- 41943 Views
- 24 replies
- 51 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 ...
- 41943 Views
- 24 replies
- 51 kudos
- 51 kudos
Great initiative by Databricks! This is a valuable opportunity to build practical GenAI skills and stay ahead in the rapidly evolving AI space.
- 51 kudos
- 2226 Views
- 6 replies
- 5 kudos
Resolved! Request to Enable Foundation Model Endpoint Rate Limits
Hi,I'm working on a trade surveillance agent and need access to foundation model endpoints.Currently getting this error when calling any LLM endpoint:Error: "The endpoint is temporarily disabled due to a Databricks-set rate limit of 0"Could you pleas...
- 2226 Views
- 6 replies
- 5 kudos
- 5 kudos
@balajij8 -- qwen3-next-80b-a3b-instruct model has been very helpful for my POC/use case as it gives consistent and reproducible results.
- 5 kudos
- 635 Views
- 1 replies
- 1 kudos
'Schedules' feature in Genie One
I have created a schedule in the Genie One interface to share a report generated by Genie using my natural language questions. I receive the report on my outlook as expected.Is it possible to add other people to the schedule so that they receive the ...
- 635 Views
- 1 replies
- 1 kudos
- 1 kudos
Hi DevyaniHow are you doing today? as per my knowledge, No, not today. A Genie One schedule belongs to whoever created it. The fields are only Title, Instructions, Connections, Schedule and Timezone, so there is no subscriber list, and the email goes...
- 1 kudos
- 913 Views
- 1 replies
- 0 kudos
Enable Foundation Model APIs for AWS Marketplace trial workspace
Hello,I created a new Databricks account through the AWS Marketplace $400 trial using my business email. The workspace is in us-east-1, the AWS Marketplace payment method is connected, and the full $400 credit balance is active.Every Databricks-hoste...
- 913 Views
- 1 replies
- 0 kudos
- 0 kudos
That 403 with "rate limit of 0" isn't something you accidentally configured, it's a Databricks-imposed gate that applies to newly created accounts. Even with active trial credit and a valid payment method on file, Foundation Model API access gets hel...
- 0 kudos
- 850 Views
- 1 replies
- 0 kudos
New Agentic AI Ecosystem in Databricks
it seems Databricks is moving from traditional RAG pipelines toward agent-native architectures with Lakebase Search, Genie Agents, MCP integration, and semantic business context.For teams building enterprise GenAI applications today:Are you still bui...
- 850 Views
- 1 replies
- 0 kudos
- 0 kudos
Given Databricks is now very mature in the Agentic/AI landscape comparing to 1 year ago, we are starting to leverage most of the capabilities from Databricks such as:1. Vector Search for Vector Database -> Transitioning to Lakebase Search.2. Lakebase...
- 0 kudos
- 973 Views
- 2 replies
- 0 kudos
Short Term Memory & Long Term Memory
I am building an Agentic Application on Databricks using LangGraph (Classic Compute — Serverless cant be used so Agent Brickscant be used ).I want my agent to have two types of memory:Short-term memory → Remember the current conversation and tool out...
- 973 Views
- 2 replies
- 0 kudos
- 0 kudos
Use two layers: Short-term: LangGraph checkpointer for thread/session state.Long-term: for your case, prefer Databricks Managed Memory if available; otherwise use self-managed Lakebase. Managed memory is the simplest cross-session option and works wi...
- 0 kudos
- 1153 Views
- 1 replies
- 1 kudos
Resolved! Enforcing Minimum Cohort Size in a Databricks App with AI/BI Genie
Hello, I'm currently building a Databricks App using AppKit and AI/BI Genie to let business users ask natural-language questions over registration and customer-demographic data. For privacy protection, demographic records are currently filtered so th...
- 1153 Views
- 1 replies
- 1 kudos
- 1 kudos
There's no built-in Genie feature that enforces a post-join HAVING threshold centrally, so you're right to think about this architecturally. The most reliable pattern in AppKit is to own the query execution layer yourself rather than letting Genie se...
- 1 kudos
- 784 Views
- 1 replies
- 1 kudos
Governance for vector search across multi domain unstructured data
What is the recommended governance strategy for Databricks Vector Search in an enterprise Unified Data Platform (UDP) where structured and unstructured data from multiple business domains (Sales, Marketing.) is ingested into a common analytics platfo...
- 784 Views
- 1 replies
- 1 kudos
- 1 kudos
The short answer on index architecture: separate indexes per domain is usually the right call for an enterprise setup, not a single shared index with metadata filters. Here's why the "one index with filtering" approach is tempting but fragile. Vector...
- 1 kudos
- 1110 Views
- 1 replies
- 0 kudos
Official databricks-openai package fails to import after resolving databricks-vectorsearch
I filed a detailed GitHub issue here:https://github.com/databricks/databricks-ai-bridge/issues/433Summary:A clean install of `databricks-openai==0.15.0` currently resolves `databricks-vectorsearch==0.74`, after which the documented import fails:```py...
- 1110 Views
- 1 replies
- 0 kudos
- 0 kudos
Good news, this is already fixed. A Databricks maintainer confirmed the bug on your GitHub issue and shipped databricks-openai==0.16.0 together with databricks-ai-bridge==0.20.0 on June 10 to resolve it. So the actual fix, instead of pinning databric...
- 0 kudos
- 644 Views
- 1 replies
- 0 kudos
Genie not able to list MCP prompts
Hi community,I'm building a custom MCP proxy server (hosted as a Databricks App) that forwards requests to an upstream MCP server. The upstream server exposes both **tools** and **prompts** as per the MCP specification.I can confirm that Genie Code s...
- 644 Views
- 1 replies
- 0 kudos
- 0 kudos
This almost always turns out to be st.cache_resource on the connection, not the reverse proxy reusing anything. You said you checked your st.cache_data functions and they key on username, which is the right instinct, but the leak usually hides in wha...
- 0 kudos
- 1273 Views
- 1 replies
- 1 kudos
Resolved! Genie API List Conversations Incomplete
Hello,In my team we have a dashboard that tracks the Genie Answers Quality: the question that was made, the feedback, who made it,... We use the Genie API to extract the conversations of the Genie, write the data into a table, and feed the dashboard ...
- 1273 Views
- 1 replies
- 1 kudos
- 1 kudos
Genie agents are documented to support up to 10,000 conversations per agent and 10,000 messages per conversation, and the API is designed to retain prior messages as conversation context rather than silently omitting them. More likely causes are: You...
- 1 kudos
- 982 Views
- 2 replies
- 0 kudos
credential delegation not found (404) / permission delegation name (500)
Hi, We run a monitoring integration that reads a Genie space's conversations via the Conversation API, using a service principal with CAN MANAGE on the space - capturing each conversation's prompt, generated SQL, and query result.Listing conversation...
- 982 Views
- 2 replies
- 0 kudos
- 0 kudos
Thank you very much, @Lu_Wang_ENB_DBX — this is really helpful and provides great insights! As a first step, we’ll ask the customer enable Genie chat sharing and check whether our monitoring identity can then read the results. If the 404s/500s pers...
- 0 kudos
- 1258 Views
- 1 replies
- 0 kudos
Resolved! Order of common questions in genie room
I want to add a set of Common Questions to my genie room as a guideline for users of what functions (i.e., question types) they are encouraged to choose from. I want it to be like a pseudo-menu, with functions F1, F2, and F3. The actual questions w...
- 1258 Views
- 1 replies
- 0 kudos
- 0 kudos
Unfortunately, not at the moment. I've explored this as well, including the possibility of removing or customizing the menu/action buttons, but there currently isn't any control available for that.The only option is to include a list of suggested que...
- 0 kudos
- 2604 Views
- 3 replies
- 2 kudos
Resolved! OBO Authentication with Unity AI Gateway and databricks.agents.deploy()
Hi everyone,I'm trying to use the new Unity AI Gateway v2 (beta) endpoint from an agent deployed with the Mosaic AI Agent Framework and I'm running into what looks like a scope mismatch.Library versionsdatabricks-agents==1.11.0mlflow==3.12.0python~3....
- 2604 Views
- 3 replies
- 2 kudos
- 2 kudos
This isn't a config problem on your end, it's a support gap. On-behalf-of auth for the standalone Unity AI Gateway beta endpoint isn't supported yet when you're deploying through databricks.agents.deploy(). Specifically, "ai-gateway" isn't a valid va...
- 2 kudos
- 1726 Views
- 9 replies
- 0 kudos
AI Search Endpoint Quota in Azure
I have seen the common responses to most in this thread, so I will get ahead of it by saying that our workspace is not a trial, but a premium workspace in Azure. I am a global admin in the workspace as well. It seems like a lot of the AI settings g...
- 1726 Views
- 9 replies
- 0 kudos
- 0 kudos
Hi, this doesn't appear to be a product limitation. The documented default quota is 500 AI Search endpoints per workspace, and the documentation explicitly notes that this limit can be increased through your account team. Because of that, a Premium w...
- 0 kudos
- 1139 Views
- 1 replies
- 1 kudos
Resolved! Does "move fast and break things" ruin AI agents?
Is the "move fast and break things" startup mindset actually fatal for custom AI agent development?I read that rushing MVPs creates massive tech debt and unstable guardrails that cause projects to crash by year two.Have any of you hit this "year 2 wa...
- 1139 Views
- 1 replies
- 1 kudos
- 1 kudos
Well, you can only break things which exist, so if you're delivering an MVP, nothing yet exists to be broken. This is kind of the wrong mindset, I think you should look at the agile process of "ship fast, ship small, iterate". Sometimes the iterati...
- 1 kudos
