- 39313 Views
- 22 replies
- 48 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 ...
- 39313 Views
- 22 replies
- 48 kudos
- 48 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...
- 48 kudos
- 2193 Views
- 2 replies
- 2 kudos
Resolved! How to use CrewAI with Databricks-hosted LLMs (not OpenAI) ?
I am trying to use CrewAI to train an agent with a Databricks-hosted LLM (such as Llama 2 instruct or DBRX) via the databricks_langchain integration. I want CrewAI to use only my Databricks LLM and not requiring OpenAI authentication.However, when I ...
- 2193 Views
- 2 replies
- 2 kudos
- 2 kudos
@lucami To configure CrewAI to use only Databricks-hosted models without OpenAI dependencies Use CrewAI's LLM class (which wraps litellm) rather than ChatDatabricks Pass the LLM at both levels: agents use it to complete their tasks, and the crew u...
- 2 kudos
- 1187 Views
- 1 replies
- 3 kudos
Resolved! What functions privileges are required to create/see Unity Catalog Function MCPs?
When you go AI/ML -> Agents - MCP Servers you can see the schema names with a server type UC Function for seemingly all schemas that contain Unity Catalog functions that you have created. However, when my colleague creates a function in a different s...
- 1187 Views
- 1 replies
- 3 kudos
- 3 kudos
Now I see. My colleague didn't create a function, but a procedure. It is listed as a function in the MCP Servers view, but it is different in that it is a sequence of statements.
- 3 kudos
- 1893 Views
- 3 replies
- 2 kudos
Resolved! Clouds in Databricks
I'm trying to understand the differences between the clouds that offer Databricks, and I'm interested in GCP. However, I'm unsure if choosing GCP would allow me to use AI functionalities like Agent Bricks. Regardless of the cloud I choose, will I hav...
- 1893 Views
- 3 replies
- 2 kudos
- 2 kudos
In my experience, Azure Databricks leads in rolling out new features, and GCP is generally the last.
- 2 kudos
- 417 Views
- 0 replies
- 0 kudos
Where Data + Gen AI Adds Value in Modern Data Platforms
Data + Gen AI is most effective when grounded in real data constraints.On Databricks, combining Gen AI with Spark and Delta accelerates prototyping and testing, but fundamentals still matter—schema design, realistic distributions, and domain understa...
- 417 Views
- 0 replies
- 0 kudos
- 5862 Views
- 5 replies
- 2 kudos
Resolved! Documentation on all ways to access agent serving endpoint from outside databricks
Struggling to find clear documentation which can help me with the subject. Need to know all the ways (production best practices) along with API method. As far as I know, using PAT is not a production best practice
- 5862 Views
- 5 replies
- 2 kudos
- 2 kudos
To access an Agent serving endpoint without a Personal Access Token (PAT), you must use OAuth 2.0 Machine-to-Machine (M2M) authentication. This is the industry-standard approach for production applications.1. OAuth M2M Authentication WorkflowInstead ...
- 2 kudos
- 892 Views
- 1 replies
- 0 kudos
- 892 Views
- 1 replies
- 0 kudos
- 0 kudos
For every endpoint there will be an inference table that can be configured to store the logs . https://docs.databricks.com/aws/en/ai-gateway/inference-tables#enable-and-disable-inference-tablesYou can then query and analyze this table - https://docs....
- 0 kudos
- 1679 Views
- 2 replies
- 0 kudos
Resolved! Agents button is missing
Dear Community,Recently I've followed the AI Agents on Databricks training and wanted to dive into AI world using my company Databricks account.After logging in to the workspace I was quite surprised to see that the Agents button in AI/ML menu is mis...
- 1679 Views
- 2 replies
- 0 kudos
- 0 kudos
Hi @kuznetsovvs , I checked this internally and on Azure, the Mosaic AI Agent Framework and Model Serving are supported in West Europe, the Agent Bricks UI itself is limited to specific regions (primarily in US). That's why the “Agents” button doesn’...
- 0 kudos
- 2119 Views
- 3 replies
- 1 kudos
Resolved! multi agent Genie AI app in serving endpoint fails with PERMISSION ERROR on Databricks tabls.
I have deployed simple multi agent genie app on serving endpoint and it always fails PERMISSION error on tables accessed by Genie agent, however the same app works perfectly when tested from notebook. not sure what am i missing here. I checked all th...
- 2119 Views
- 3 replies
- 1 kudos
- 1 kudos
hi @davidmorton thanks for responding, I am only using databricks_token for my authentication when tested via notebook. Can you help what changes needs to be done as per below notebook to enable access to tables when model deployed in serving endpoin...
- 1 kudos
- 1094 Views
- 1 replies
- 2 kudos
Resolved! How to create an information extraction agent (Trial Version)
I haven't been using Databricks for very long and I'm testing how things work. I tried to create a pre-built agent to extract information from one of my tables, but I get an error when I click create: "Permission denied: provisioned throughput is not...
- 1094 Views
- 1 replies
- 2 kudos
- 2 kudos
Hi @Artur1 If you are using Agent Bricks to create the agent, this feature is not supported in the Databricks free edition.Please refer here Databricks Free Edition limitations
- 2 kudos
- 3820 Views
- 7 replies
- 1 kudos
Azure Content Understanding Equivalent
Hi all,I am exploring Databricks services or components that could be considered equivalent to Azure Document Intelligence and Azure Content Understanding.Our customer works with dozens of Excel and PDF files. These files follow multiple template typ...
- 3820 Views
- 7 replies
- 1 kudos
- 1 kudos
I would work, but you will need to specify and manage the ranges or number of header rows manually. You could potentially read the whole sheet in and then write some code that identifies the range that is of interest and cleans it in parsing. My reco...
- 1 kudos
- 2895 Views
- 1 replies
- 1 kudos
Databricks Vector Search Algorithm
I’m working on using Databricks vector search combined with full-text search in my application. I want to filter queries by the id field in my vector search index. I noticed that there is a limit of 1,024 IDs per query when using filters.If I need to...
- 2895 Views
- 1 replies
- 1 kudos
- 1 kudos
Hi @deane , I worked on a similar issue months earlier and the limit of 1024 is not configurable (no explicit way to increase the filter count), so my suggestion back then was to perform a two step process like filter for half of the filters once and...
- 1 kudos
- 3393 Views
- 1 replies
- 1 kudos
Resolved! Local LLM's available in Databricks for email classification
Hello everyone,I am currently working on an email classification model in Azure Databricks. Since I work for an international company, the emails contain PII data. Because of this, I need to be very careful about compliance and data privacy, especial...
- 3393 Views
- 1 replies
- 1 kudos
- 1 kudos
Hi, It is absolutely acceptable. Here are some details that you may want to consider. I'd also think about GPU availability in your cloud and region and whether there is GPU available for you to deploy these models to. You should be able to easily te...
- 1 kudos
- 3270 Views
- 4 replies
- 3 kudos
Resolved! Accessing Knowledge Base from Databricks One
Is it possible to use Knowledge Assistant from Databricks one ?
- 3270 Views
- 4 replies
- 3 kudos
- 3 kudos
@piotrsofts , if you are happy please accept as a solution so others can be confident in the approach. Cheers, Louis.
- 3 kudos
- 1073 Views
- 2 replies
- 1 kudos
Resolved! Not able to add scorer to multi agent supervisor
Hello,When I try to add scorers to Multi agent endpoint based on the last 10 traces that I have logged and visible in the experiments tab, i get this error.Also, are there any demos which i can refer regarding the tabs within the evaluation bar expla...
- 1073 Views
- 2 replies
- 1 kudos
- 1 kudos
Hi @shivamrai162 , Did you add the last 10 traces to the evaluation dataset? You can follow the steps here to make sure you added the traces to the evaluation dataset. To answer your second question, here is a good article that covers the concepts an...
- 1 kudos
- 2117 Views
- 1 replies
- 1 kudos
Resolved! Claude Code-Execution Call Format
Is it possible to use the code execution tool with instances of Claude hosted through Databricks? If I try to format the payload like in Anthropic's documentation, I get an error that the function isn't defined properly: tools=[{ "type": ...
- 2117 Views
- 1 replies
- 1 kudos
- 1 kudos
Greeting @jmartin1 , The Anthropic “code execution” tool isn’t supported through Databricks’ Foundation Model APIs. Databricks exposes an OpenAI-compatible tools interface, and the only supported tool type today is a function defined with a JSON sch...
- 1 kudos
