Skip to content

Conversation

safoinme
Copy link
Contributor

Describe changes

I implemented/fixed _ to achieve _.

Pre-requisites

Please ensure you have done the following:

  • I have read the CONTRIBUTING.md document.
  • I have added tests to cover my changes.
  • I have based my new branch on develop and the open PR is targeting develop. If your branch wasn't based on develop read Contribution guide on rebasing branch to develop.
  • IMPORTANT: I made sure that my changes are reflected properly in the following resources:
    • ZenML Docs
    • Dashboard: Needs to be communicated to the frontend team.
    • Templates: Might need adjustments (that are not reflected in the template tests) in case of non-breaking changes and deprecations.
    • Projects: Depending on the version dependencies, different projects might get affected.

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Other (add details above)

Copy link
Contributor

coderabbitai bot commented Sep 15, 2025

Important

Review skipped

Auto reviews are disabled on this repository.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

✨ Finishing touches
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch misc/update-examples-deployed-pipelines

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@github-actions github-actions bot added the internal To filter out internal PRs and issues label Sep 15, 2025
Copy link
Contributor

github-actions bot commented Sep 15, 2025

🔍 Broken Links Report

Summary

  • 📁 Files with broken links: 1
  • 🔗 Total broken links: 1
  • 📄 Broken markdown links: 1
  • 🖼️ Broken image links: 0
  • ⚠️ Broken reference placeholders: 0

Details

File Link Type Link Text Broken Path
book/toc.md 📄 "Pipeline Serving Capture Policies" how-to/serving/capture-policies.md
📂 Full file paths
  • /home/runner/work/zenml/zenml/scripts/../docs/book/toc.md

Copy link
Contributor

github-actions bot commented Sep 15, 2025

Documentation Link Check Results

Absolute links check failed
There are broken absolute links in the documentation. See workflow logs for details
Relative links check failed
There are broken relative links in the documentation. See workflow logs for details
Last checked: 2025-09-20 19:46:50 UTC

Copy link
Contributor

Classification template updates in examples/mlops_starter have been pushed.

@htahir1 htahir1 self-requested a review September 18, 2025 12:59
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

settings:
docker:
requirements: requirements.txt
parent_image: zenmldocker/zenml:0.85.0-py3.12
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove

settings={
"docker": DockerSettings(
requirements="requirements.txt",
parent_image="zenmldocker/zenml:0.85.0-py3.12",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remember to remove

settings={
"docker": DockerSettings(
requirements="requirements.txt",
parent_image="zenmldocker/zenml:0.85.0-py3.12",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remember to remove

@strickvl strickvl self-requested a review September 19, 2025 15:24
Copy link
Contributor

@strickvl strickvl left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Getting there. Bunch of small suggestions, but yeah almost there!

(Thanks for adding the eval pipeline too!)

Comment on lines 4 to 5
Usage:
python run.py --train # Train classifier and tag as production
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

add the rest of the options here as well?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

(or delete)

# limitations under the License.
#
from typing import Optional
#!/usr/bin/env python3
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does this file (and others) need the ZenML license at the top?

("good morning", "general"),
("i have a question about my account", "general"),
("what services do you offer", "general"),
("i need assistance with banking", "general"),
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
("i need assistance with banking", "general"),
("i need assistance with banking", "general"),
# More Card Lost (6 examples)
("please freeze my card i cant find it", "card_lost"),
("how do i report my card stolen", "card_lost"),
("need a new card mine went missing", "card_lost"),
("lost debit card cancel it now", "card_lost"),
("misplaced my credit card can you disable it", "card_lost"),
("i lost my atm card what now", "card_lost"),
# More Payments (6 examples)
("set up autopay for my account", "payments"),
("why was my payment declined", "payments"),
("make a one time payment today", "payments"),
("can i change my payment date", "payments"),
("payment is pending how long will it take", "payments"),
("set a recurring monthly payment", "payments"),
# More Account Balance (6 examples)
("whats my available credit right now", "account_balance"),
("show balance for my checking account", "account_balance"),
("how much can i spend before reaching my limit", "account_balance"),
("tell me my statement balance", "account_balance"),
("balance inquiry please", "account_balance"),
("how much do i have available to spend", "account_balance"),
# More Dispute (6 examples)
("i want to file a chargeback", "dispute"),
("merchant charged me twice", "dispute"),
("charged the wrong amount", "dispute"),
("i didnt receive the service i paid for", "dispute"),
("how do i dispute a fraudulent transaction", "dispute"),
("there is an unauthorized withdrawal on my card", "dispute"),
# More Credit Limit (6 examples)
("lower my credit limit please", "credit_limit"),
("temporary limit increase for travel", "credit_limit"),
("why was my credit limit reduced", "credit_limit"),
("can you review my credit line", "credit_limit"),
("whats my current credit limit", "credit_limit"),
("reduce my credit line for safety", "credit_limit"),
# More General (6 examples)
("good afternoon", "general"),
("thanks for your help", "general"),
("i need support with my account", "general"),
("can i talk to an agent", "general"),
("help please", "general"),
("can you assist me with something", "general"),

Added some more examples


logger = get_logger(__name__)

# Expanded dataset for intent classification with more diverse examples
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
# Expanded dataset for intent classification with more diverse examples

@@ -0,0 +1,106 @@
"""Visualization utilities for the ZenML quickstart."""
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Small thing, but not sure all this logic should be in an init file

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is fine i think

This quickstart demonstrates the evolution from generic LLM responses to structured, intent-driven customer support. You'll see how adding a simple intent classifier dramatically improves response quality and user experience. We will:

Unlike traditional MLOps tools, ZenML offers unparalleled flexibility and control. It integrates seamlessly with your infrastructure, allowing both ML and Ops teams to collaborate effectively without compromising on their specific requirements.
- Deploy a generic LLM agent that gives general banking advice
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
- Deploy a generic LLM agent that gives general banking advice
- Deploy a generic LLM agent that gives generic banking advice

Unlike traditional MLOps tools, ZenML offers unparalleled flexibility and control. It integrates seamlessly with your infrastructure, allowing both ML and Ops teams to collaborate effectively without compromising on their specific requirements.
- Deploy a generic LLM agent that gives general banking advice
- Train an intent classifier and tag it as "production"
- Compare generic responses vs. structured, targeted responses
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Are we missing the part where we deploy the intent classifier and/or use it in a
newly deployed agent or something? At least in this story, I somehow assume that
when I run an eval, I'm comparing against two deployments.

def my_pipeline():
data = load_data() # Step 1: Load data
model = train_model(data) # Step 2: Train model using data from step 1
do_agentic_loop(model) # Step 3: Evaluate the model with an agent (toy example)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the comments are out of step with the names of the steps..

```

You can edit `configs/training_aws.yaml` to adjust the settings for running your pipeline in aws.
This generates:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Include screenshots of the visualizations?


zenml stack set <INSERT_YOUR_STACK_NAME_HERE>
python run.py --model_type=t5-small
The magic happens in the init hook:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

link to our docs on hooks?

Copy link

socket-security bot commented Sep 20, 2025

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff Package Supply Chain
Security
Vulnerability Quality Maintenance License
Addedmatplotlib@​3.10.67510010010080

View full report

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
internal To filter out internal PRs and issues
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants