cancel
Showing results for 
Search instead for 
Did you mean: 
Data Engineering
cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Anonymous
by Not applicable
  • 281 Views
  • 0 replies
  • 0 kudos

docs.databricks.com

What Serverless features are you using on Databricks? I am curious to know.Is it Databricks SQL Serverless or Model Serving?Proceed here to Compare serverless compute to other Databricks architectureshttps://docs.databricks.com/serverless-compute/ind...

  • 281 Views
  • 0 replies
  • 0 kudos
bhawik21
by New Contributor II
  • 1428 Views
  • 4 replies
  • 0 kudos

Resolved! How do I invoke a data enrichment function before model.predict while serving the model

I have used mlflow and got my model served through REST API. It work fine when all model features are provided. But my use case is that only a single feature (the primary key) will be provided by the consumer application, and my code has to lookup th...

  • 1428 Views
  • 4 replies
  • 0 kudos
Latest Reply
LuisL
New Contributor II
  • 0 kudos

You can create a custom endpoint for your REST API that handles the data massaging before calling themodel.predict function. This endpoint can take in the primary key as an input, retrieve the additional features from the database based on that key, ...

  • 0 kudos
3 More Replies
harish_s
by New Contributor II
  • 3287 Views
  • 5 replies
  • 5 kudos

Resolved! Hi, I get the following error when I enable model serving for spacy model via MLFLOW.

+ echo 'GUNICORN_CMD_ARGS=--timeout 63 --workers 4 'GUNICORN_CMD_ARGS=--timeout 63 --workers 4 + mlflow models serve --no-conda -m /tmp/tmp1a4ltdrk/spacymodelv1 -h unix:/tmp/3.sock -p12022/03/01 08:26:37 INFO mlflow.models.cli: Selected backend for f...

  • 3287 Views
  • 5 replies
  • 5 kudos
Latest Reply
Kaniz
Community Manager
  • 5 kudos

Hi @Harish S​ , We haven't heard from you on the last response from @Prabakar Ammeappin​ , me, and @Jose Gonzalez​ , and I was checking back to see if you have a resolution yet. If you have any solution, please share it with the community as it can b...

  • 5 kudos
4 More Replies
Maverick1
by Valued Contributor II
  • 2006 Views
  • 5 replies
  • 7 kudos

How to deploy mlflow models to sagemaker endpoints where sagemaker refers the private docker registry?

Is it possible to deploy the mlflow model to a sagemaker endpoint where the image URL is not referring to an image in ECR but the image is actually present in a private docker registry?

  • 2006 Views
  • 5 replies
  • 7 kudos
Latest Reply
Atanu
Esteemed Contributor
  • 7 kudos

@Saurabh Verma​ , this to create the endpoint.also, check this out - https://github.com/mlflow/mlflow/blob/0fa849ad75e5733bf76cc14a4455657c5c32f107/mlflow/sagemaker/__init__.py#L361

  • 7 kudos
4 More Replies
gibbona1
by New Contributor II
  • 2562 Views
  • 5 replies
  • 1 kudos

Resolved! Correct setup and format for calling REST API for image classification

I trained a basic image classification model on MNIST using Tensorflow, logging the experiment run with MLflow.Model: "my_sequential" _________________________________________________________________ Layer (type) Output Shape ...

mnist_model_error
  • 2562 Views
  • 5 replies
  • 1 kudos
Latest Reply
Atanu
Esteemed Contributor
  • 1 kudos

@Anthony Gibbons​  may be this git should work with your use case - https://github.com/mlflow/mlflow/issues/1661

  • 1 kudos
4 More Replies
Mihai1
by New Contributor III
  • 1327 Views
  • 4 replies
  • 4 kudos

Resolved! MLflow Model Serving on Azure Databricks General Availability

When is MLflow Model Serving on Azure Databricks expected to become General Available?

  • 1327 Views
  • 4 replies
  • 4 kudos
Latest Reply
User16764241763
Honored Contributor
  • 4 kudos

Hello Mihai,We plan to GA, Model serving by end of this year as we are working on a lot of improvements.

  • 4 kudos
3 More Replies
User16826992666
by Valued Contributor
  • 987 Views
  • 1 replies
  • 0 kudos

Resolved! MLflow Model Serving latency expectations

What kind of latency should I expect when using the built in model serving capability in MLflow. Evaluating whether it would be a good fit for our use case

  • 987 Views
  • 1 replies
  • 0 kudos
Latest Reply
sajith_appukutt
Honored Contributor II
  • 0 kudos

What are your throughput requirements in addition to latency. Currently this is in private preview and databricks recommends this only for low throughput and non-critical applications. However, as it move towards GA, this would change. Please get in...

  • 0 kudos
Labels