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
  • 34560 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 ...

Screenshot 2024-01-24 at 11.32.01 PM.png
  • 34560 Views
  • 22 replies
  • 46 kudos
Latest Reply
Darshan137
New Contributor II
  • 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
21 More Replies
vashistaT
by New Contributor II
  • 1468 Views
  • 2 replies
  • 3 kudos

mlflow Dependency Error with pydantic

Getting the following error while running the default base template for "Create Agent Notebook" under playground. /mlflow/types/agent.py", line 57, in check_content_and_tool_calls content = values.content AttributeError: 'pydantic_core._pydantic_core...

  • 1468 Views
  • 2 replies
  • 3 kudos
Latest Reply
DinoSaluzzi
New Contributor III
  • 3 kudos

Hi!, had the same problem. Mlflow 3.2 just came out today and solve this issue. 

  • 3 kudos
1 More Replies
king728
by New Contributor
  • 1844 Views
  • 1 replies
  • 0 kudos

Resolved! Claude 4 models are unusable

Litterally can't get a response from either model without getting TEMPORARILY_UNAVAILABLE error. Is there quota for these models can't find it anywhere in the docs. 

  • 1844 Views
  • 1 replies
  • 0 kudos
Latest Reply
Vinay_M_R
Databricks Employee
  • 0 kudos

Hello @king728 , Claude 4 models are currently encountering issues related to availability, specifically resulting in the TEMPORARILY_UNAVAILABLE error. This situation appears from capacity constraints and throttling rather than an explicit quota lim...

  • 0 kudos
raresaxpo
by New Contributor
  • 1489 Views
  • 1 replies
  • 0 kudos

Displaying plots in custom AI Agents

I am trying to build an agent that uses custom functions running python code. However, I can't find a way to make the agent display plots or images. How can I tackle this?

  • 1489 Views
  • 1 replies
  • 0 kudos
Latest Reply
Khaja_Zaffer
Esteemed Contributor
  • 0 kudos

Hello @raresaxpo Good day!The content was asked from GPT to make a structured response but the whole process is not from GPT. Step-by-Step Guide: Building an AI Data Visualization AgentThis guide provides a detailed walkthrough to help you build a fu...

  • 0 kudos
Vini_Coin
by New Contributor
  • 1753 Views
  • 2 replies
  • 0 kudos

Sentiment analysis using GEN AI

Has someone started a sentiment analysis in customer surveys using gen AI? How was the experience?

  • 1753 Views
  • 2 replies
  • 0 kudos
Latest Reply
nayan_wylde
Esteemed Contributor II
  • 0 kudos

@Vini_Coin I recently did a sentiment analysis on a table and used the AI function ai_analyze_sentiment in databricks it was very simple without needing to write a model or long code. here is the doc if you want to refer.https://learn.microsoft.com/e...

  • 0 kudos
1 More Replies
Tee_O
by New Contributor II
  • 2105 Views
  • 1 replies
  • 1 kudos

Chatbot Deployment Error on Databricks

Hi All,I am trying to deploy a chatbot on databricks and I get this error in the build log:Build could not start due to an internal error. If you are serving a model from UC and Azure storage firewall or Private Link is configured on your storage acc...

  • 2105 Views
  • 1 replies
  • 1 kudos
Latest Reply
Vidhi_Khaitan
Databricks Employee
  • 1 kudos

Hi team,The underlying cause of this issue is an incorrect Network Connectivity Configuration (NCC) for Azure Storage in the Databricks environment. The NCC determines which resources are accessible from within the Databricks environment. If the NCC ...

  • 1 kudos
darioschiraldi9
by New Contributor II
  • 671 Views
  • 0 replies
  • 1 kudos

Newbie Dario Schiraldi, CEO of Travel Works

Hello Community, Hi, I’m Dario Schiraldi, CEO of Travel Works. I’m excited to join the Databricks community to connect with innovators who are shaping the future of data and AI. I’m here to learn, contribute, and collaborate around scalable data solu...

  • 671 Views
  • 0 replies
  • 1 kudos
fcardoze
by New Contributor III
  • 4734 Views
  • 4 replies
  • 1 kudos

Pydantic usage for structured output with provisioned LLM

Hi,I am looking for a resource that has examples of using Pydantic with a provisioned LLM on Databricks to get structured output.I can find many examples of using Pydantic with LLMs, but not on the Databricks.My use case is to extract text from image...

  • 4734 Views
  • 4 replies
  • 1 kudos
Latest Reply
fcardoze
New Contributor III
  • 1 kudos

Thank you!

  • 1 kudos
3 More Replies
vishxlrxghxv
by New Contributor III
  • 3652 Views
  • 4 replies
  • 1 kudos

Resolved! Problem with Review App

I’m trying to deploy a Databricks Review App, but I’m running into the following error.Interestingly, the same code works fine when executed from a Databricks Notebook.Does anyone know what might be going wrong here? Could this be a bug with the Revi...

  • 3652 Views
  • 4 replies
  • 1 kudos
Latest Reply
Amruth_Ashok
Databricks Employee
  • 1 kudos

I recently wrote a KB article on this. Let me know if this helps!TLDR: Databricks Apps are lightweight, container-based runtimes designed for UI rendering and light orchestration. They do not ship with an Apache Spark driver, executor, or JVM. Any ca...

  • 1 kudos
3 More Replies
prakashhinduja
by New Contributor III
  • 3936 Views
  • 5 replies
  • 4 kudos

Prakash Hinduja Switzerland (Swiss) How do I build a RAG pipeline on Databricks?

Hello DataBricks Community,I'm Prakash Hinduja from Geneva, Switzerland (Swiss). As a financial strategist, I play an active role in strengthening the Swiss investment market. By connecting global investors with high-potential opportunities across Sw...

  • 3936 Views
  • 5 replies
  • 4 kudos
Latest Reply
simonsmart
New Contributor II
  • 4 kudos

@Khaja_Zaffer It's actually a weird type of spam - see simon-smart88/Hinduja_spam on GitHub. I've reported this post.

  • 4 kudos
4 More Replies
SandipCoder
by New Contributor II
  • 4675 Views
  • 1 replies
  • 0 kudos

How can we deploy a custom model

Goal:Let's say we have a custom function with arbitrary python code . And we want to deploy that as model as we wanted to generate an API endpoint .So that that can be accessed from external applications.I am attaching the below code I have tried .If...

Generative AI
GenAI
modelcreation
  • 4675 Views
  • 1 replies
  • 0 kudos
Latest Reply
Vidhi_Khaitan
Databricks Employee
  • 0 kudos

Hi @SandipCoder I believe that you are not seeing an output because you're calling the MLflow model via a REST API endpoint. MLflow’s REST API expects the inputs to be a DataFrame-like structure, not just a single string.Instead of passing this - {"i...

  • 0 kudos
yvesbeutler
by New Contributor III
  • 2640 Views
  • 2 replies
  • 3 kudos

Resolved! Can Genie ask clarifying questions?

I am looking for a way to force Genie to ask questions when an instruction is not entirely clear. Are there specific options or instructions that I could use for this, or is it managed internally by Databricks and we cannot adjust it?I would like Gen...

  • 2640 Views
  • 2 replies
  • 3 kudos
Latest Reply
Sharanya13
Contributor III
  • 3 kudos

Thanks @Vinay_M_R for the detailed explanation. It's good to know that Genie can ask clarifying questions.

  • 3 kudos
1 More Replies
dbx_beginner_10
by New Contributor II
  • 1943 Views
  • 2 replies
  • 1 kudos

Vector Search Indexes on dlt pipelines / materialized views

Hello, I am not seeing the "create vector search index" option on my materialized views I created from Databricks Asset Bundles using dlt. Is this expected behavior?

  • 1943 Views
  • 2 replies
  • 1 kudos
Latest Reply
dbx_beginner_10
New Contributor II
  • 1 kudos

Yes, that failed because I didn't have change data capture on, which I learned materialized views don't support.I really like the dev/prod Databricks Asset Bundles, but I'm not sure the forcing of materialized views is compatible with a lot of work I...

  • 1 kudos
1 More Replies
ChrisChan
by New Contributor III
  • 8551 Views
  • 6 replies
  • 6 kudos

Resolved! Databricks AI Genie - Data Security and Thrid Party Platform

I am currently exploring the possibility of using Databricks AI Genie to allow layman users to ask questions and retrieve data on their own.We would like to keep the data in our warehouse (e.g., Snowflake or local). I read the documentation, but it s...

  • 8551 Views
  • 6 replies
  • 6 kudos
Latest Reply
k1chi
New Contributor II
  • 6 kudos

Genie allows you to use serverless as well as classic compute (sql warehouse). Classic compute runs within your tenant using your vpc/vnet. Irrespective of the type of compute you use, data needs to be read into it and this applies to any other solut...

  • 6 kudos
5 More Replies
llIIlI1ll1II
by New Contributor III
  • 2461 Views
  • 2 replies
  • 2 kudos

Is it possible to run Databricks Genie entirely within a private network ?

We're considering using Databricks Genie in a secure environment. Is there a way to run Genie fully on an internal network without requiring outbound internet access?

  • 2461 Views
  • 2 replies
  • 2 kudos
Latest Reply
llIIlI1ll1II
New Contributor III
  • 2 kudos

Thank you @charlie_wei We're actually using AWS.Is it not possible to establish a private connection on AWS?(Certain financial institutions in specific countries are not allowed to communicate with external LLMs over the internet.)

  • 2 kudos
1 More Replies