cancel
Showing results for 
Search instead for 
Did you mean: 
Generative AI
Explore discussions on generative artificial intelligence techniques and applications within the Databricks Community. Share ideas, challenges, and breakthroughs in this cutting-edge field.
cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Sujitha
by Databricks Employee
  • 35206 Views
  • 22 replies
  • 47 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 ...

Screenshot 2024-01-24 at 11.32.01 PM.png
  • 35206 Views
  • 22 replies
  • 47 kudos
Latest Reply
Darshan137
New Contributor II
  • 47 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...

  • 47 kudos
21 More Replies
michael365
by New Contributor III
  • 583 Views
  • 1 replies
  • 1 kudos

Resolved! Purpose and usage of Entity matching in Genie Spaces

Hi all,I'm tyring to improve a Genie space and and experimenting with features like Format assistance and Entity matching for single columns.Doens anybody know how to use Entity matching feature?Documentation says:"Entity matching: Entity matching pr...

  • 583 Views
  • 1 replies
  • 1 kudos
Latest Reply
Ashwin_DSA
Databricks Employee
  • 1 kudos

Hi @michael365, You don’t configure those 1,024 distinct values manually anywhere. For each column with Entity matching turned on, Genie automatically scans the underlying table (up to 100M rows) and picks up to 1,024 distinct values (currently the m...

  • 1 kudos
wirrywoo
by New Contributor III
  • 1205 Views
  • 6 replies
  • 3 kudos

Resolved! Are there limits set for Agent Mode in Databricks Free Edition?

Hi everyone,I’ve been trying out Agent Mode in the Databricks Free Edition and I’m a bit unclear on the usage limits.From what I can tell, Agent Mode seems to default back to chat mode after a certain point, and when I was using it more heavily, I st...

  • 1205 Views
  • 6 replies
  • 3 kudos
Latest Reply
wirrywoo
New Contributor III
  • 3 kudos

Great thank you for the explanation @Ashwin_DSA . Very helpful response!I'll be more conscious of my usage of Genie in Free Edition moving forward. To re-enable Genie in my Free Edition workspace, would I just need to wait until the limits are reset ...

  • 3 kudos
5 More Replies
juliechen
by New Contributor II
  • 253 Views
  • 1 replies
  • 1 kudos

Poll: With the current maturity of LLMs and Genie, how are you positioning Genie in your org

Do you see Genie (or similar AI analytics tools) as:1️⃣ Primarily for power users / data-savvy users to enhance their daily work by correlating multiple business signals to generate deeper insights and answer more complex questions for the organizati...

  • 253 Views
  • 1 replies
  • 1 kudos
Latest Reply
michael365
New Contributor III
  • 1 kudos

According to my experience both target groups can be adressed:Genie (spaces) are made for use by power usersEnabling Genie spaces via Databricks One* can be used by a broad organizationGenie Code is for technical persons e.g. data engineers, data sci...

  • 1 kudos
actualhuman_012
by New Contributor III
  • 387 Views
  • 2 replies
  • 0 kudos

Unable to make fresh deployments to an agent model serving endpoint due to permission issues

One of my teammate left and now I cannot make fresh deployments to the agent serving endpoint created by him. Getting below error while trying to deploy with agents.deploy(). Any way to solve it without recreating the endpoint?PermissionDenied: Princ...

  • 387 Views
  • 2 replies
  • 0 kudos
Latest Reply
szymon_dybczak
Esteemed Contributor III
  • 0 kudos

Hi @actualhuman_012 ,That a bit problematic. According to docs:Create custom model serving endpoints | Databricks on AWS"The identity under which a model serving endpoint runs is tied to the original creator of the endpoint.After endpoint creation, t...

  • 0 kudos
1 More Replies
Abeard1
by New Contributor II
  • 850 Views
  • 2 replies
  • 1 kudos

Genie Code severely regressed over the past 2 days — no longer behaves as before

Hi community,Starting around April 21, 2026, Genie Code in our Azure Databricks workspace has severely regressed and no longer functions the way it did before. No changes were made on our end — no DBR updates, no workspace config changes.We are a tea...

Generative AI
azure-databricks
generative-ai
genie-code
inline-editing
regression
  • 850 Views
  • 2 replies
  • 1 kudos
Latest Reply
Abeard1
New Contributor II
  • 1 kudos

@DivyaandData thank you for the quick response! I'm checking with my workspace admin to confirm whether AI partner-powered features are enabled. I'll report back shortly. This could definitely explain the degraded experience — the loss of Agent Mode ...

  • 1 kudos
1 More Replies
MA4
by New Contributor II
  • 1407 Views
  • 1 replies
  • 1 kudos

Resolved! Databricks Hosted Foundation Models usage and costs

Before proceeding with experimentation and subsequent production use of the Databricks‑hosted Foundation Models (e.g., Claude, Llama, Gemma via Foundation Model APIs), could you please confirm whether a separate agreement with the underlying model pr...

  • 1407 Views
  • 1 replies
  • 1 kudos
Latest Reply
Ashwin_DSA
Databricks Employee
  • 1 kudos

Hi @MA4, For Databricks-hosted foundation models that you access via Foundation Model APIs (for example, Claude, Llama, Gemma on Azure Databricks), you do not need to sign a separate commercial contract with Anthropic/Meta/Google in addition to your ...

  • 1 kudos
smith2
by New Contributor
  • 247 Views
  • 1 replies
  • 0 kudos

Need Help with This Issue in Databricks Workflow

Hi everyone,I’m currently working with Databricks and facing an issue related to my setup/workflow. I’ve tried checking the basic configurations, but I’m still not able to resolve it.Could someone please guide me on the best approach or point out wha...

  • 247 Views
  • 1 replies
  • 0 kudos
Latest Reply
Sumit_7
Esteemed Contributor
  • 0 kudos

@smith2 Please specify the issue faced and screenshots of errors will be helpful.

  • 0 kudos
nagamaddikunta
by New Contributor
  • 548 Views
  • 1 replies
  • 0 kudos

Resolved! AI playground - Unable to access LLM's

I was having playground access and now I  bumped up to enterprise access  The endpoint GPT-5.4 has encountered an error and responded with the following: InternalError{"error_code":"PERMISSION_DENIED","message":"PERMISSION_DENIED: The endpoint is tem...

  • 548 Views
  • 1 replies
  • 0 kudos
Latest Reply
Ashwin_DSA
Databricks Employee
  • 0 kudos

Hi @nagamaddikunta, Having checked this internally, this error message doesn’t come from the QPM/TPM values you see on the Serving endpoint. It means that, for your workspace, Databricks has set the system-level quota for that model to 0, so the GPT-...

  • 0 kudos
SlavaPeshkov
by New Contributor
  • 833 Views
  • 3 replies
  • 2 kudos

Resolved! Knowledge cutoff for Genie

Hi, I was trying to make a dashboard using AI Genie - it worked well for the basics, but was unable to perform some of the modifications that were obviously (via UI) doable. Per Genie's response below - it only knows Databricks documentation up to Ap...

  • 833 Views
  • 3 replies
  • 2 kudos
Latest Reply
emma_s
Databricks Employee
  • 2 kudos

Hi, Just wanted to add to what others have said and make sure its clear, I think you're trying to use a Genie Space to create your dashboard. But Genie code is probably a better tool here. If you have visuals created in a Genie space that you would l...

  • 2 kudos
2 More Replies
ShivaPolusani
by New Contributor II
  • 978 Views
  • 2 replies
  • 0 kudos

Claude Desktop connect to Databricks MCP

How do I connect Claude desktop to Databricks connector (available in connectors)What are the steps involved in it,  Can any one provide detailed step by step implementation for this so that I can query the data using Claude desktop please?

  • 978 Views
  • 2 replies
  • 0 kudos
Latest Reply
Sumit_7
Esteemed Contributor
  • 0 kudos

@ShivaPolusani This is achieved via MCP remote, using few args such as Workspace link and Token.Check the documentation here - https://docs.databricks.com/aws/en/generative-ai/mcp/connect-external-services?language=Claude+Desktop#pat-examplesVideo Li...

  • 0 kudos
1 More Replies
mansi26
by Databricks Partner
  • 547 Views
  • 2 replies
  • 2 kudos

Resolved! Request for blog publishing access

Hi,I would like to request access to publish blogs on the Databricks Community. I am a seasoned SME in Generative AI, with extensive hands-on experience in this domain. I have actively worked on various GenAI use cases and regularly write about emerg...

  • 547 Views
  • 2 replies
  • 2 kudos
Latest Reply
szymon_dybczak
Esteemed Contributor III
  • 2 kudos

Hi @mansi26 ,Pleasure to meet you. You can publish your articles without asking for consent in community articles section:https://community.databricks.com/t5/community-articles/bd-p/Knowledge-Sharing-Hub 

  • 2 kudos
1 More Replies
GunaR
by New Contributor III
  • 3984 Views
  • 12 replies
  • 1 kudos

RLS in Genie Space

I am developing a Conversational BI Solution using Genie. There are users from different roles and we need to restrict the rows returned based on the user's role. Typically RLS. I understand from documentation Genie leverage the RLS setup on the Unit...

  • 3984 Views
  • 12 replies
  • 1 kudos
Latest Reply
Prathusha_
New Contributor II
  • 1 kudos

Hi Guna, I have been trying to implement the same in my environment. Do you have any luck?

  • 1 kudos
11 More Replies
martkev
by New Contributor III
  • 4064 Views
  • 1 replies
  • 0 kudos

Resolved! Error: "Invalid model name" in Databricks AI Gateway when setting up Vertex AI endpoint

Hi everyone,I'm trying to set up a new serving endpoint in Databricks using Google Cloud Vertex AI as the provider. I want to route it to claude-opus-4-6.However, as soon as I try to create it, I get the following UI error (see screenshot):"Invalid m...

martkev_0-1775828309497.png
  • 4064 Views
  • 1 replies
  • 0 kudos
Latest Reply
anuj_lathi
Databricks Employee
  • 0 kudos

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...

  • 0 kudos
trickywhitecat
by New Contributor
  • 626 Views
  • 1 replies
  • 0 kudos

Petition to update your documentation about inferencing LLMs and standardize LLM response format

TL;DRInconsistent & Undocumented Response Format: Contrary to Databricks documentation, enabling thinking.type for Gemini 2.5 Flash changes the ChatCompletion content field from a standard string to a list of dictionaries, breaking expected behavior....

  • 626 Views
  • 1 replies
  • 0 kudos
Latest Reply
Louis_Frolio
Databricks Employee
  • 0 kudos

Hey @trickywhitecat , You're right that when thinking.type is enabled for Gemini 2.5 Flash on a Databricks serving endpoint, the content field comes back as a list of dictionaries instead of a plain string. That breaks the expected OpenAI ChatComplet...

  • 0 kudos
samuel86
by New Contributor III
  • 1707 Views
  • 1 replies
  • 1 kudos

Resolved! ai_query and cached tokens

Is ai_query actually able to use OpenAI's cached tokens? I was not unable to prove it. The response object from ai_query does not contain the raw response, and when I re-run an identical request via OpenAI SDK (identical model, settings etc.) and exa...

Generative AI
ai_query
  • 1707 Views
  • 1 replies
  • 1 kudos
Latest Reply
anuj_lathi
Databricks Employee
  • 1 kudos

Great question -- this is a nuanced topic because there are two layers involved: Databricks' proxy layer and OpenAI's caching mechanism. Short answer: No, ai_query does not currently support OpenAI's prompt caching. 1. ai_query doesn't expose token u...

  • 1 kudos