cancel
Showing results for 
Search instead for 
Did you mean: 
Machine Learning
Dive into the world of machine learning on the Databricks platform. Explore discussions on algorithms, model training, deployment, and more. Connect with ML enthusiasts and experts.
cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

yhyhy3
by New Contributor III
  • 1200 Views
  • 2 replies
  • 0 kudos

Foundation Model APIs HIPAA compliance

I saw that Foundation Model API  is not HIPAA compliant. Is there a timeline in which we could expect it to be HIPAA compliant? I work for a healthcare company with a BAA with Databricks.

  • 1200 Views
  • 2 replies
  • 0 kudos
Latest Reply
User16776430979
New Contributor III
  • 0 kudos

It is now HIPAA compliant: Provisioned throughput endpoints are available with compliance certifications like HIPAA, Model Serving is HIPAA compliant in all regions

  • 0 kudos
1 More Replies
grajee
by New Contributor
  • 80 Views
  • 0 replies
  • 1 kudos

Lakehouse Monitoring of Inference Table

All,I'm trying to setup a lakehouse monitoring process for the WineQuality model that is widely available. While setting up the Serving Endpoint, I enabled "Inference Table" option for which the inference table was created automatically. The columns ...

Machine Learning
Inference Table
Lakehouse-Monitoring
  • 80 Views
  • 0 replies
  • 1 kudos
sodrberg
by New Contributor
  • 154 Views
  • 1 replies
  • 0 kudos

Model serving endpoint creation failed

I have a logged pyfunc mlflow model that runs without issues in a databricks notebook using "mlflow.pyfunc.load_model()". I can deploy it without issues as a model serving endpoint with "workload_type" set to GPU, but when i try to update the endpoin...

  • 154 Views
  • 1 replies
  • 0 kudos
Latest Reply
kamal_ch
Databricks Employee
  • 0 kudos

The error encountered when updating the endpoint to a CPU-only configuration could be due to several reasons related to dependency and environment configuration mismatches:   • Dependency Mismatch: The error may be related to mismatched dependencies...

  • 0 kudos
gustavocavsanto
by New Contributor II
  • 886 Views
  • 4 replies
  • 1 kudos

Error 401: "Missing authorization details for accessing model serving endpoints" with OAuth Token on

I am trying to generate an OAuth token for my Azure Databricks workspace to access a model serving API in production. The code I’m using generates a token successfully, but I keep receiving a 401 error with the message "Missing authorization details ...

  • 886 Views
  • 4 replies
  • 1 kudos
Latest Reply
dansayan
New Contributor II
  • 1 kudos

I managed to retrieve the access token but when i call the served endpoint i get the same error as the user above. my code is below. As for the SP in databricks workspace, it was given the manage permission on the served endpoint. Any suggestions? 

  • 1 kudos
3 More Replies
dcunningham1
by New Contributor II
  • 658 Views
  • 2 replies
  • 1 kudos

Possible to use `params` argument of `mlflow.pyfunc.PythonModel` deployed to Databricks endpoint?

I'm deploying a custom model using the `mlflow.pyfunc.PythonModel` class as described here. My model uses the `params` argument in the `predict` method to allow the user to choose some aspects of the model at inference time. For example:class CustomM...

  • 658 Views
  • 2 replies
  • 1 kudos
Latest Reply
umesh_gattem
New Contributor II
  • 1 kudos

Is there any update on this feature? 

  • 1 kudos
1 More Replies
Nawneet
by New Contributor II
  • 205 Views
  • 2 replies
  • 0 kudos

Error: "[REQUIRES_SINGLE_PART_NAMESPACE] sparkcatalog requires a single-part namespace"

Hi, In my code I am creating a Spark session, that can be to used query the Unity Catalog delta tables.I have an MLFlow Pyfunc model that uses these table to retrieve information. Things work well from my cluster but getting below error from model se...

  • 205 Views
  • 2 replies
  • 0 kudos
Latest Reply
Nawneet
New Contributor II
  • 0 kudos

Hi @Alberto_Umana ,But I am not getting exception as "Exception: No SparkSession Available!" ,probably because I am installing that as part of conda environment creation. Spark session is available. Exception is "[REQUIRES_SINGLE_PART_NAMESPACE] spar...

  • 0 kudos
1 More Replies
Djay101
by New Contributor
  • 532 Views
  • 2 replies
  • 0 kudos

How do we log without a dbfs for MLFlow models.

Hi Databricks Team,We are planning a UC Migration for a customer who currently has around 500 experiments, each with multiple runs. These experiments are registered and MLflow is logging to DBFS locations. However, we have not found any documentation...

  • 532 Views
  • 2 replies
  • 0 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 0 kudos

Hi @rahuja / @Djay101, Do you have any account team contact for your Databricks subscription? I think this kind of migration requires more analysis based on your use-case. I could not find a straight-forward way to perform this migration, perhaps the...

  • 0 kudos
1 More Replies
Akash_Wadhankar
by New Contributor III
  • 477 Views
  • 0 replies
  • 0 kudos

Learn Databricks AI medium article series for fellow learners.

When it comes to machine learning, the platform plays a pivotal role in successful implementation. Databricks offers a best-in-class machine learning platform with cutting-edge features such as MLflow, Model Registry, Feature Store, and MLOps, which ...

Machine Learning
DatabricksML MachineLearning AI FeatureStore DecisionScience
  • 477 Views
  • 0 replies
  • 0 kudos
johndoe99012
by New Contributor II
  • 599 Views
  • 4 replies
  • 1 kudos

How to serve a Unity Catalog ML model to external usage

Hello everyone I am following this notebook tutorial https://docs.databricks.com/en/machine-learning/manage-model-lifecycle/index.html#example-notebook Now I can register a machine learning model in Unity Catalog, but the tutorial only shows how to u...

  • 599 Views
  • 4 replies
  • 1 kudos
Latest Reply
filipniziol
Contributor III
  • 1 kudos

Hi @johndoe99012 If the answer resolved your question, please consider marking it as the solution. It helps others in the community find answers more easily.  

  • 1 kudos
3 More Replies
TinSlim
by New Contributor III
  • 3230 Views
  • 3 replies
  • 0 kudos

Maximum wait time Databricks Model Serving

hi, hope you are fineI deployed a model 3 or 2 months ago using Databricks Serving and MLFlow. The model worked good using GPU from model serving.I stopped using it for some months and when I tried again deploying it, it has some errors.1. [FIXED] A ...

TinSlim_0-1733768150465.png TinSlim_1-1733768584347.png
  • 3230 Views
  • 3 replies
  • 0 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 0 kudos

Thanks, I will review it and get back. I'll DIM you.

  • 0 kudos
2 More Replies
robertol
by New Contributor III
  • 749 Views
  • 2 replies
  • 0 kudos

Resolved! Error in creating a serving endpoint: registered model not found

I have registered a custom model which loads another model in the load_context method. Everything works fine when I load (with mlflow.pyfunc.load_model) and use the model in a notebook. When I try to create a serving endpoint for it I keep becoming t...

  • 749 Views
  • 2 replies
  • 0 kudos
Latest Reply
robertol
New Contributor III
  • 0 kudos

It is registered in the Unity Catalog. I have found a complete other solution now. With the help of TransformedTargetRegressor I don't need a separate normalisation step anymore and therefore don't load a model in load_context anymore.

  • 0 kudos
1 More Replies
damselfly20
by New Contributor III
  • 515 Views
  • 2 replies
  • 1 kudos

Endpoint creation without scale-to-zero

Hi, I've got a question about deploying an endpoint for Llama 3.1 8b. The following code should create the endpoint without scale-to-zero. The endpoint is being created, but with scale-to-zero, although scale_to_zero_enabled is set to False. Instead ...

  • 515 Views
  • 2 replies
  • 1 kudos
Latest Reply
damselfly20
New Contributor III
  • 1 kudos

Thanks for the reply @Walter_C. This didn't quite work, since it used a CPU and didn't consider the max_provisioned_throughput, but I finally got it to work like this: from mlflow.deployments import get_deploy_client client = get_deploy_client("data...

  • 1 kudos
1 More Replies
hawa
by New Contributor II
  • 529 Views
  • 1 replies
  • 0 kudos

Problem serving a langchain model on Databricks

Hi, I've encountered a problem of serving a langchain model I just created successfully on Databricks.I was using the following code to set up a model in unity catalog:from mlflow.models import infer_signatureimport mlflowimport langchainmlflow.set_r...

  • 529 Views
  • 1 replies
  • 0 kudos
Latest Reply
hawa
New Contributor II
  • 0 kudos

I suspected the issue is coming from this small error I got: Got error: Must specify a chain Type in config. I used the chain_type="stuff" when building the langchain but I'm not sure how to fix it.

  • 0 kudos
Labels