- 30437 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 ...
- 30437 Views
- 18 replies
- 33 kudos
- 1476 Views
- 2 replies
- 1 kudos
Resolved! ProgramOfThought module in Dspy error in Databricks notebooks
This module uses deno, but even after installing it. I get a permissions error. Anyone encountered this before?Failed to run ProgramOfThought: [Errno 13] Permission denied: 'deno'
- 1476 Views
- 2 replies
- 1 kudos
- 1 kudos
Got it working @Renu_ I needed to add the permissions in my notebook as I am on serverless. import ospath = "/local_disk0/.ephemeral_nfs/envs/{Python_Env_instance}/bin/deno"os.chmod(path, 0o777)
- 1 kudos
- 1586 Views
- 1 replies
- 1 kudos
Is the basic model considering adding Claude 4 Opus?
Is the basic model considering adding Claude 4 Opus? It should be the strongest model in the world right now, and AWS already supports it.
- 1586 Views
- 1 replies
- 1 kudos
- 1 kudos
Hello @ninicky, Databricks has recently integrated Anthropic's latest models, Claude Opus 4 into our platform as part of a partnership with Anthropic announced on March 26, 2025. Opus will be available in Databricks Mosaic AI as additional first-par...
- 1 kudos
- 2456 Views
- 2 replies
- 0 kudos
Issue with RAG - Review app - endpoint failed to stream the response
Hi Databricks Support,I am facing issue for using - RAG review app endpoint url. Error message: The endpoint failed to stream the response. Retrying without streaming.The RAG endpoint url was created earlier and it worked with review app, at the time...
- 2456 Views
- 2 replies
- 0 kudos
- 0 kudos
Can you share error details? I updated it without an porblme using mlflow.
- 0 kudos
- 11269 Views
- 1 replies
- 1 kudos
Resolved! ai_query issue
As per the doc , one can execute an ai_query in python. But I am sot sure why I can'tWorks in SQLselect 1 as colA, ai_query('databricks-llama-4-maverick', 'what is 2+2') as testBut not in sparkdf = spark.sql("select 1 as colA") df = df.selectExpr(""...
- 11269 Views
- 1 replies
- 1 kudos
- 1 kudos
Hello @smpa01, I tried to reproduce this issue internally and it worked for me as expected in spark as well. I am sharing below screenshot for your reference: I used DBR 15.4 LTS and serverless it worked on both
- 1 kudos
- 1381 Views
- 2 replies
- 0 kudos
Questions about the Knowledge Assistant during agentBrick
hello.I'm testing agentBricks right now. As I'm testing, I have a few questions that I'd like to ask.1) Is it possible to input the schema in a format with input and output?2) In the free trial, when I create a vector search index and utilize it as a...
- 1381 Views
- 2 replies
- 0 kudos
- 0 kudos
Hi @Remy, Yes, you can define input and output schemas in Databricks, typically using formats like Python dictionaries, especially when working with Vector Search indexes.Free Edition allows only one Vector Search endpoint per workspace, so creating ...
- 0 kudos
- 6195 Views
- 1 replies
- 0 kudos
How to use `predict_stream` in Databricks deployed ChatAgent.
Hello,We are working on a solution to have a streaming chat agent. Our agent works fine in the Playground but when we try to call it as an api under /invocations, the streaming does not work.
- 6195 Views
- 1 replies
- 0 kudos
- 0 kudos
Hello @jcastro I wish you a wonderful day ahead! Databricks recommends the MLflow ChatAgent interface to author production-grade agents. These ChatAgent provides advanced agent capabilities like Streaming output to enable interactive user experiences...
- 0 kudos
- 159444 Views
- 12 replies
- 11 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
- 159444 Views
- 12 replies
- 11 kudos
- 11 kudos
Here's the GEnie API Docs - currently in public preview. > Genie API | REST API reference | Databricks on AWSYou can connect to your Genie Spaces and interact with it programmatically.
- 11 kudos
- 3350 Views
- 1 replies
- 1 kudos
Resolved! Delta Sync index - Slow Sync Performance from Delta Table to Mosaic AI Vector
I'm currently working with Mosaic AI Vector Search on Databricks and using a Delta Sync index (TRIGGERED) to sync from a Delta table (with embedding column already precomputed) to a vector index.However, I'm noticing the sync process is quite slow Ro...
- 3350 Views
- 1 replies
- 1 kudos
- 1 kudos
Hello @amitkumarvish , I wish you a wonderful day ahead! This could be due to dimension mismatch between precomputed embeddings and index expectations or due to storing unnecessary metadata columns or binary data in metadata fields which may creates ...
- 1 kudos
- 10934 Views
- 3 replies
- 3 kudos
Lets talk genAI
Im Jose and lets talk genAI
- 10934 Views
- 3 replies
- 3 kudos
- 574 Views
- 1 replies
- 0 kudos
How to build MLOps
How to use Databricks to build MLOps
- 574 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @hemeiling, To build MLOps on Databricks, you can manage the full machine learning lifecycle in one unified platform. Start by preparing your data using Delta Lake and notebooks. Then, train and track models using MLflow, which lets you log metric...
- 0 kudos
- 2592 Views
- 1 replies
- 0 kudos
Resolved! Azure Databricks: Where are foundation models hosted
In the updated Supported models for Databricks Foundation Models APIs - Azure Databricks | Microsoft Learn document, it's stated that Claude 3.7 and 4 Opus are " hosted by Databricks Inc. in AWS". Is that accurate for Azure Databricks, or is there a...
- 2592 Views
- 1 replies
- 0 kudos
- 0 kudos
Claude is not hosted on Azure. Only Amazon Bedrock and Google Cloud's Vertex AI. Databricks hosts it through AWS within their security perimeter; i.e., requests go through Amazon Bedrock (Fig. 1), as indicated by the model name in AWS format and the ...
- 0 kudos
- 3923 Views
- 6 replies
- 1 kudos
Claude Opus not available in Databricks?
https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-modelsOpus is listed here as available model, but I only see Sonnet 4 in Databricks?
- 3923 Views
- 6 replies
- 1 kudos
- 1 kudos
Hi @kingn718 , Can you check to see if your workspace is in a supported region? Right now, Opus is only availble in us-east-1, us-east-2 and us-west-2 per https://docs.databricks.com/aws/en/machine-learning/model-serving/foundation-model-overview. If...
- 1 kudos
- 3845 Views
- 1 replies
- 0 kudos
Multi-Vector Embedding Support
Does Databricks Vector Search support Multi-Vector Embedding?
- 3845 Views
- 1 replies
- 0 kudos
- 0 kudos
I believe we can only have one embedding source column mapped to one embedding column.
- 0 kudos
- 1014 Views
- 2 replies
- 0 kudos
Error when querying RAG serving endpoint
I built a RAG by cloning the databricks example (create a vector search index of databricks documentation and then a RAG).When I try and call the RAG via the serving endpoint from a notebook, I get the following error:dictionary update sequence eleme...
- 1014 Views
- 2 replies
- 0 kudos
- 0 kudos
Hi @mark_goodwin , I believe this has to do with the formatting of the messages. In the serving UI, the formatting is abstracted out for you, but you may need to format it as a list of dictionaries for the invoke() call, such as: messages = [ {"r...
- 0 kudos
- 1773 Views
- 4 replies
- 1 kudos
How to enable word_timestamps=True when querying a Whisper model deployed in Databricks?
I’ve deployed OpenAI’s Whisper model as a serving endpoint in Databricks and I’m trying to transcribe an audio file.import whisper model = whisper.load_model("small") transcript = model.transcribe( word_timestamps=True, audio="path/to/audio...
- 1773 Views
- 4 replies
- 1 kudos
- 1 kudos
Hi @JoaoPigozzo To enable word_timestamps=True when querying your Whisper model deployed as a serving endpoint in Databricks,you must modify the serving endpoint’s inference logic to accept and process this parameter.1. Update your model serving func...
- 1 kudos
