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
  • 30546 Views
  • 18 replies
  • 33 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
  • 30546 Views
  • 18 replies
  • 33 kudos
Latest Reply
AIChief
New Contributor II
  • 33 kudos

thanks for sharing

  • 33 kudos
17 More Replies
GiriSreerangam
by New Contributor III
  • 11 Views
  • 0 replies
  • 0 kudos

ai_parse_document + Genie with ai_query

Hi EveryoneI have used ai_parse_document to process multiple PDFs and store the parsed data in a table (one PDF per row). Later, I ran ai_query in natural language, which correctly scans all rows and returns answers from each PDF.However, when I use ...

  • 11 Views
  • 0 replies
  • 0 kudos
andcch552
by Visitor
  • 21 Views
  • 1 replies
  • 0 kudos

Slow Delta write when creating embeddings with mapPartitions

I’m trying to generate 35k+ embeddings in Databricks. What I’ve tried so far:Per-row UDF (very slow).Replaced UDF with rdd.mapPartitions to batch API calls, create one Azure client per partition, and call client.embed_documents(texts) in batches. Thi...

  • 21 Views
  • 1 replies
  • 0 kudos
Latest Reply
bianca_unifeye
New Contributor III
  • 0 kudos

HiYou’ve optimised the embedding side really nicely already, batching in mapPartitions and creating one Azure client per partition is exactly what we recommend.For 35k rows, if embedding is fast but the Delta write/commit is slow, it’s almost always ...

  • 0 kudos
JN_Bristol
by Contributor
  • 1777 Views
  • 5 replies
  • 1 kudos

ai_parse_document struggling to detect pdf

Hi helpful experts I'm writing my first PySpark Notebook that makes use of the new `ai_parse_document` function.  I am basically following the code example from here: https://learn.microsoft.com/en-gb/azure/databricks/sql/language-manual/functions/ai...

  • 1777 Views
  • 5 replies
  • 1 kudos
Latest Reply
lucaperes
New Contributor II
  • 1 kudos

Hello @JN_Bristol,I discovered that ai_parse_document only works when the input is parsed as real Python bytes.The binaryFile format in Spark returns the content as an internal binary type (like a memoryview), and ai_parse_document can’t process that...

  • 1 kudos
4 More Replies
rajcoder
by New Contributor
  • 126 Views
  • 3 replies
  • 3 kudos

Issue with ai_parse_document Not Extracting Text from Images in PDF

Hello Team,I hope you are doing well.I am a student currently exploring Databricks and learning how to work with the "ai parse document" function. While experimenting, I encountered a couple of issues related to text extraction from images inside PDF...

  • 126 Views
  • 3 replies
  • 3 kudos
Latest Reply
rajcoder
New Contributor
  • 3 kudos

Thank you for your reply!Yes, I have gone through your article — it explains very well how to extract text content from PDFs. However, I am facing a different issue.In my case, the PDF contains multiple images and paragraphs, but "ai_parse_document" ...

  • 3 kudos
2 More Replies
Suheb
by New Contributor III
  • 32 Views
  • 1 replies
  • 0 kudos

What is the difference between full fine-tuning, LoRA, and p-tuning on Databricks?

How are these three methods different?Full Fine-TuningLoRAP-Tuning

  • 32 Views
  • 1 replies
  • 0 kudos
Latest Reply
saurabh18cs
Honored Contributor II
  • 0 kudos

Hi @Suheb Summary Table:Method What’s Tuned Speed/Cost Flexibility Use CaseFull Fine-TuningAll model weightsSlow/HighMaximumCustom tasks, large dataLoRASmall adapter layersFast/LowHighEfficient adaptationp-tuningPrompt embeddingsFastest/LowLimitedPro...

  • 0 kudos
Hemanthr
by New Contributor
  • 51 Views
  • 1 replies
  • 0 kudos

Genie - Value dictionary

When I add the tables to the genie space, it automatically turns on the value dictionary for first 120 string fields, Is there a way to disable them by default and add only to the needed fields later?I am working in curating responses for around 15 t...

  • 51 Views
  • 1 replies
  • 0 kudos
Latest Reply
Hubert-Dudek
Esteemed Contributor III
  • 0 kudos

"Value sampling is enabled by default for all Genie spaces." The only solution that I see is to build json and use as a serialized_space template https://docs.databricks.com/api/azure/workspace/genie/getspace

  • 0 kudos
Suheb
by New Contributor III
  • 57 Views
  • 1 replies
  • 1 kudos

How do I build a robust multi-agent system (e.g. using Agent Bricks / Genie) on Databricks, while en

How can I set up several AI agents on Databricks that work together at the same time, and make sure they don’t mess up the data or break the system?

  • 57 Views
  • 1 replies
  • 1 kudos
Latest Reply
KaushalVachhani
Databricks Employee
  • 1 kudos

@Suheb, Depends on your usecase. However, if it fits, I would recommend that you start with a multi-agent supervisor if you have the agents from the list below An existing Agent Bricks: Knowledge Assistant(/generative-ai/agent-bricks/knowledge-assist...

  • 1 kudos
snarayan
by New Contributor II
  • 158 Views
  • 3 replies
  • 4 kudos

Multi‑Agent Supervisor: url_citation (source links) not shown in Playground — why and how to enable?

I’m seeing a difference in citation behavior between a single Knowledge Assistant (KA) agent and the Multi‑Agent Supervisor setup.What I testedIn Agent Bricks → Knowledge Assistant, I created an agent that returns citations with links (e.g., url_cita...

  • 158 Views
  • 3 replies
  • 4 kudos
Latest Reply
Hubert-Dudek
Esteemed Contributor III
  • 4 kudos

@snarayan great feedback what should be improved!

  • 4 kudos
2 More Replies
snarayan
by New Contributor II
  • 106 Views
  • 2 replies
  • 1 kudos

How to Increase HTTP Request Timeout for Databricks App Beyond 120 Seconds?

I’ve built a Databricks App using Gradio that leverages predict_stream to get streaming responses from a multi-agent supervisor. The app coordinates reasoning across four knowledge agents, so the model uses a long chain-of-thought process before retu...

  • 106 Views
  • 2 replies
  • 1 kudos
Latest Reply
szymon_dybczak
Esteemed Contributor III
  • 1 kudos

Hi @snarayan ,I think you might be hitting timeout from model serving endpoint:Debug model serving timeouts - Azure Databricks | Microsoft LearnYou can try to increase timeout using environment variables using the Serving UI or programmatically using...

  • 1 kudos
1 More Replies
maikel
by New Contributor III
  • 242 Views
  • 9 replies
  • 2 kudos

Resolved! Custom MCP deployment

Hi Community!I have a question - could somebody please guide me how to deploy my custom MCP server to databricks?What I would like to achieve is the following:I have a unity catalog in databricks for which I would like to have MCPif the data in unity...

  • 242 Views
  • 9 replies
  • 2 kudos
Latest Reply
maikel
New Contributor III
  • 2 kudos

@Hubert-Dudek ! Okay, I did not know about it! Unfortunately in my databricks workspace a can see Agent Bricks as Coming Soon  

  • 2 kudos
8 More Replies
Shivani_Pande
by New Contributor II
  • 183 Views
  • 3 replies
  • 3 kudos

Resolved! Serving model issue in databricks

I’m facing an issue while trying to deploy a custom pyfunc model for Qwen3-Embedding-8B (GGUF format) registered in Unity Catalog. The GGUF model file is stored inside a Unity Catalog Volume, and during model training and registration everything work...

  • 183 Views
  • 3 replies
  • 3 kudos
Latest Reply
Shivani_Pande
New Contributor II
  • 3 kudos

Thank you so much. That solved my problem

  • 3 kudos
2 More Replies
Prashanthkumar
by New Contributor III
  • 1433 Views
  • 5 replies
  • 2 kudos

Resolved! Databricks Genie new space creation using API

I am exploring an option to see if Databricks Genie can be created using API or using python script?

  • 1433 Views
  • 5 replies
  • 2 kudos
Latest Reply
mcassis15
Databricks Employee
  • 2 kudos

A recent update introduced the ability to create, update, and delete genie spaces. By stringing these together into your CI/CD pipeline, you should be able to accomplish everything you need. It is not in the SDK or DABs quite yet, but keep an eye out...

  • 2 kudos
4 More Replies
shivamrai162
by New Contributor III
  • 111 Views
  • 1 replies
  • 0 kudos

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...

shivamrai162_0-1763609354150.png shivamrai162_2-1763609468060.png
  • 111 Views
  • 1 replies
  • 0 kudos
Latest Reply
stbjelcevic
Databricks Employee
  • 0 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...

  • 0 kudos
Suheb
by New Contributor III
  • 88 Views
  • 3 replies
  • 1 kudos

What is the core goal of your project or what problem are you trying to solve with generative AI or

What problem are you trying to solve using Databricks and generative AI?

  • 88 Views
  • 3 replies
  • 1 kudos
Latest Reply
iyashk-DB
Databricks Employee
  • 1 kudos

Below are high-impact problems you can solve with Databricks and generative AI, grounded in your enterprise data and governed end to end. Customer and employee knowledge accessBuild RAG-powered knowledge assistants that answer questions over your pr...

  • 1 kudos
2 More Replies
shivamrai162
by New Contributor III
  • 201 Views
  • 3 replies
  • 2 kudos

Resolved! Multi Agent Supervisor not able to coordinate with genie when deployed as a databricks app

Hello,I've provided necessary permissions to a chatbot that i created using DAB and deployed on databricks apps following this documentation. At the backend its using below agentsMulti Agent SupervisorKnowledge AssistantAI/BI GenieI've provided can_q...

shivamrai162_0-1764239231427.png
  • 201 Views
  • 3 replies
  • 2 kudos
Latest Reply
shivamrai162
New Contributor III
  • 2 kudos

Hello Bianca,After following what you told, i found issues at two levelsOne was the missing genie-space configuration within databricks.ymlOther was with granting permissions to the service principal (app identity) access to the underlying tables.tha...

  • 2 kudos
2 More Replies

Join Us as a Local Community Builder!

Passionate about hosting events and connecting people? Help us grow a vibrant local community—sign up today to get started!

Sign Up Now