How to Manage "Grounding with Bing" Resources Programmatically

2026-02-12 · Source: Microsoft Foundry Blog articles · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure, Software Development & Engineering · Depth: Intermediate, quick

Summary

This blog post details how to programmatically manage "Grounding with Bing" resources, specifically "Grounding with Bing Custom Search," using Azure Resource Manager (ARM). It addresses the limitations of manual Azure portal deployments for scaled or CI/CD integrated environments. The article outlines two primary approaches: using the REST API and utilizing Python or C# SDKs. It provides a step-by-step guide for the REST API method, covering login, registering Bing as an Azure resource provider, preparing ARM templates, obtaining access tokens, and creating/configuring/managing Bing resources and their inclusion/exclusion lists. The post emphasizes using ARM templates for version-controlled, repeatable deployments and offers a GitHub repository with code examples.

Key takeaway

For MLOps Engineers managing "Grounding with Bing" deployments across multiple environments, adopting Azure Resource Manager (ARM) is crucial. You should transition from manual portal configurations to programmatic methods using REST APIs or SDKs to ensure consistency, enable version control, and integrate seamlessly with your CI/CD pipelines, reducing deployment errors and operational overhead.

Key insights

Programmatic management of "Grounding with Bing" resources via ARM enables scalable, consistent deployments.

Principles

• Define search settings as code.
• Integrate resource management with CI/CD.

Method

Automate "Grounding with Bing" resource provisioning and configuration using Azure Resource Manager (ARM) templates, either via REST API calls or Python/C# SDKs, to ensure consistency and version control.

In practice

• Use `az login` to authenticate Azure CLI.
• Register `Microsoft.Bing` as a resource provider.
• Utilize ARM templates for custom search configurations.

Topics

• Grounding with Bing
• Azure Resource Manager
• Programmatic Deployment
• REST API
• SDK Management

Code references

• Azure-Samples/foundry-bing-custom-search-arm

Best for: MLOps Engineer, DevOps Engineer, AI Engineer

Related on AIssential

• Scalable ML Runtime Deployment with H2O MLOps | Part 7 — Automated validation and isolated, scalable runtime environments are crucial for robust ML model deployment.
• Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents — Decoupling search from LLM reasoning via a vendor-agnostic gateway improves control, reduces cost, and enhances performance for agentic workloads.
• Manage AI costs with Amazon Bedrock Projects — Amazon Bedrock Projects enables granular cost attribution for AI workloads using tagging and integration with AWS billing tools.
• Cross-Region Model Connectivity Options in Microsoft Foundry: Supported Patterns and Tradeoffs — Azure API Management enables governed, VNet-secured cross-region model access in Microsoft Foundry, extending agent and inference capabilities.
• Combine code repositories with Confluence MCP for maximum context — Custom Cloud Code commands automate complex deployment tasks by prioritizing internal documentation and code repositories.
• Stop Celebrating The Illusion of Progress In AntiGravity Update! — Celebrating basic operational transparency as progress highlights fundamental platform design deficiencies.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Microsoft Foundry Blog articles.