Databricks Community

Based on your description, you are encountering a 500 Server Error when trying to use the Langchain ChatDatabricks integration with a Databricks Serving Endpoint connected to an external OpenAI GPT-4 Turbo model on Azure. This error usually indicates...

To dynamically select a prompt template in Databricks based on the input prompt received through a legacy model serving endpoint, you can implement a Python function that maps incoming prompts to specific templates. This often involves using conditio...

You can achieve combined retrieval across both PDF-extracted unstructured data and multiple columns from structured Delta tables in Databricks, but there are important considerations and available patterns to optimize this workflow for your RAG appli...

Your multi-agent framework has several issues affecting agent iteration control and error handling. Here’s a lined explanation and practical suggestions for each problem: Agents not stopping at one iteration Agents consistently reaching the max iter...

Overwriting a Delta table versus using a MERGE operation has different impacts on Databricks vector index sync, especially when Change Data Feed (CDF) is enabled and your embeddings are generated via Azure OpenAI models. Overwrite Mode When you overw...

AI/BI Genie is confirmed to use Azure OpenAI under the hood, as it leverages generative AI models for translating natural language into analytical queries and producing business intelligence insights. Additionally, there is strong evidence that Langc...

To use a custom MLflow pyfunc model for sentence-transformers with preprocessing, you need to comply with the expected interface of mlflow.pyfunc.PythonModel, especially the predict method. The method signature, data handling, and serialization are k...

Greetings @smferro54epam , the errors point to two distinct issues: your custom MCP app expects OAuth-based Databricks credentials (not a raw bearer token), and the URL you pass to the HTTP transport must be a fully qualified https URL to the app’s /...

Greetings @Maylin ,  A single many-to-many multilingual model, fine-tuned jointly across your 17 languages, is usually the best trade-off between quality, scalability, and operational simplicity; combine it with lightweight adapters to preserve quali...

Greetings @MarsWalker ,  here’s how to get true streaming from a served RAG chain on Databricks Model Serving.   What’s going on The served endpoint error (“This endpoint does not support streaming”) is expected when the deployed entity doesn’t expos...

Greetings @c4ndy ,  Thanks for sharing the context and links. I couldn’t read the Databricks Community thread from the URL you provided; please verify the URL and access settings, as it may not yet be available to Glean or require additional permissi...

Greetings @avadhut22111997 , sorry this fell through the cracks. I am Happy to help you lock down access to a single Genie Space so the user can only view it and ask questions there.   What “view and ask only” means in Genie Give the user the Genie S...

Hey @tholers , here’s how Databricks handles data for the embedding model endpoints and what that means for tenant and data residency requirements. Short answer If you use Databricks-hosted embedding endpoints (for example, GTE-Large or BGE-Large), y...