google/skills

BigQuery User-Defined Functions (UDFs)

BigQuery User-Defined Functions (UDFs) extend GoogleSQL with custom logic written in SQL, JavaScript, managed Python (python-3.11), or hosted externally as Remote Functions on Cloud Run and Cloud Run functions.

Usage Attribution

MUST READ: Before executing any gcloud, REST API, or MCP command, you MUST read and follow the instructions in Usage Attribution.

Choosing the Right UDF Type

Always select the lightest-weight runtime that satisfies the requirement, because BigQuery optimizes native SQL expressions inline while external runtimes incur serialization and container startup overhead:

Prerequisites & Setup

Ensure the Google Cloud project has an active billing account attached (see BigQuery Pricing):

1. Install and Authenticate Google Cloud SDK: Install the Google Cloud SDK and authenticate:

   gcloud auth login
   

   Pass --project={project_id} and --region={region} (or --location for bq) explicitly on each command instead of running gcloud config set, which persists beyond the task. Default to us-central1 when the user has not specified a region (see BigQuery Locations).

2. Enable Required APIs:

   • For SQL, JavaScript, and offline Python UDFs: bigquery.googleapis.com
   • Additionally for Python UDFs calling APIs (WITH CONNECTION) and Remote Functions: bigqueryconnection.googleapis.com (and run.googleapis.com for Remote Functions)

   CLOUDSDK_METRICS_REQUEST_ATTRIBUTION="agent-skills/1.0 (skill:bigquery-udfs)" \
   gcloud services enable bigquery.googleapis.com \
     bigqueryconnection.googleapis.com \
     run.googleapis.com --quiet
   

3. Verify Required IAM Roles:

   • All UDFs: roles/bigquery.dataEditor on the dataset and roles/bigquery.jobUser on the project.
   • When using WITH CONNECTION (API-calling Python UDFs & Remote Functions):
     • UDF Creator: roles/bigquery.connectionAdmin on the project (plus resourcemanager.projects.setIamPolicy, e.g., roles/resourcemanager.projectIamAdmin, when granting project-level IAM roles to the connection service account via GRANT ... ON PROJECT).
     • UDF Caller: roles/bigquery.connectionUser on the connection.

Core Implementation Patterns

1. SQL UDFs (Scalar & Templated)

Use CREATE OR REPLACE FUNCTION for persistent UDFs or CREATE TEMP FUNCTION for query-scoped functions. Use ANY TYPE for polymorphic parameters:

CREATE OR REPLACE FUNCTION `{project_id}.{dataset_id}.normalize_phone`(
  raw_phone STRING,
  country_code ANY TYPE
)
RETURNS STRING
AS (
  CONCAT('+', CAST(country_code AS STRING), '-', REGEXP_REPLACE(raw_phone, r'[^0-9]', ''))
);

See SQL and JavaScript UDFs for aggregate UDFs (CREATE AGGREGATE FUNCTION) and JavaScript Cloud Storage library loading.

2. JavaScript UDFs

Use raw triple-quoted strings (r"""...""") to avoid escaping backslashes:

CREATE OR REPLACE FUNCTION `{project_id}.{dataset_id}.extract_url_query_keys`(
  url_str STRING
)
RETURNS ARRAY<STRING>
DETERMINISTIC
LANGUAGE js
OPTIONS (
  library = ['gs://{bucket_name}/libs/uri-parser.js']
)
AS r"""
  if (!url_str) return [];
  try {
    return URIParser.getQueryKeys(url_str);
  } catch (err) {
    return [];
  }
""";

3. Managed Python UDFs (With and Without Connection)

Python UDFs must be persistent (do not use TEMP), specify runtime_version = 'python-3.11', and define an entry_point. numpy, pandas, and pyarrow are pre-installed in the python-3.11 base image.

BigQuery defaults to container_memory = '512Mi', container_cpu = 1.0, and container_request_concurrency = 80. Omit these options when the defaults are sufficient, and configure them explicitly only when a workload requires custom container sizing or concurrency (see Python UDFs).

Top-level Python statements (import, helper functions, classes, and def {entry_point}(...)) inside AS r'''...''' must have zero leading indentation (flush to the left margin). Indenting top-level Python definitions to align with surrounding SQL causes an IndentationError when BigQuery loads the container module.

A. Offline / Vectorized Python UDF (No Connection Needed)

Omit WITH CONNECTION when the UDF only performs computation or uses PyPI packages (packages=[...]) / Cloud Storage libraries (library=['gs://...']). To vectorize execution over batches of rows, annotate the parameter with pd.DataFrame (or pyarrow.RecordBatch) and return a pd.Series:

[!WARNING] Vectorized operations must be row-independent: BigQuery calls vectorized UDFs on arbitrary row batches (up to max_batching_rows). Do NOT compute global column statistics (such as z-scores, dataset mean/std, or rank) across df, because each batch only sees an arbitrary slice of rows. Use SQL window functions ((val - AVG(val) OVER()) / NULLIF(STDDEV(val) OVER(), 0)) for dataset-wide statistics. Vectorized Python UDFs should perform row-independent calculations (e.g. geometric distances or multi-column math).

CREATE OR REPLACE FUNCTION `{project_id}.{dataset_id}.vectorized_distance`(
  x1 FLOAT64, y1 FLOAT64, x2 FLOAT64, y2 FLOAT64
)
RETURNS FLOAT64
LANGUAGE python
OPTIONS (
  runtime_version = 'python-3.11',
  entry_point = 'compute_distance'
)
AS r'''
import numpy as np
import pandas as pd

def compute_distance(df: pd.DataFrame) -> pd.Series:
    return pd.Series(
        np.hypot(df['x2'] - df['x1'], df['y2'] - df['y1']),
        index=df.index,
    )
''';

B. Online Python UDF Calling an External / Cloud API (WITH CONNECTION)

Include WITH CONNECTION only when the Python code makes outbound network or API calls at runtime.

Always configure explicit timeouts, logging, and prescriptive exception handling in the try...except block:

• Transient errors only → NULL: Catch retryable exceptions (google.api_core.exceptions.TooManyRequests, ServiceUnavailable, DeadlineExceeded, InternalServerError, and RetryError), log them with logging.warning, and return None so a transient blip does not abort the query. Do not catch the base class GoogleAPICallError here: it also matches PermissionDenied, Unauthenticated, and InvalidArgument.
• Fatal errors → raise: Let auth, permission, and invalid-argument errors propagate (or log and re-raise as RuntimeError) so they surface as a user error on the query instead of silently producing NULLs.
• Never log row values: Anyone with Cloud Logging access can read UDF logs regardless of BigQuery table permissions. Log exception types and messages, not input or output data. Logs are only emitted when the session sets SET @@udf.properties = JSON '{"enableDebugOutput": true}';.
• Set a per-request timeout: Retry(timeout=...) only caps the total retry duration; also pass timeout= on each client call.

1. Create a Cloud Resource Connection and Retrieve its Service Account:

   bq mk --connection --connection_type=CLOUD_RESOURCE \
     --location={region} --project_id={project_id} {connection_id}
   
   bq show --connection {project_id}.{region}.{connection_id}
   

2. Grant Permissions to the Connection Service Account: Grant roles/serviceusage.serviceUsageConsumer on {project_id} plus the required API role (e.g., roles/cloudtranslate.user) on the target project. Running GRANT ... ON PROJECT modifies the project's IAM policy and requires resourcemanager.projects.setIamPolicy (for example, roles/resourcemanager.projectIamAdmin); confirm with the user before running project-level IAM grants. The DCL connection: grantee takes the connection path ([project_id.]location.connection_id), not the service account email; BigQuery resolves the connection's service account automatically (use "serviceAccount:{connection_sa_email}" to grant by email instead):

   GRANT `roles/serviceusage.serviceUsageConsumer`
   ON PROJECT `{project_id}`
   TO "connection:{project_id}.{region}.{connection_id}";
   
   GRANT `roles/cloudtranslate.user`
   ON PROJECT `{project_id}`
   TO "connection:{project_id}.{region}.{connection_id}";
   

3. Create the Python UDF with WITH CONNECTION (keep top-level Python statements flush-left at column 0):

CREATE OR REPLACE FUNCTION `{project_id}.{dataset_id}.translate_to_es`(
  text STRING
)
RETURNS STRING
LANGUAGE python
WITH CONNECTION `{project_id}.{region}.{connection_id}`
OPTIONS (
  entry_point = 'do_translate',
  runtime_version = 'python-3.11',
  packages = ['google-cloud-translate>=3.11', 'google-api-core']
)
AS r'''
import logging
from google.api_core import exceptions
from google.api_core.retry import Retry
from google.cloud import translate

client = translate.TranslationServiceClient()

TRANSIENT_ERRORS = (
    exceptions.TooManyRequests,
    exceptions.ServiceUnavailable,
    exceptions.DeadlineExceeded,
    exceptions.InternalServerError,
    exceptions.RetryError,
)

def do_translate(text: str) -> str:
    if not text:
        return None
    try:
        # Note: Replace {project_id} with your Google Cloud Project ID
        response = client.translate_text(
            request={
                "parent": "projects/{project_id}/locations/us-central1",
                "contents": [text],
                "target_language_code": "es",
                "mime_type": "text/plain",
            },
            retry=Retry(timeout=30.0),  # Total retry budget.
            timeout=10.0,  # Per-attempt deadline.
        )
        return response.translations[0].translated_text
    except TRANSIENT_ERRORS as e:
        # Log the error type only; never log row values.
        logging.warning("Transient Translation API error: %s", type(e).__name__)
        return None
    except exceptions.GoogleAPICallError as e:
        # PermissionDenied, Unauthenticated, InvalidArgument, etc. are fatal.
        logging.error("Fatal Translation API error: %s: %s", type(e).__name__, e)
        raise RuntimeError(f"Translation failed: {type(e).__name__}") from e
''';

See Python UDFs for container sizing (container_cpu, container_memory, container_request_concurrency), Cloud Logging (SET @@udf.properties = JSON '{"enableDebugOutput": true}';), and checking container build status via INFORMATION_SCHEMA.ROUTINES.

4. Remote Functions (Cloud Run Endpoints)

Use Remote Functions when the endpoint is hosted on Cloud Run or Cloud Run functions (for non-Python languages, VPC networking, or custom hardware):

1. Grant roles/run.invoker to the Connection Service Account (confirm with the user before modifying the Cloud Run service IAM policy):

   CLOUDSDK_METRICS_REQUEST_ATTRIBUTION="agent-skills/1.0 (skill:bigquery-udfs)" \
   gcloud run services add-iam-policy-binding {cloud_run_service} \
     --region={region} \
     --member="serviceAccount:{connection_sa_email}" \
     --role="roles/run.invoker"
   

2. Register the Remote Function: The endpoint must accept {"calls": [[arg1, ...], ...]} and return {"replies": [res1, ...]} with matching element count:

   CREATE OR REPLACE FUNCTION `{project_id}.{dataset_id}.enrich_address`(
     street STRING, postal_code STRING
   )
   RETURNS JSON
   REMOTE WITH CONNECTION `{project_id}.{region}.{connection_id}`
   OPTIONS (
     endpoint = 'https://{cloud_run_service_url}',
     max_batching_rows = 1000
   );
   

See Remote Functions for Cloud Run handler templates and retry handling.

Validation Checklist

After generating or modifying a UDF, follow this validate→fix→repeat loop:

• Step 1 — Validate Python code before BigQuery DDL: For Python UDFs, validate the Python function and packages dependencies before submitting the BigQuery DDL—either locally with python3 test inputs (None, edge cases, pd.DataFrame batches) or in a containerized Cloud Run Job (gcloud run jobs deploy {job_name} --source . --region={region} and gcloud run jobs execute {job_name} --region={region} --wait; see Python UDFs Validation).

• Step 2 — Execute DDL and poll container build status: Run CREATE OR REPLACE FUNCTION. Because the DDL statement returns before the Python container image finishes building, poll INFORMATION_SCHEMA.ROUTINES until build_state transitions from IN_PROGRESS to SUCCEEDED (or fix and re-run if FAILED):

  SELECT build_status.*
  FROM `{project_id}.{dataset_id}`.INFORMATION_SCHEMA.ROUTINES
  WHERE routine_name = '{udf_name}';
  

• Step 3 — Test the UDF with SQL SELECT: Once build_state = 'SUCCEEDED' (or immediately after DDL for SQL/JS UDFs), run a test SELECT query covering NULL and valid inputs.

Cleanup & Teardown

Delete unused routines, connections, Cloud Run services, and staged Cloud Storage artifacts (note