All topics and tags

Azure OpenAI

9 articles tagged Azure OpenAI.

  1. Azure AI Search Integrated Vectorization: Indexing PDFs from Blob Storage

    Index business PDFs from Azure Blob Storage for RAG without custom code: an indexer, a Text Split and Azure OpenAI embedding skillset, index projections, and a vectorizer for text-to-vector queries.

    AI engineering12 min read
  2. Azure API Management AI Gateway: Token Limits and Load Balancing for OpenAI

    Put Azure API Management in front of Azure OpenAI to give each app its own token rate limit and quota, emit token metrics to Application Insights, and balance traffic across regions with circuit breakers.

    AI engineering12 min read
  3. Azure OpenAI Deployment Types: Global Standard vs Data Zone vs Provisioned

    Choose between Global Standard, Data Zone, Standard and Provisioned deployments in Azure OpenAI based on where data is processed, latency variance, throughput guarantees and billing model.

    AI engineering12 min read
  4. Azure OpenAI Keyless Access: Managed Identity, Entra ID and Private Endpoints

    Remove API keys from Azure OpenAI: call it with a managed identity and Entra ID RBAC, disable local auth, and reach it only through a private endpoint with public network access turned off.

    AI engineering12 min read
  5. Azure OpenAI model retirement runbook: avoid 410 errors, upgrade safely

    Track Azure OpenAI model retirement dates, set versionUpgradeOption, validate the replacement model and migrate provisioned deployments before the cutoff.

    AI engineering11 min read
  6. Build RAG Over SharePoint Documents Without Breaking Permissions

    Ground an internal AI assistant on SharePoint files so each user only gets answers from documents they can open, using the Copilot Retrieval API or Azure AI Search with ACL ingestion.

    AI engineering12 min read
  7. Fix Azure OpenAI 429 Too Many Requests: TPM, RPM and PTU limits

    Diagnose Azure OpenAI 429 errors on Standard and provisioned deployments and fix them with quota changes, max_tokens tuning, correct retries and spillover.

    AI engineering14 min read
  8. Fix Azure OpenAI content filter 400 errors: ResponsibleAIPolicyViolation

    Find which Azure OpenAI content filter category blocked a request, then fix false positives with custom content filters, Prompt Shields settings and blocklists.

    AI engineering12 min read
  9. Migrate from the Azure OpenAI Assistants API to Foundry Agent Service

    Move code from the retired Azure OpenAI Assistants API to Foundry Agent Service: assistants to agents, threads to conversations, runs to responses, plus exporting thread history.

    AI engineering10 min read