Get hands-on with what's next in Foundry IQ. Build a knowledge base that grounds answers in your documents with citations. Then go beyond classic RAG with a Microsoft-hosted agentic retriever, graph structures that connect entities and relationships across records, and topics that reveal themes across a corpus. Compare the results side by side and learn when to use each approach.
If you're following along during a live session:
- Sign in to the lab environment provided for the session
- Follow the lab instructions in the Skillable sidebar
If you're learning at your own pace:
- Clone this repository
- Deploy the Azure resources to your own subscription by following Deploy to your own Azure subscription
- Follow the lab instructions and run the
notebooks in
src/notebooks/. See the source guide for setup details.
Setup restores three search indexes from snapshots: cocoarynth-topics for
named topic vectors and sitemap GQL, cocoarynth-chunks for PDF chunks and
embeddings, and cocoarynth-graph for ontology-constrained business triples.
It also splits the chunk snapshot into three document-group indexes for Part 1.
The business ontology is a checked-in OWL file,
not an index. Both the business graph and the topic sitemap use the November
inline-ontology private preview; the target Search service must have access.
By the end of this session, you will be able to:
- Build a Foundry IQ knowledge base over multiple indexes, follow its citations back to source documents, and compare standard agentic retrieval with microsoft-retriever-1
- Use an ontology, GQL queries, and graph provenance to answer questions that follow explicit relationships across records
- Explore labeled topic groups and compare topic-based routing with direct vector search
- Foundry IQ
- Agentic retrieval in Azure AI Search
- microsoft-retriever-1
- Entity graphs in Azure AI Search
- Topic graphs in Azure AI Search
- Microsoft Foundry Models
Pick your next step based on your learning style:
| Resource | What you'll get |
|---|---|
| Ignite 2026 Next Steps | Additional session repos and materials from Microsoft Ignite 2026 |
| Microsoft AI Skills Navigator | Discover AI skills, learning paths, and resources for your next step |
| Microsoft Learn | Official documentation and guided learning paths on these topics |
| Microsoft Foundry Community | Connect with other learners and experts in our Discord community |
The Microsoft Learn MCP Server gives your AI agent direct access to Microsoft's official documentation — grounded, up-to-date answers about the topics in this session.
GitHub Copilot CLI — Install with:
copilot plugin install microsoftdocs/mcpFor more information, visit the Learn MCP Server repo.
![]() Pamela Fox 📢 |
![]() Matt Gotteiner 📢 |
![]() Ayca Bas 📢 |
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
Any use of third-party trademarks or logos are subject to those third-party's policies.



