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: 
Data + AI Summit 2024 - Generative AI

Forum Posts

Sujitha
by Community Manager
  • 15035 Views
  • 6 replies
  • 11 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
  • 15035 Views
  • 6 replies
  • 11 kudos
Latest Reply
KhileshKhubnani
New Contributor III
  • 11 kudos

Thanks for sharing 

  • 11 kudos
5 More Replies
tefrati
by New Contributor II
  • 530 Views
  • 5 replies
  • 0 kudos

Is llama 3.0 not supported anymore or is it just a glitch

Hello all,For some reason, I can't find llama-3.0 models on either the playground or serving endpoints even though we've been using it for months.I can see both llama-3.1 models on the serving endpoints page and it also says they have been last modif...

  • 530 Views
  • 5 replies
  • 0 kudos
Latest Reply
Sujitha
Community Manager
  • 0 kudos

@tefrati Thank you for your patience on this one! The pricing remains the same. Our team found version 3.1 to be better than 3 in many aspects, with the added benefit of not requiring any prompt changes. As a result, we have transitioned to 3.1. Our ...

  • 0 kudos
4 More Replies
VELU1122
by New Contributor
  • 285 Views
  • 0 replies
  • 0 kudos

Copying/cloning Vector index table

Regarding copying or cloning vector index tables, it appears that direct copying or cloning is not possible, as Databricks throws the message: "Securable with kind TABLE_ONLINE_VECTOR_INDEX_REPLICA does not support Lakehouse Federation."It seems that...

  • 285 Views
  • 0 replies
  • 0 kudos
sue01
by New Contributor II
  • 266 Views
  • 1 replies
  • 0 kudos

ai_forecast function error

Hello,I am trying to forecast using ai_forecast function and I get this error (https://docs.databricks.com/en/sql/language-manual/functions/ai_forecast.html)I changed my cluster to use current channel yet this is not solved.. any idea why this occurs...

sue01_0-1724431017068.png
  • 266 Views
  • 1 replies
  • 0 kudos
Latest Reply
szymon_dybczak
Contributor
  • 0 kudos

Hi @sue01 ,Make sure that you run it on clusters aligned with below recommendations:"Only available on Pro SQL warehouses running Databricks SQL version 2024.35 and above"

  • 0 kudos
mortenhaga2
by New Contributor III
  • 216 Views
  • 1 replies
  • 0 kudos

Monitoring Genie: Result not available from chat session

Hi!Have anyone experienced that you cant see the result of what Genie produced as an answer in the history of a chat session? How can I enable to view and correct historical answers for any Genie chat? 

Skjermbilde 2024-08-13 121630.jpg
Generative AI
Genie SQL AIBI AI
  • 216 Views
  • 1 replies
  • 0 kudos
Latest Reply
mortenhaga2
New Contributor III
  • 0 kudos

Anyone?

  • 0 kudos
Michael_Galli
by Contributor III
  • 711 Views
  • 7 replies
  • 4 kudos

Resolved! SQL AI functions not working

I am working in the following environment:- New Databricks workspsace with UC enabled- Azure, region west-europe- Cluster: Interactive (DBR 15.4), or SQL Warehouse (Serverless)Running for example:SELECT ai_gen('Generate a concise, cheerful email titl...

  • 711 Views
  • 7 replies
  • 4 kudos
Latest Reply
jessysantos
Esteemed Contributor III
  • 4 kudos

Hello @Michael_Galli Sorry for the delay in my response. Unfortunately, only the two models you mentioned, Meta Llama 3.1 70B Instruct and GTE Large (En), are currently available in the EU Geo. Our team is working to make more models available soon f...

  • 4 kudos
6 More Replies
samueldaly
by New Contributor
  • 192 Views
  • 0 replies
  • 0 kudos

AI/BI Genie - Real world experience?

I have been tasked with creating a NLP interface for management to our internal datalake that has numerous joined tables around customer information. I have tried the hello-world llamaindex, langchain sql/pandas agents with limited success (too many ...

  • 192 Views
  • 0 replies
  • 0 kudos
avadhut22111997
by New Contributor
  • 143 Views
  • 0 replies
  • 0 kudos

Request to share Genie space URL with restricted access

Dear Databricks Team,I hope this email finds you well.I would like to share a specific Genie Space URL with a user, but I want to ensure that the user only has access to view this particular Genie Space ask questions in that space and no other featur...

  • 143 Views
  • 0 replies
  • 0 kudos
MattB
by New Contributor II
  • 13349 Views
  • 9 replies
  • 4 kudos

AI/BI Genie - Call

HiIs there any way to call a Genie space from a notebook and get the response ? Is there any API available?#genie, #databricksgenie, #databricks_genie

  • 13349 Views
  • 9 replies
  • 4 kudos
Latest Reply
Vadiraja
New Contributor II
  • 4 kudos

Hi @Kaniz_Fatma, I too have a similar request. Your initial response was that there are no end points for Genie. However in your latest response, you have mentioned that we can achieve this through custom development. Can you please share sample code...

  • 4 kudos
8 More Replies
Mohanrajv27
by New Contributor
  • 174 Views
  • 0 replies
  • 0 kudos

Cost Analysis for Databricks Compute

I am currently using the Databricks Vector Search on top of my databricks workspace and running the DBRX Model for querying off and retrieve the results out of it.I have noticed something, a category of compute occurred, which I haven't seen earlier....

  • 174 Views
  • 0 replies
  • 0 kudos
cleversuresh
by New Contributor
  • 389 Views
  • 1 replies
  • 1 kudos

Generative Certification notebook error

I am preparing for Generative Certification and facing the below error (LookupError:) when running the notebook in the first module. These were running without any errors in the past.Complete error stack trace:****************************************...

  • 389 Views
  • 1 replies
  • 1 kudos
Latest Reply
Kaniz_Fatma
Community Manager
  • 1 kudos

Hi @cleversuresh, You're encountering a LookupError because the averaged_perceptron_tagger_eng resource is missing. To fix it, run this in a new cell: python import nltk nltk.download('averaged_perceptron_tagger_eng') This will download the necessa...

  • 1 kudos
WynanddB
by New Contributor III
  • 404 Views
  • 3 replies
  • 2 kudos

Enabling vector search

I have a team member doing the GenAI certification but she gets the following errorResponse content b'{"error_code":"BAD_REQUEST","message":"This trial workspace no longer has access to Vector Search. Please upgrade the workspace to continue to use V...

  • 404 Views
  • 3 replies
  • 2 kudos
Latest Reply
szymon_dybczak
Contributor
  • 2 kudos

Hi @WynanddB ,To upgrade your Azure Databricks workspace pricing plan, go to your workspace in the Azure portal then click Upgrade to Premium.For AWS follow below guide:Manage your subscription | Databricks on AWS 

  • 2 kudos
2 More Replies
hammad
by New Contributor
  • 487 Views
  • 1 replies
  • 0 kudos

How can we serve Genie as an endpoint model like RAG?

Is there any way to serve genie bot as a endpoint model like we serve RAG models. So we can access the genie bot outside the genie space?

  • 487 Views
  • 1 replies
  • 0 kudos
Latest Reply
Kaniz_Fatma
Community Manager
  • 0 kudos

Hi @hammad, Genie has its own APIs and cannot be served through Model Serving (creating a Model Serving Endpoint). All Genie queries happen in the context of a Genie Space even when accessed through the API. The Space is how Genie knows what data it ...

  • 0 kudos
yashshingvi
by New Contributor
  • 351 Views
  • 0 replies
  • 0 kudos

Unable to add dependencies to mlflow.langchain.log_model

Hello,I'm doing this-with mlflow.start_run(run_name="run1"): logged_chain_info = mlflow.langchain.log_model( # lc_model=os.path.join(os.getcwd(), 'full_chain'), this doesnt work too lc_model='/Workspace/Users/{user_name}/exp/d...

  • 351 Views
  • 0 replies
  • 0 kudos