Hi @martkev -- good news: your model name is correct. The Vertex AI model ID for Claude Opus 4.6 is indeed claude-opus-4-6 (per Anthropic's official documentation). The issue is on the Databricks side -- the UI enforces an internal allowlist of recog...
Hi @pfzoz -- the "Model architectures failed to be inspected" error you are hitting is a well-known compatibility issue between vLLM, the transformers library, and the Qwen2/2.5-VL model family. The root cause is that vLLM's model registry subprocess...
Hi — great question! This is a common pattern when you have a large medallion architecture with many bronze-to-silver dependencies. There are several approaches you can take, ranging from simple to more advanced.
———
Option 1: Single DLT Pipeline wit...
This is a well-known class of issue with gRPC/HTTP2 long-lived streams being killed by network intermediaries. The fact that the Databricks SQL Connector (poll-based HTTP/1.1) works perfectly while Spark Connect (gRPC/HTTP2 streaming) fails is the ke...
This is a classic hub-spoke + on-premises hybrid networking scenario. Here's how to architect it end-to-end.
Architecture Overview
The traffic flow will be:
VM (VNet-App) --> ExpressRoute/VPN Gateway --> On-Prem Proxy Server --> ExpressRoute/VPN Gate...
