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

javieryw
by New Contributor
  • 298 Views
  • 1 replies
  • 0 kudos

Error Calling Llama Guard Model from Databricks Marketplace after deploying the model

I am facing issues calling the Llama Guard Model after deploying it to Model Serving on Databricks.  I deployed the model by requesting instant access from Databricks Marketplace and deployed it to Model Serving.I am following the code examples here:...

  • 298 Views
  • 1 replies
  • 0 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 0 kudos

@javieryw, The error you are encountering, "400 Client Error: Bad Request for url:  https://westus.azuredatabricks.net/serving-endpoints/llama-guard/invocations. Response text: Bad request: json: unknown field 'dataframe_split'", indicates that the p...

  • 0 kudos
felipe_silva
by New Contributor II
  • 8189 Views
  • 4 replies
  • 1 kudos

Genie Space Embedded or access using a REST API

Hi all.I would like to embed Genie Space in my company's data intranet to be used like a "ChatGPT", would it be possible?Or use an API to make a call from Genie Space (in this case we would develop an interface on the intranet and send the questions ...

  • 8189 Views
  • 4 replies
  • 1 kudos
Latest Reply
Atharv_1604
New Contributor III
  • 1 kudos

@felipe_silva Have you got api for the same 

  • 1 kudos
3 More Replies
narenderkumar57
by New Contributor
  • 323 Views
  • 0 replies
  • 0 kudos

How to perform combined search on structured and unstructured data in databrick using RAG or other

I created a RAG application in databricks which performs the following steps:1. Extract text from PDF files2. Prepare embeddings on extracted text and create vector search index3. Create a LLM model and served the model which can answer question base...

  • 323 Views
  • 0 replies
  • 0 kudos
Sujitha
by Databricks Employee
  • 1008 Views
  • 1 replies
  • 2 kudos

Insights from a global survey of 1,100 technologists and interviews with 28 CIOs

How to unlock enterprise AI: “You can have all the AI in the world, but if it’s on a shaky data foundation, then it’s not going to bring you any value.” — Carol Clements, Chief Digital and Technology Officer, JetBlue Companies everywhere have been qu...

Screenshot 2024-11-15 at 3.52.14 AM.png
  • 1008 Views
  • 1 replies
  • 2 kudos
Latest Reply
Ajay-Pandey
Esteemed Contributor III
  • 2 kudos

Must read

  • 2 kudos
koantek_user
by New Contributor
  • 916 Views
  • 1 replies
  • 0 kudos

What model is powering the AI/BI Genie in Databricks

Hello,We are conducting feasibility study of securely opening up the new features to our team members and want to use AI/BI Genie  - Genie Spaces1. How does it leverage the AI underneath .. what AI service is used , is the data shared with AI service...

  • 916 Views
  • 1 replies
  • 0 kudos
Latest Reply
jamesl
Databricks Employee
  • 0 kudos

Hi @koantek_user, In case you haven't already found answers in documentation, AI/BI Genie uses Azure OpenAI -- your data is not used for training and model partners do not retain your data. (see trust and safety) Your data is governed and secured by ...

  • 0 kudos
dinusr
by New Contributor
  • 522 Views
  • 1 replies
  • 0 kudos

from langchain.qa import RetrievalQA

Hi ,I have installed the library using "%pip install langchain", but still I couldn't import RetrievalQA. Could anyone help?

  • 522 Views
  • 1 replies
  • 0 kudos
Latest Reply
filipniziol
Contributor III
  • 0 kudos

Hi @dinusr ,Are you using the correct namespace langchain.chains to import?from langchain.chains import RetrievalQAIf yes, try to 1. Install the most recent version %pip install --upgrade --force-reinstall langchain2. Restart the kernel : dbutils.lib...

  • 0 kudos
dileepkumar_t
by New Contributor
  • 641 Views
  • 0 replies
  • 0 kudos

Error - Interact with SQL database

 When I try to use Datbricks sql agent, I'm getting below error:DatabaseError: (databricks.sql.exc.ServerOperationError) [UNBOUND_SQL_PARAMETER] Found the unbound parameter: param_1. Please, fix `args` and provide a mapping of the parameter to a SQL ...

  • 641 Views
  • 0 replies
  • 0 kudos
mortenhaga2
by New Contributor III
  • 4365 Views
  • 7 replies
  • 2 kudos

Resolved! Genie: Cant upvote/downvote, cant edit queries nor view other results

Hi allI have been trying to get some feedback on this before, but since this is important to if and how my organization is going to adopt this tool, I need some help on this:For me as an account admin and workspace admin, my problem is that I cant up...

mortenhaga2_0-1725264270178.png mortenhaga2_1-1725264435843.png mortenhaga2_3-1725264479589.png
  • 4365 Views
  • 7 replies
  • 2 kudos
Latest Reply
holly
Databricks Employee
  • 2 kudos

Amazing user story - this has been great for our internal discussions, thank you

  • 2 kudos
6 More Replies
SandipCoder
by New Contributor II
  • 1178 Views
  • 1 replies
  • 0 kudos

How to deploy an agent into model registry using MLFlow

Goal :Here below I am attaching my code snippet where I am trying to build an agent on my custom functions .Things are working well when I am running agent.invoke(“Question”).But now I want to deploy this agent into model registry using MLFlow but I ...

  • 1178 Views
  • 1 replies
  • 0 kudos
Latest Reply
prar_shah
New Contributor III
  • 0 kudos

Had the same question when I was trying to deploy my custom llm. How we did it was wrapping it inside a custom mlflow model and registering it.

  • 0 kudos
VELU1122
by New Contributor II
  • 769 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...

  • 769 Views
  • 0 replies
  • 0 kudos
sue01
by New Contributor II
  • 688 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
  • 688 Views
  • 1 replies
  • 0 kudos
Latest Reply
szymon_dybczak
Esteemed Contributor III
  • 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
Michael_Galli
by Contributor III
  • 2497 Views
  • 6 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...

  • 2497 Views
  • 6 replies
  • 4 kudos
Latest Reply
jessysantos
Databricks Employee
  • 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
5 More Replies
Amit_Dass_Chmp
by New Contributor III
  • 1392 Views
  • 1 replies
  • 0 kudos

How we can choose the right LLM model, also considering the cost.

Hi All, I understand we are in the evaluation journey where we have 100+ LLMs (Open or Proprietary models ), but please guide us on how we can choose the right LLM model, also considering the cost. Do we have any benchmark to follow considering the u...

  • 1392 Views
  • 1 replies
  • 0 kudos
Latest Reply
mhiltner
Databricks Employee
  • 0 kudos

Hey! It depends a lot on your application. Different LLMs excel in different functions. Proprietary models will be more expensive then Open Source ones, but they will likely lead you to a faster time to production with your applications.  Also, if yo...

  • 0 kudos