- 35189 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 ...
- 35189 Views
- 22 replies
- 47 kudos
- 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
- 687 Views
- 2 replies
- 0 kudos
Resolved! MLFlow tracking from Azure Container Instance
Hi everyone,we're building a voice chatbot for a customer using a mix of technologies — Databricks, Azure AI Foundry, and a few external containerized services.Currently, we're tracking requests and logs via Lakebase with custom traces, but I'm now e...
- 687 Views
- 2 replies
- 0 kudos
- 0 kudos
Similar response to the one from WorksBuddy. Short answer: yes, it's supported, and there's a specific Databricks guide for your case. The tutorial you found is for local/IDE; the production-container equivalent is here: Trace agents deployed out...
- 0 kudos
- 244 Views
- 1 replies
- 0 kudos
Provisioned throughput is not enabled for this workspace
I am seeing two related issues with Databricks-hosted Claude models in my workspace.Workspace details:- Cloud: AWS- Region: us-west-2- Tier: Premium PAYG- Serverless compute: enabled- Unity Catalog/metastore: configured- Compliance security profile...
- 244 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @andr11v, What you are seeing appears to be two separate issues rather than a single root cause. For the pay-per-token issue, the regional support table shows that Claude models are supported in AWS us-west-2, and the docs also say those models ar...
- 0 kudos
- 384 Views
- 1 replies
- 1 kudos
Resolved! Improving Genie Space via text instructions
Dear all,I'm trying to improve my Genie Space with some text instructions but very often Genie does not use it. If I prompt "Why have you not considered my instructions" after he answered a question he realizes that he forgot it. But this is too late...
- 384 Views
- 1 replies
- 1 kudos
- 1 kudos
Hi @michael365, There is no documented hard rule that "general instructions must be 20 lines or less." Databricks guidance is to keep text instructions small, focused, and well-organised, because long or overly broad instructions can become less effe...
- 1 kudos
- 423 Views
- 1 replies
- 2 kudos
Resolved! Genie Space API – Inspect Mode Limitation
Hi everyone,Is Inspect mode supported when using the Genie Space API?If not, is there any plan to support it in the future?I notice a significant difference in answer quality when using Genie with Inspect mode enabled and disabled in th Databricks UI...
- 423 Views
- 1 replies
- 2 kudos
- 2 kudos
Hi @lej6 ,For now inspection is not supported through Genie Space API. I guess it will be added in the future though. If my answer was helpful, please consider marking it as accepted solution.https://docs.databricks.com/aws/en/genie/conversation-api#...
- 2 kudos
- 370 Views
- 1 replies
- 1 kudos
Resolved! Facing issue while opening Genie Code
Hi,For the past 3-4 days, I have not been able to open the Genie Code AI assistant in the Databricks workspace. Earlier, it was working fine and was quite helpful for code development.I am getting the error message shown below (screenshot pasted). I ...
- 370 Views
- 1 replies
- 1 kudos
- 1 kudos
Hi @ashdc2026 ,Check below thread. Try to also delete cookies. If that won't help use inspect tool and attach more detailed error message:Solved: Not able to access Databricks AI assistant or crea... - Databricks Community - 147951
- 1 kudos
- 402 Views
- 1 replies
- 2 kudos
Resolved! OAuth authentication is required for MCP servers hosted on Databricks Apps
Hi all.I'm deploying an agent with a custom MCP using Databrikcs.Unfortunately when I try to test the MCP connectivity I receive this error:OAuth authentication is required for MCP servers hosted on Databricks Apps. Your current authentication method...
- 402 Views
- 1 replies
- 2 kudos
- 2 kudos
I found the issue. I missed to create the OAuth token into Identity & user. I was using the SP secret.
- 2 kudos
- 526 Views
- 1 replies
- 0 kudos
Resolved! FMAPI Anthropic endpoint rejects requests with trailing assistant message — known limitation?
Hey all — looking for confirmation on a behavior I'm hitting on the Foundation Model API (pay-per-token) Anthropic-compatible endpoint, in case anyone else has worked around it.What I'm doing: serving Claude models through /serving-endpoints/anthropi...
- 526 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @cormierjohn , Your understanding is correct. The validation rejecting a trailing assistant turn is happening at the FMAPI proxy layer before the request reaches Claude, so any client that uses Anthropic's prefill primitive will 400 against this e...
- 0 kudos
- 347 Views
- 1 replies
- 0 kudos
Genie PDF export corrupts non-ASCII characters (Polish diacritics ł, ż, ś, ź, ę, ą)
When exporting a Genie conversation response to PDF, all Polish diacritical characters are systematically replaced with wrong ASCII characters, making the document unreadable for Polish-speaking users.Character substitution patternExpected Rendered a...
- 347 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @MWojcicki My understanding is that Genie space skills would not solve this issue.The problem you described appears to be a **PDF rendering/export bug**, not something related to Genie instructions, skills, or table definitions.Based on your techn...
- 0 kudos
- 1984 Views
- 6 replies
- 1 kudos
Resolved! Prakash Hinduja Geneva, Switzerland, How do I fine-tune a large language model (LLM) in Databricks?
Hello Databricks Community,I am Prakash Hinduja from Geneva, Switzerland (Swiss), currently exploring fine-tuning large language models (LLMs) in Databricks and would appreciate any guidance or suggestions from those with experience in this area. Reg...
- 1984 Views
- 6 replies
- 1 kudos
- 1 kudos
Hi @jayshan, you're right the material is outdated now. The more current path is Foundation Model Fine-tuning, which is part of Mosaic AI Model Training. You can run it from the Databricks UI or with the databricks_genai SDK, point it at training dat...
- 1 kudos
- 4899 Views
- 2 replies
- 0 kudos
Multi Vector Index
Can we create multi vector indexes on multiple embedding columns in delta table as part of databricks vector search
- 4899 Views
- 2 replies
- 0 kudos
- 0 kudos
Is this still the case? Both the rest api (https://docs.databricks.com/api/workspace/vectorsearchindexes/createindex) and the python sdk (https://databricks-sdk-py.readthedocs.io/en/latest/dbdataclasses/vectorsearch.html#databricks.sdk.service.vector...
- 0 kudos
- 545 Views
- 2 replies
- 0 kudos
Resolved! AI Playground access Tools(SQL Function) with spark connect PERMISSION_DENIED
Hello, Dear community, I have one SQL function defined in Unity Catalog accessing delta table in the unity catalog. It works normally if i use SQL to execute Function. I see the possibility connecting function to Agent/ Chat. For the quick prototype,...
- 545 Views
- 2 replies
- 0 kudos
- 0 kudos
Hello @loujiang, a few questions to understand the issue.Does your workspace have serverless compute enabled?When AI Playground calls your function as a tool, is there an active classic cluster attached ?If you have a classic cluster, is it configur...
- 0 kudos
- 311 Views
- 0 replies
- 2 kudos
Request for Genie Agent Mode API with Streaming & Reasoning Trace Support
Hi everyone,Genie Agent Mode has been incredibly impressive and is one of the best tools we’ve come across, especially in how it handles multi-step reasoning and delivers structured end-to-end insights.We’re currently building a frontend application ...
- 311 Views
- 0 replies
- 2 kudos
- 745 Views
- 1 replies
- 0 kudos
ai-dev-kit -Best practices and Scoped PATs
SpoilerHi,I am experimenting with ai-dev-kit and would like to ask whether there are any best practices, demos, or safety guardrails that were followed when using it. Specifically recommended settings for a limited-access PAT for dev-ai-toolkit.Thank...
- 745 Views
- 1 replies
- 0 kudos
- 0 kudos
@skarangi_349 As this is not a official DB product hence there's no such guide or docs. Best would be to follow the creators - https://www.youtube.com/@DustinVannoyYou may check other videos over youtube as well.
- 0 kudos
- 171 Views
- 0 replies
- 0 kudos
Genie Code prompt context absent, what I think, could be power features
But for all I can know are these limits intentional?Empathy for the Genie (image(1))---This feels a little short sighted. Almost the like, in some ways, a terminal is still more elevated. AI prompt certainly won't be a challenge to HAL9000 anytime so...
- 171 Views
- 0 replies
- 0 kudos
- 9596 Views
- 7 replies
- 6 kudos
OpenAi gpt-oss support for responses API?
I was looking forward to using there openAI responses API when the new gpt-oss models were added to Databricks.The openAI website states these model are compatible with the responses API.However, it does not seem to support it on Databricks. See erro...
- 9596 Views
- 7 replies
- 6 kudos
- 6 kudos
Great discussion here—this highlights a real gap between the Chat Completions API and the newer Responses API. It’s clear the Responses API is the direction forward, especially with better multi-modal and tool-calling capabilities, but the lack of su...
- 6 kudos
