• Haytham Abuelfutuh

    Haytham Abuelfutuh

    3 weeks ago
    @Alex Pozimenko Please meet @Eduardo Apolinario (eapolinario) @Yee they are looking into real world use-cases for what we have been calling Signaling (Human-in-the-loop feature)…
    Haytham Abuelfutuh
    Alex Pozimenko
    +1
    9 replies
    Copy to Clipboard
  • Sandra Youssef

    Sandra Youssef

    2 weeks ago
    Hi Flyers, Tune in to the latest on

    Flyte's Roadmap

    , the upcoming Machine Learning Hangout featuring Flyte & Ray, and hear MLOps Lead @Fabio Grätz present an intro on

    how to build ML systems using open-source tools

    and a typical software adoption journey, presented in depth at the Open Source Summit in Europe next week. Also check out a Flyte Ecosystem project

    UnionML review

    .
  • Sujith Samuel

    Sujith Samuel

    3 weeks ago
    #general I am trying to pass a tensorflow h5 model file between tasks but seems to have hit an issue. Is there any example for passing h5 files between tasks. [1/1] currentAttempt done. Last Error: USER:😛od failed. No message received from kubernetes. [adpz8w6l67zrzfglb9m9-n4-0] terminated with exit code (137). Reason [Error]. Message: use python type that flyte support."} {"asctime": "2022-09-06 08:39:46,752", "name": "flytekit", "levelname": "WARNING", "message": "Unsupported Type <class 'keras.engine.training.Model'> found, Flyte will default to use PickleFile as the transport. Pickle can only be used to send objects between the exact same version of Python, and we strongly recommend to use python type that flyte support."} Different versions of python message is also confusing since all of my tasks are present in the same container and follow the same versions.
    Sujith Samuel
    Shivay Lamba
    +3
    12 replies
    Copy to Clipboard
  • Eduardo Apolinario (eapolinario)

    Eduardo Apolinario (eapolinario)

    2 weeks ago
    Github issue tracking this: https://github.com/flyteorg/flyte/issues/2855 We're going to take care of this asap. The expectation is to have another flytekit beta version by tomorrow (9/7).
    Eduardo Apolinario (eapolinario)
    Ketan (kumare3)
    +1
    4 replies
    Copy to Clipboard
  • h

    Harshit Sharma

    3 weeks ago
    Hi everyone, I am trying to update the node group instance type through env.yaml while deploying with opta. Currently it's at default t3.medium. However, adding node_instance_type with the desired instance type seems to have no effect. I am adding this under - type: k8s-cluster. Do I need to create a separate node group using opta env to achieve this?
    h
    Samhita Alla
    +2
    26 replies
    Copy to Clipboard
  • Kevin Su

    Kevin Su

    2 weeks ago
    could you share your docker file?
    Kevin Su
    2 replies
    Copy to Clipboard
  • varsha Parthasarathy

    varsha Parthasarathy

    2 weeks ago
    Question about BQ plugin: (ref doc https://docs.flyte.org/projects/cookbook/en/latest/auto/integrations/gcp/bigquery/index.html) Will the flyte task also include monitoring/checking if results for the query is complete? Most of our queries does take a while to execute, so wondering how will the pods behave in this case?
    varsha Parthasarathy
    Dan Rammer (hamersaw)
    3 replies
    Copy to Clipboard
  • t

    Tamis van der Laan

    2 weeks ago
    Question, does flyte support continues training and hyper parameter optimisation?
    t
    Samhita Alla
    2 replies
    Copy to Clipboard
  • j

    jeev

    1 month ago
    we're getting collisions with the execution IDs of subworkflow launch plans that propeller is kicking off:
    Setting the MetadataDir for StartNode [<gs://flyte-freenome-computational/metadata/propeller/balrog-production-fldyczra/start-node/data>]
    fldyczra
    was already used. given that these are much shorter than what can be used, is there an easy way to make these longer to avoid possible collisions?
    j
    Ketan (kumare3)
    +5
    54 replies
    Copy to Clipboard
  • Niels Bantilan

    Niels Bantilan

    2 weeks ago
    hi all 👋, I just wanted to ping the community to ask a quick question 🤔: Say you have workflow that uses a trained model to generate predictions on a scheduled launchplan. The question is, how do you typically want to get features for that prediction? I.e. when the scheduled workflow kicks off, where are you reading those features from? Do you need the kick-off time as a parameter to fetching data from, say, an s3 bucket or DB?
    Niels Bantilan
    Ketan (kumare3)
    4 replies
    Copy to Clipboard