merge commit on master - test-all-warehouses.yml: remove vertica-compat branch override Co-Authored-By: Itamar Hartstein <haritamar@gmail.com> * fix: add vertica_seed_override to e2e project (fixes seed_rejects collision) dbt-vertica's COPY command hardcodes 'seed_rejects' as the reject table name for every seed, causing 'Object already exists' errors when dbt seed processes more than one file. This override (same as in dbt-data-reliability integration tests) uses per-seed reject table names. Co-Authored-By: Itamar Hartstein <haritamar@gmail.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Itamar Hartstein <haritamar@gmail.com>
diff --git a/.github/workflows/test-all-warehouses.yml b/.github/workflows/test-all-warehouses.yml
@@ -102,6 +102,7 @@ jobs:
             spark,
             fabric,
             sqlserver,
+            vertica,
           ]
     uses: ./.github/workflows/test-warehouse.yml
     with:
diff --git a/.github/workflows/test-warehouse.yml b/.github/workflows/test-warehouse.yml
@@ -20,6 +20,7 @@ on:
           - dremio
           - fabric
           - sqlserver
+          - vertica
       elementary-ref:
         type: string
         required: false
@@ -167,6 +168,12 @@ jobs:
         run: |
           docker compose up -d --wait sqlserver
 
+      - name: Start Vertica
+        if: inputs.warehouse-type == 'vertica'
+        working-directory: ${{ env.E2E_DBT_PROJECT_DIR }}
+        run: |
+          docker compose up -d --wait vertica
+
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
@@ -185,15 +192,34 @@ jobs:
           sudo ACCEPT_EULA=Y apt-get install -y msodbcsql18 unixodbc-dev
 
       - name: Install dbt
+        if: inputs.warehouse-type != 'vertica'
         run: >
           pip install
           "dbt-core${{ inputs.dbt-version && format('=={0}', inputs.dbt-version) }}"
           "dbt-${{ (inputs.warehouse-type == 'databricks_catalog' && 'databricks') || (inputs.warehouse-type == 'athena' && 'athena-community') || (inputs.warehouse-type == 'dremio' && 'dremio') || inputs.warehouse-type }}${{ (inputs.warehouse-type == 'spark' && '[PyHive]') || '' }}${{ inputs.dbt-version && format('~={0}', inputs.dbt-version) }}"
 
+      # dbt-vertica pins dbt-core~=1.8 which lacks the 'arguments' attribute
+      # used by newer dbt-core.  Install dbt-vertica without deps first, then
+      # install the latest compatible dbt-core separately.  We also install
+      # vertica-python (dbt-vertica's runtime dep) explicitly.
+      - name: Install dbt (Vertica)
+        if: inputs.warehouse-type == 'vertica'
+        run: |
+          pip install --no-deps dbt-vertica
+          pip install vertica-python
+          pip install "dbt-core${{ inputs.dbt-version && format('=={0}', inputs.dbt-version) }}"
+
       - name: Install Elementary
         run: |
           pip install -r dev-requirements.txt
-          pip install ".[${{ (inputs.warehouse-type == 'databricks_catalog' && 'databricks') || inputs.warehouse-type }}]"
+          # For Vertica, dbt-vertica is already installed with --no-deps above;
+          # using ".[vertica]" would re-resolve dbt-vertica's deps and downgrade
+          # dbt-core to ~=1.8.  Install elementary without the adapter extra.
+          if [ "${{ inputs.warehouse-type }}" = "vertica" ]; then
+            pip install "."
+          else
+            pip install ".[${{ (inputs.warehouse-type == 'databricks_catalog' && 'databricks') || inputs.warehouse-type }}]"
+          fi
 
       - name: Write dbt profiles
         env:
@@ -204,7 +230,7 @@ jobs:
           # This enables caching the seeded database state between runs.
           IS_DOCKER=false
           case "${{ inputs.warehouse-type }}" in
-            postgres|clickhouse|trino|dremio|duckdb|spark|sqlserver) IS_DOCKER=true ;;
+            postgres|clickhouse|trino|dremio|duckdb|spark|sqlserver|vertica) IS_DOCKER=true ;;
           esac
 
           if [ "$IS_DOCKER" = "true" ]; then
diff --git a/elementary/clients/dbt/transient_errors.py b/elementary/clients/dbt/transient_errors.py
@@ -120,6 +120,11 @@
     ),
     "fabric": _TSQL_TRANSIENT,
     "sqlserver": _TSQL_TRANSIENT,
+    "vertica": (
+        "connection timed out",
+        "could not connect to the server",
+        "ssl syscall error",
+    ),
 }
 
 # Pre-computed union of all adapter-specific patterns for the fallback path
diff --git a/elementary/monitor/dbt_project/package-lock.yml b/elementary/monitor/dbt_project/package-lock.yml
@@ -4,5 +4,5 @@ packages:
     version: 0.8.6
   - git: https://github.com/elementary-data/dbt-data-reliability.git
     name: elementary
-    revision: 534afc63c75d28b87d7cbd3b222dd3ea9a980f7b
-sha1_hash: cb18b7df65415901187dcf469dcd377e56c0dc70
+    revision: 2ab66fbe7e347c3cbbf2910c91f03cd6db2ef517
+sha1_hash: 7dc83ea83a781be623eea141eca2a0cceb4878e9
diff --git a/elementary/monitor/dbt_project/packages.yml b/elementary/monitor/dbt_project/packages.yml
@@ -2,7 +2,7 @@ packages:
   - package: dbt-labs/dbt_utils
     version: [">=0.8.0", "<0.9.0"]
   - git: https://github.com/elementary-data/dbt-data-reliability.git
-    revision: 534afc63c75d28b87d7cbd3b222dd3ea9a980f7b
+    revision: 2ab66fbe7e347c3cbbf2910c91f03cd6db2ef517
 
   #  NOTE - for unreleased CLI versions we often need to update the package version to a commit hash (please leave this
   #  commented, so it will be easy to access)
diff --git a/pyproject.toml b/pyproject.toml
@@ -58,6 +58,7 @@ dbt-duckdb = {version = ">=1.5.0,<2.0.0", optional = true}
 dbt-dremio = {version = ">=1.5.0,<2.0.0", optional = true}
 dbt-fabric = {version = ">=1.4,<2.0.0", optional = true}
 dbt-sqlserver = {version = ">=1.4,<2.0.0", optional = true}
+dbt-vertica = {version = ">=1.7,<2.0.0", optional = true}
 [tool.poetry.extras]
 snowflake = ["dbt-snowflake"]
 bigquery = ["dbt-bigquery"]
@@ -72,7 +73,8 @@ duckdb = ["dbt-duckdb"]
 dremio = ["dbt-dremio"]
 fabric = ["dbt-fabric"]
 sqlserver = ["dbt-sqlserver"]
-all = ["dbt-snowflake", "dbt-bigquery", "dbt-redshift", "dbt-postgres", "dbt-databricks", "dbt-spark", "dbt-clickhouse", "dbt-athena-community", "dbt-trino", "dbt-duckdb", "dbt-dremio", "dbt-fabric", "dbt-sqlserver"]
+vertica = ["dbt-vertica"]
+all = ["dbt-snowflake", "dbt-bigquery", "dbt-redshift", "dbt-postgres", "dbt-databricks", "dbt-spark", "dbt-clickhouse", "dbt-athena-community", "dbt-trino", "dbt-duckdb", "dbt-dremio", "dbt-fabric", "dbt-sqlserver", "dbt-vertica"]
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]
diff --git a/tests/e2e_dbt_project/docker-compose.yml b/tests/e2e_dbt_project/docker-compose.yml
@@ -290,6 +290,36 @@ services:
       timeout: 5s
       retries: 10
 
+  # ── Vertica CE ────────────────────────────────────────────────────
+  vertica:
+    image: ghcr.io/ratiopbc/vertica-ce
+    container_name: vertica
+    ports:
+      - "127.0.0.1:5433:5433"
+    environment:
+      APP_DB_USER: dbadmin
+      APP_DB_PASSWORD: vertica
+      TZ: "UTC"
+      VERTICA_DB_NAME: elementary_tests
+      VMART_ETL_SCRIPT: ""
+    deploy:
+      mode: global
+    ulimits:
+      nofile:
+        soft: 65536
+        hard: 65536
+    volumes:
+      - vertica-data:/data
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          "/opt/vertica/bin/vsql -U dbadmin -w vertica -c 'SELECT 1;'",
+        ]
+      interval: 5s
+      timeout: 5s
+      retries: 10
+
   # ── SQL Server (for Fabric / SQL Server adapters) ─────────────────
   sqlserver:
     image: mcr.microsoft.com/mssql/server:2022-latest
@@ -316,3 +346,4 @@ volumes:
   dremio-minio-data:
   spark-warehouse:
   spark-hive-metastore:
+  vertica-data:
diff --git a/tests/e2e_dbt_project/macros/vertica_seed_override.sql b/tests/e2e_dbt_project/macros/vertica_seed_override.sql
@@ -0,0 +1,23 @@
+{#- Override the dbt-vertica seed helper so that each seed file uses a
+    unique reject-table name.  The upstream macro hardcodes
+    ``seed_rejects`` for every seed, which causes "Object already exists"
+    errors when ``dbt seed`` processes more than one file. -#}
+{% macro copy_local_load_csv_rows(model, agate_table) %}
+    {% set cols_sql = get_seed_column_quoted_csv(model, agate_table.column_names) %}
+
+    {#- Build a per-seed reject table name so concurrent seeds don't clash. -#}
+    {% set reject_table = model["alias"] ~ "_rejects" %}
+
+    {% set sql %}
+        copy {{ this.render() }}
+        ({{ cols_sql }})
+        from local '{{ agate_table.original_abspath }}'
+        delimiter ','
+        enclosed by '"'
+        skip 1
+        abort on error
+        rejected data as table {{ this.without_identifier() }}.{{ reject_table }};
+    {% endset %}
+
+    {{ return(sql) }}
+{% endmacro %}
diff --git a/tests/profiles/profiles.yml.j2 b/tests/profiles/profiles.yml.j2
@@ -73,6 +73,16 @@ elementary_tests:
       trust_cert: true
       threads: 4
 
+    vertica: &vertica
+      type: vertica
+      host: 127.0.0.1
+      port: 5433
+      username: dbadmin
+      password: vertica
+      database: elementary_tests
+      schema: {{ schema_name }}
+      threads: 4
+
     # ── Cloud targets (secrets substituted at CI time) ─────────────────
 
     fabric: &fabric
@@ -148,7 +158,7 @@ elementary_tests:
 elementary:
   target: postgres
   outputs:
-{%- set targets = ['postgres', 'clickhouse', 'trino', 'dremio', 'duckdb', 'spark', 'fabric', 'sqlserver', 'snowflake', 'bigquery', 'redshift', 'databricks_catalog', 'athena'] %}
+{%- set targets = ['postgres', 'clickhouse', 'trino', 'dremio', 'duckdb', 'spark', 'fabric', 'sqlserver', 'vertica', 'snowflake', 'bigquery', 'redshift', 'databricks_catalog', 'athena'] %}
 {%- for t in targets %}
     {{ t }}:
       <<: *{{ t }}

Original file line number	Diff line number	Diff line change
`@@ -102,6 +102,7 @@ jobs:`
`102`	`102`	`spark,`
`103`	`103`	`fabric,`
`104`	`104`	`sqlserver,`
	`105`	`+ vertica,`
`105`	`106`	`]`
`106`	`107`	`uses: ./.github/workflows/test-warehouse.yml`
`107`	`108`	`with:`