Microsoft Foundry brings Azure API Management support to all Foundry model integrations in Azure AI Search, now in public preview. Enterprise platform engineers and AI solution teams running large-scale RAG pipelines can place Foundry and Azure OpenAI models behind APIM for the GenAI Prompt Skill, embedding models, and vectorizer operations used at indexing and query time. APIM provides traffic shaping, load balancing, custom domains, identity governance, and private connectivity in front of every model endpoint a Search workload depends on. Customers can eliminate indexing failures caused by endpoint throttling or outages, stabilize high-throughput ingestion, and consolidate authentication and policy management into a single control plane. Operations teams gain consistent observability and audit trails across enrichment dependencies, while RAG systems hold accuracy and freshness as content volume grows.
Learn more.