Content by Foundry IQ microsoft-retriever-1 team (1)

The Foundry IQ microsoft-retriever-1 team introduces Microsoft Retriever 1, a preview model that handles agentic retrieval without reindexing or additional provisioning. Benchmarks show lower knowledge-base latency and token usage, while search API results improve recall at added latency. The team also explains configuration options and remaining limitations.
Community

End of content

Rejoining the server...

Rejoin failed... trying again in seconds.

Failed to rejoin.
Please retry or reload the page.

The session has been paused by the server.

Failed to resume the session.
Please reload the page.