- 33367 Views
- 22 replies
- 46 kudos
Databricks Announces the Industry’s First Generative AI Engineer Learning Pathway and Certification
Today, we are announcing the industry's first Generative AI Engineer learning pathway and certification to help ensure that data and AI practitioners have the resources to be successful with generative AI. At Databricks, we recognize that generative ...
- 33367 Views
- 22 replies
- 46 kudos
- 46 kudos
Dear Certifications TeamI have completed full Generative AI Engineering Pathway, so I received module wise knowledge badge but I didn't received the overall certificate which mentioned in description which is Generative AI Engineer with one Star. Req...
- 46 kudos
- 691 Views
- 1 replies
- 1 kudos
Resolved! Running Into Erroneous "Databricks Connected" Messages with Claude Desktop
When I try to connect Databricks via the connector that is now available within Claude Desktop to a genie space I have available (which is just the default test one), Databricks appears to say that it connects successfully, but it never actually work...
- 691 Views
- 1 replies
- 1 kudos
- 1 kudos
Greetings @kcailabs , Thanks for sharing the screenshots—this helps. From what I can see, Claude shows a “Successfully connected to Databricks” toast while the Databricks connector still displays “Disconnected,” and the Server URL entered is just a p...
- 1 kudos
- 5303 Views
- 4 replies
- 3 kudos
How to implement prompt caching using Claude models?
Hi, I am trying to use prompt caching future using claude "databricks-claude-sonnet-4" databricks endpoint (wrapped in a ChatDatabricks instance). Using langchain, I set SystemMessage( content=[ { ...
- 5303 Views
- 4 replies
- 3 kudos
- 3 kudos
@DinoSaluzzi If you can restructure your system& user prompt in a similar manner to the examples provided, prompt caching should start working as expected. messages = [ { "role": "system", "content": [ { ...
- 3 kudos
- 783 Views
- 1 replies
- 1 kudos
Getting error while trying to use external MCP
I have created a mcp connection from marketplace :Conn Name : mcp_brightdata_web_surfermcp product url : https://brightdata.com/I have attached the mcp through playground . But while submitting the prompt I am getting the following error .Error : The...
- 783 Views
- 1 replies
- 1 kudos
- 1 kudos
Based on the error, which is a "502 Bad Gateway" error indicates that a server sitting as a gateway or proxy received an invalid response from an upstream server. Here, Databricks is trying to communicate with the external MCP server associated with...
- 1 kudos
- 2925 Views
- 13 replies
- 6 kudos
Resolved! AgentBricks - Multi Agent Supervisor Issue
Hi, I am doing POC using AgentBricks and using Multi Agent Supervisor. I have configured 2 subagents.1. Genie Space2. UC Function to call LLM3. UC Function to plot chartsHowever, the agent is able to access and use only Genie space agent and not usin...
- 2925 Views
- 13 replies
- 6 kudos
- 6 kudos
Also, as you can see on the top right of the attached image, it creates an MLFlow experiment. Click on that MLflow experiment, and check the traces and let me know what it shows, as you can see here it shows the tool is being called in the trace. ...
- 6 kudos
- 1212 Views
- 1 replies
- 4 kudos
Why Agent Bricks Is a Game Changer
Check out Agent Bricks — Databricks’ new framework for building AI agents without writing a single line of code. Picture this: you describe your business challenge in plain English, point it at your data, and boom… a domain-specific agent comes to li...
- 1212 Views
- 1 replies
- 4 kudos
- 4 kudos
Absolutely love the direction Databricks is heading with Agent Bricks — this is true innovation. Taking something as complex as building AI agents and turning it into a no-code, domain-aware, business-ready framework is a huge leap forward for teams ...
- 4 kudos
- 933 Views
- 4 replies
- 0 kudos
Add AI Guardrail results into response?
We're considering switching from Azure AI Foundry to Mosaic AI Gateway. One nice feature AI Foundry has is it adds the content filter results to the response (and in a streaming response, each delta). This allows us to provide some feedback to the ...
- 933 Views
- 4 replies
- 0 kudos
- 0 kudos
To include AI Guardrail results in your responses, you need to enable logging or metadata propagation when the model generates output. Check if Mosaic AI Gateway supports attaching Guardrail flags or filter results as part of the response payload or ...
- 0 kudos
- 564 Views
- 3 replies
- 0 kudos
Databrcks + sharepoint +Microsoft Teams Bot
I recently created a Teams Bot using Databricks Genie, and some of the data I want to retrieve from Databricks can be very large. The solution I am thinking of is for every bot request which will lead to lots of rows and columns to be retrieved, I wa...
- 564 Views
- 3 replies
- 0 kudos
- 0 kudos
Hello @KaushalVachhani I was trying to find out if Databricks already has a template for this part "Genie Conversation API, saves it as a CSV file, and uploads it to SharePoint" Because the data might be big, eg more than 50 rows with more than four ...
- 0 kudos
- 523 Views
- 2 replies
- 1 kudos
System tables for vector search index?
Are there system tables or log files for monitoring vector search index searches? I didn't see vector search mentioned on the system tables documentation (Monitor account activity with system tables - Azure Databricks | Microsoft Learn).
- 523 Views
- 2 replies
- 1 kudos
- 1 kudos
Thanks @mark_ott are there plans to make the vector search a "proper" system table in Databricks rather than using an Azure Monitor table?
- 1 kudos
- 520 Views
- 1 replies
- 1 kudos
MLflow LangChain Model Serving Fails: _UNSUPPORTED_MODEL_ERROR_MESSAGE ImportError
I’m trying to log and serve a LangChain-based RFI chatbot model using MLflow in Databricks, but I’m encountering the following error when loading the model:ImportError: cannot import name '_UNSUPPORTED_MODEL_ERROR_MESSAGE' from 'mlflow.langchain.util...
- 520 Views
- 1 replies
- 1 kudos
- 1 kudos
@Darshan13 , Based on the error, It looks like when Databricks Model Serving tries to load your model, MLflow's internal code attempts to import _UNSUPPORTED_MODEL_ERROR_MESSAGE which doesn't exist in the LangChain utils structure. Are you successful...
- 1 kudos
- 4465 Views
- 1 replies
- 0 kudos
Add Azure Databricks tables as knowledge source into Copilot Studio Agent
Hello!I’m trying to add some tables from my Azure Databricks as a knowledge source in a Copilot Studio agent so that I can ask questions about the information stored in these tables.The connection is created successfully, and I can see a preview of m...
- 4465 Views
- 1 replies
- 0 kudos
- 0 kudos
If your Azure Databricks tables show up as a knowledge source in Copilot Studio, but the agent cannot access data when you ask questions, the issue is often related to user or service account permissions, network rules, or the configuration of the ta...
- 0 kudos
- 7070 Views
- 4 replies
- 0 kudos
Unable to log MLFlow run for LangChain chain while using databricks-langchain library
Whenever I try to log my run it throws me the following error: MlflowException: Failed to save runnable sequence: {'0': 'RunnableParallel<query,context> -- Failed to save runnable sequence: {\'context\': "RunnableSequence -- Failed to save runnable s...
- 7070 Views
- 4 replies
- 0 kudos
- 0 kudos
Hi @heramb13 , Your chain is being serialized by MLflow; during that process MLflow re-imports each runnable by its module path. The error shows MLflow is trying to import ChatDatabricks from the legacy module path “langchain_databricks”, which isn’t...
- 0 kudos
- 4785 Views
- 1 replies
- 0 kudos
Unable to add dependencies to mlflow.langchain.log_model
Hello,I'm doing this-with mlflow.start_run(run_name="run1"): logged_chain_info = mlflow.langchain.log_model( # lc_model=os.path.join(os.getcwd(), 'full_chain'), this doesnt work too lc_model='/Workspace/Users/{user_name}/exp/d...
- 4785 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @yashshingvi , Thanks for the details—this is a common gotcha with MLflow “models from code.” Why your imports fail code_paths are only added to sys.path when the model is loaded (for inference/serving), not while the driver is executing mlflow.la...
- 0 kudos
- 4886 Views
- 1 replies
- 2 kudos
AI/BI Genie - Real world experience?
I have been tasked with creating a NLP interface for management to our internal datalake that has numerous joined tables around customer information. I have tried the hello-world llamaindex, langchain sql/pandas agents with limited success (too many ...
- 4886 Views
- 1 replies
- 2 kudos
- 2 kudos
Hi there Sam,I work for Databricks. The pace of innovation with AI/BI is wild (fast). Databricks itself just migrated off a leading BI platform and now exclusively runs its business on AI/BI (Blog). We also have customer testimonials on our website, ...
- 2 kudos
- 4352 Views
- 5 replies
- 3 kudos
Using Genie in Multi-Agent Systems — SQL Query Missing from Output
Hi Community,I’ve implemented a multi-agent system using Genie in Databricks, following the guide on "Use Genie in multi-agent systems | Databricks Documentation". The system integrates well with vector indexes, and everything works fine during model...
- 4352 Views
- 5 replies
- 3 kudos
- 3 kudos
When using a custom Genie agent with the Databricks Genie REST API (GetMessage endpoint), extracting SQL queries and results works well as a standalone agent. However, integrating this custom agent into a multi-agent framework (especially when combin...
- 3 kudos
- 5451 Views
- 2 replies
- 0 kudos
DatabricksFunctionClient : PERMISSION_DENIED when creating the client
Hello, I'm currently working with Databricks features to create an AI agent system. In the documentation it's written that the library DatabricksFunctionClient is needed to register custom tools to UC. I followed the different steps from the explana...
- 5451 Views
- 2 replies
- 0 kudos
- 0 kudos
This error is most often due to missing permissions, workspace types, or cluster configuration settings necessary for AI agents and custom tools to access Unity Catalog (UC) functions using Spark Connect in Databricks. The main causes and solutions a...
- 0 kudos
