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
  • 34423 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
  • 34423 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
the_peterlandis
by New Contributor III
  • 926 Views
  • 2 replies
  • 1 kudos

Resolved! Help with hybrid search function

I need help writing a filter.  I want to pre-filter a vector index before performing a hybrid search and create this as a function.  Below is a simple example of searching for products for a given customer.  A prefilter is key as this provides author...

  • 926 Views
  • 2 replies
  • 1 kudos
Latest Reply
KaushalVachhani
Databricks Employee
  • 1 kudos

@the_peterlandis, Yes, currently vector_search SQL function doesn't provide pre filter support. However, if you must implement the UC function for this, you can do it something like below using Python code with filters.   %sql CREATE OR REPLACE FUNCT...

  • 1 kudos
1 More Replies
Saurabh2406
by Contributor
  • 690 Views
  • 1 replies
  • 3 kudos

Resolved! Multi-agent chatbot Optimization

We have developed a multi-agent chatbot using LangGraph within the Databricks environment. The solution is functional, but we are facing challenges related to performance observability and end-to-end optimization.We need guidance in the following are...

  • 690 Views
  • 1 replies
  • 3 kudos
Latest Reply
stbjelcevic
Databricks Employee
  • 3 kudos

Hi @Saurabh2406 , This sounds like a fairly advanced use case - are you in touch with your account team at Databricks? They would be able to provide you with more detailed guidance on this use case. They could also get you connected with internal spe...

  • 3 kudos
tarunnagar
by Contributor
  • 3827 Views
  • 6 replies
  • 0 kudos

How to Use Databricks Repos for Collaborative Development and CI/CD Integration?

I’d like to gather insights, best practices, and real-world experiences from anyone who has worked with Databricks Repos for team-based development. Databricks Repos is designed to streamline source control, versioning, and automation, but the workfl...

  • 3827 Views
  • 6 replies
  • 0 kudos
Latest Reply
Suheb
Contributor
  • 0 kudos

Databricks Repos make collaborative development easy by connecting notebooks to Git. You can work on branches, track changes, and sync with your team. Plus, they integrate with CI/CD pipelines, allowing automated testing and deployment of notebooks o...

  • 0 kudos
5 More Replies
Nadav
by New Contributor II
  • 2047 Views
  • 3 replies
  • 5 kudos

Resolved! Information Extraction Agent - Update Agent failed

Hi everyone,I’m running into a persistent issue when trying to save an Information Extraction Agent in Databricks.Every time I click Save and update, I get: Update Agent failed. Failed to save AgentThis happens regardless of what I change — schema, g...

  • 2047 Views
  • 3 replies
  • 5 kudos
Latest Reply
tarunnagar
Contributor
  • 5 kudos

It sounds like the update for your Information Extraction Agent didn’t go through successfully. A few things you could try:Check logs – Look for any error messages during the update process; they often give clues about what went wrong.Verify dependen...

  • 5 kudos
2 More Replies
shivamrai162
by New Contributor III
  • 817 Views
  • 2 replies
  • 0 kudos

Resolved! Agent Bricks Multi Agent Supervisor failing update

Hello,I recently created a Multi Agent supervisor yesterday and it is working fine till date but when i created a second Multi Agent Supervisor assistant, im facing below error: Endpoint update failedFailed to deploy : Quota Exceeded: You've hit the ...

shivamrai162_0-1763468341971.png
  • 817 Views
  • 2 replies
  • 0 kudos
Latest Reply
shivamrai162
New Contributor III
  • 0 kudos

Thanks Advika, I have deleted some of the endpoints and its working now. Also wanted to know if instead of deleting the endpoint, can I just pause it or scale it to zero to avoid endpoint cost.

  • 0 kudos
1 More Replies
actualhuman_012
by New Contributor III
  • 2767 Views
  • 3 replies
  • 0 kudos

Resolved! Measuring latency metrics like TTFT, TBT when deploying agents on Databricks

Is there an inbuilt method to measure latency metrics like TTFT, TBT when deploying agents on Databricks? Using MLFlow ChatAgent, ChatDatabricks/OpenAI client(workspace client)What would be the way to measure them in case no inbuilt method exists?

  • 2767 Views
  • 3 replies
  • 0 kudos
Latest Reply
Louis_Frolio
Databricks Employee
  • 0 kudos

@actualhuman_012 ,  You’re close: for production observability you can use server‑side tracing when you deploy agents on Databricks, and client‑side instrumentation when the app runs outside; you don’t have to rely only on the client side. What to us...

  • 0 kudos
2 More Replies
epistoteles
by Databricks Partner
  • 6584 Views
  • 3 replies
  • 1 kudos

Vector search index creation is incredibly slow

I am trying to create a vector search index for a Delta Table using Azure OpenAI embeddings (text-embedding-3-large). The table contains 5000 chunks with approx. 1000 tokens each. The OpenAI embeddings are generated through a Databricks model serving...

  • 6584 Views
  • 3 replies
  • 1 kudos
Latest Reply
amitkumarvish
Databricks Partner
  • 1 kudos

@epistoteles I am also facing the same issue while delta table sync with Index. Could you please share if you have any work around or used some different appoarch to decrease latency.Thanks in advance.

  • 1 kudos
2 More Replies
Mario_D
by New Contributor III
  • 1237 Views
  • 4 replies
  • 1 kudos

Resolved! Agentic AI Workload Analyzer

Hello Databricks experts,In Automating Best Practices with Agentic AI Workload Analyzer, Krishna Satyavarapu and Nikhil Mishra mentioned  "The Agentic AI Workload Analyzer". Is it known when this will be available.cheersMario  

  • 1237 Views
  • 4 replies
  • 1 kudos
Latest Reply
Thompson2345
New Contributor III
  • 1 kudos

Generative AI is transforming how we handle data and automation. The key challenge now is balancing model creativity with control — ensuring reliable outputs while keeping innovation at the core.

  • 1 kudos
3 More Replies
tsukitsune
by Databricks Partner
  • 2441 Views
  • 8 replies
  • 4 kudos

Resolved! Agent Bricks - MAS 500 Internal error

Hi Databricks Team / Community,I’m encountering a 500 Internal Server Error when calling an Agent Bricks MAS endpoint in my workspace. The error message is:500 Internal Error. Please try again later. If this issue persists, please contact Databricks ...

  • 2441 Views
  • 8 replies
  • 4 kudos
Latest Reply
shivamrai162
New Contributor III
  • 4 kudos

Hello, i'm facing the same issue while testing sample queries in the "Test your Agent" box. Could anyone plese help me with the process of enabling OBO authorization

  • 4 kudos
7 More Replies
Prashant_151
by Databricks Partner
  • 2104 Views
  • 2 replies
  • 2 kudos

Resolved! Agent Bricks Cost and Billing

This is regarding agent bricks and want to understand DBU consumed while creating a knowledge assistant agent. Can anyone please share any video or documentation which will help me in this regard..Let's say I take a pdf on which we want Knowledge ass...

  • 2104 Views
  • 2 replies
  • 2 kudos
Latest Reply
Raman_Unifeye
Honored Contributor III
  • 2 kudos

As it is fairly new product and yet to be made availalbe in various region even in Public preview, we are running a webinar with Databricks SA. Below is the link to our earlier post. Pls feel free to join this and hear it directly from Databricks SA ...

  • 2 kudos
1 More Replies
kcailabs
by New Contributor
  • 974 Views
  • 1 replies
  • 1 kudos

Resolved! Running Into Erroneous "Databricks Connected" Messages with Claude Desktop

When I try to connect Databricks via the connector that is now available within Claude Desktop to a genie space I have available (which is just the default test one), Databricks appears to say that it connects successfully, but it never actually work...

kcailabs_1-1763354494688.png kcailabs_0-1763354486166.png
  • 974 Views
  • 1 replies
  • 1 kudos
Latest Reply
Louis_Frolio
Databricks Employee
  • 1 kudos

Greetings @kcailabs , Thanks for sharing the screenshots—this helps. From what I can see, Claude shows a “Successfully connected to Databricks” toast while the Databricks connector still displays “Disconnected,” and the Server URL entered is just a p...

  • 1 kudos
DinoSaluzzi
by New Contributor III
  • 7181 Views
  • 4 replies
  • 3 kudos

How to implement prompt caching using Claude models?

Hi, I am trying to use prompt caching future using claude "databricks-claude-sonnet-4" databricks endpoint (wrapped in a ChatDatabricks instance). Using langchain, I set  SystemMessage( content=[ { ...

Generative AI
ChatDatabricks
Prompt caching
  • 7181 Views
  • 4 replies
  • 3 kudos
Latest Reply
Pradeep54
Databricks Employee
  • 3 kudos

@DinoSaluzzi If you can restructure your system& user prompt in a similar manner to the examples provided, prompt caching should start working as expected. messages = [ { "role": "system", "content": [ { ...

  • 3 kudos
3 More Replies
SandipCoder
by New Contributor II
  • 927 Views
  • 1 replies
  • 1 kudos

Getting error while trying to use external MCP

I have created a mcp connection from marketplace :Conn Name : mcp_brightdata_web_surfermcp product url : https://brightdata.com/I have attached the mcp through playground . But while submitting the prompt I am getting the following error .Error : The...

  • 927 Views
  • 1 replies
  • 1 kudos
Latest Reply
RahulPathakDBX
Databricks Employee
  • 1 kudos

Based on the error,  which is a "502 Bad Gateway" error indicates that a server sitting as a gateway or proxy received an invalid response from an upstream server. Here, Databricks is trying to communicate with the external MCP server associated with...

  • 1 kudos
Abhishek_Patel
by Databricks Partner
  • 3681 Views
  • 13 replies
  • 6 kudos

Resolved! AgentBricks - Multi Agent Supervisor Issue

Hi, I am doing POC using AgentBricks and using Multi Agent Supervisor. I have configured 2 subagents.1. Genie Space2. UC Function to call LLM3. UC Function to plot chartsHowever, the agent is able to access and use only Genie space agent and not usin...

  • 3681 Views
  • 13 replies
  • 6 kudos
Latest Reply
Krishna_S
Databricks Employee
  • 6 kudos

Also, as you can see on the top right of the attached image, it creates an MLFlow experiment.   Click on that MLflow experiment, and check the traces and let me know what it shows, as you can see here it shows the tool is being called in the trace. ...

  • 6 kudos
12 More Replies
Louis_Frolio
by Databricks Employee
  • 1411 Views
  • 1 replies
  • 4 kudos

Why Agent Bricks Is a Game Changer

Check out Agent Bricks — Databricks’ new framework for building AI agents without writing a single line of code. Picture this: you describe your business challenge in plain English, point it at your data, and boom… a domain-specific agent comes to li...

  • 1411 Views
  • 1 replies
  • 4 kudos
Latest Reply
Brahmareddy
Esteemed Contributor
  • 4 kudos

Absolutely love the direction Databricks is heading with Agent Bricks — this is true innovation. Taking something as complex as building AI agents and turning it into a no-code, domain-aware, business-ready framework is a huge leap forward for teams ...

  • 4 kudos