- 29970 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 ...
- 29970 Views
- 18 replies
- 33 kudos
- 3237 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...
- 3237 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
- 10874 Views
- 3 replies
- 3 kudos
Lets talk genAI
Im Jose and lets talk genAI
- 10874 Views
- 3 replies
- 3 kudos
- 529 Views
- 1 replies
- 0 kudos
How to build MLOps
How to use Databricks to build MLOps
- 529 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
- 4406 Views
- 2 replies
- 0 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...
- 4406 Views
- 2 replies
- 0 kudos
- 0 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.
- 0 kudos
- 2456 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...
- 2456 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
- 3623 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?
- 3623 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
- 2064 Views
- 4 replies
- 2 kudos
Using Genie in Multi-Agent Systems — SQL Query Missing from Output
Hi Community,I’ve implemented a multi-agent system using Genie in Databricks, following the guide on "Use Genie in multi-agent systems | Databricks Documentation". The system integrates well with vector indexes, and everything works fine during model...
- 2064 Views
- 4 replies
- 2 kudos
- 2 kudos
Hi @Karthik_Karanm,As per my understanding, the issue seems to be that the conversation state or authentication context isn’t being properly passed between agents in the multi-agent setup.A few things you might try:Avoid caching session or conversati...
- 2 kudos
- 3802 Views
- 1 replies
- 0 kudos
Multi-Vector Embedding Support
Does Databricks Vector Search support Multi-Vector Embedding?
- 3802 Views
- 1 replies
- 0 kudos
- 0 kudos
I believe we can only have one embedding source column mapped to one embedding column.
- 0 kudos
- 956 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...
- 956 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
- 1609 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...
- 1609 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
- 910 Views
- 1 replies
- 0 kudos
Resolved! AI for educators certificate
Recently I completed the Google generative A.I course for educators. At the start it was mentioned that I will receive a certificate but I didn't got any.. Please help me to get the certificate.
- 910 Views
- 1 replies
- 0 kudos
- 0 kudos
Hello @Nur07! Congratulations on completing the course! Since the course isn’t affiliated with Databricks, I recommend contacting the platform or provider where you enrolled for assistance with the certificate. Let us know if you need help with Datab...
- 0 kudos
- 1467 Views
- 2 replies
- 1 kudos
Resolved! Compound keys on Genie
Is it just me or Genie´s generated SQL code failes to use composite keys -of the underlying related tables- as its default behavoir, regardless of the model having relationships declared explicitly.Sometimes I have fixed this scenario by using an ins...
- 1467 Views
- 2 replies
- 1 kudos
- 1 kudos
Hi @JYvesLimantour Genie struggles with composite keys by design. A few things that might help:Clearly define your primary and foreign key relationships in Unity Catalog.Add example SQL queries that include composite joins to give Genie better contex...
- 1 kudos
- 1290 Views
- 1 replies
- 1 kudos
Question about response time by Llama 3.3 70B
Hey everyone !So I'm new into Databricks and I'm learning about the possibilities offered by Mosaic AI Foundation Model Serving. I'm mostly following the Azure's documentation to learn about it.In my testing, I've created 4 unity catalog functions vi...
- 1290 Views
- 1 replies
- 1 kudos
- 1 kudos
Llama 3.3 normally offers faster inference speeds compared to earlier versions. It provides approximately 40% faster responses and reduced batch processing time However, the usual performance for Mosaic AI Model Serving are also influenced by configu...
- 1 kudos
- 5765 Views
- 10 replies
- 7 kudos
Resolved! Insufficient Permission Error When Serving RAG Model with Multiple Vector Search Indexes
Hi Community,I’m currently working on a Retrieval-Augmented Generation (RAG) use case in Databricks. I’ve successfully implemented and served a model that uses a single Vector Search index, and everything works as expected.However, when I try to serv...
- 5765 Views
- 10 replies
- 7 kudos
- 2127 Views
- 3 replies
- 0 kudos
Vector Index format.
On of the key benefits of a delta table format is that it's open. Is this also the case for vector indexes as well? If so where could I find it's specification?In Databricks today, we see that we can create and manage a vector index using API's. (ht...
- 2127 Views
- 3 replies
- 0 kudos
- 0 kudos
HI Team, I am trying to update an existing vector search index with new data which is in another delta table. But i have no luck figuring out how to do it using Python SDK. Can you please hekp point to the right resources?
- 0 kudos
