Skip to content

v2.1.0

Choose a tag to compare

View all tags
@placerda placerda released this 26 Jun 03:23
· 90 commits to develop since this release
v2.1.0
5411666
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Adds Foundry IQ runtime configuration support to the AI Landing Zone Bicep pattern used by GPT-RAG.

This release configures the infrastructure and post-provision steps needed for GPT-RAG to use Foundry IQ Knowledge Bases and Knowledge Sources as a retrieval backend.

What changed

  • Added Foundry IQ Knowledge Base and Knowledge Source runtime configuration.
  • Added App Configuration values used by GPT-RAG and the orchestrator.
  • Added knowledgeRetrieval billing configuration.
  • Added preflight and post-provision data-plane setup for Foundry IQ.
  • Enabled Azure AI Search semantic ranker standard when Foundry IQ is used.
  • Aligned generated Knowledge Base, Knowledge Source, and Search endpoint values for downstream GPT-RAG deployment.

Why it matters

Operators can provision GPT-RAG infrastructure with Foundry IQ support from the landing zone module instead of performing manual portal or data-plane setup after deployment.

Validation

Validated in a live Azure environment:

  • Landing zone provision completed successfully.
  • GPT-RAG deployment completed successfully against the generated configuration.
  • Foundry IQ Knowledge Base and Knowledge Source retrieval returned HTTP 200.
  • GPT-RAG frontend, ingestion, and orchestrator endpoints were healthy.

References

Assets 2
Loading