← 返回首页
docs: Add blog post on unified transformation framework by Copilot · Pull Request #5858 · feast-dev/feast · GitHub
Skip to content

Navigation Menu

Toggle navigation
Sign in
Appearance settings
Search or jump to...

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Appearance settings
Resetting focus

docs: Add blog post on unified transformation framework#5858

Draft
Copilot wants to merge 4 commits into
masterfrom
copilot/add-blog-post-transformation-framework
Draft

docs: Add blog post on unified transformation framework#5858
Copilot wants to merge 4 commits into
masterfrom
copilot/add-blog-post-transformation-framework

Conversation

Copy link
Copy Markdown
Contributor

Copilot AI commented Jan 14, 2026
edited
Loading

What this PR does / why we need it:

Adds comprehensive blog post documenting Feast's unified transformation framework, covering the Transformation API, multiple compute engines, and migration patterns.

Changes

Blog Post (infra/website/docs/blog/transformation-framework.md)

  • Documents unified Transformation API with 6 execution modes (Python, Pandas, Spark, Spark SQL, Ray, SQL, Substrait)
  • Explains ComputeEngine architecture (LocalComputeEngine, SparkComputeEngine) with DAG-based execution
  • Includes mermaid diagrams for architecture and feature build flow
  • Provides migration guide from legacy On Demand Feature Views
  • Contains real-world use cases and code examples
  • Authors: @HaoXuAI and GitHub Copilot

Documentation Updates (docs/getting-started/architecture/feature-transformation.md)

  • Added callout linking to blog post
  • Documented available TransformationMode options with use case guidance

Example Usage

from feast.transformation.base import transformation from feast.transformation.mode import TransformationMode # Define transformation with decorator @transformation(mode=TransformationMode.SPARK) def transform_features(df: DataFrame) -> DataFrame: return df.withColumn("scaled", df["feature"] * 2) # Apply to FeatureView feature_view = FeatureView( name="driver_stats", feature_transformation=transform_features, schema=[...], source=data_source, )

Which issue(s) this PR fixes:

Addresses documentation request for transformation framework work from PRs #5181, #5223, #5278, #5185, #5281, #5287, #5354, #5445, #5521, #5523, #5666, #5611, #5612, #5502, #5650, #5629

Misc

Blog post covers architectural improvements that unify feature transformation logic across compute engines while maintaining backward compatibility with existing APIs.

Original prompt

This section details on the original issue you should resolve

<issue_title>Add blog post on new transformation framework</issue_title>
<issue_description>Is your feature request related to a problem? Please describe.
I want a blog post on the website that outlines the new transformation framework in feast. Please see these PRs:

Describe the solution you'd like
Please make sure the blog post is under infra/website/docs/blog and it would probably good to update /docs if needed.

Feel free to add a mermaid diagram or so. Please list @HaoXuAI and GitHub Copillot as the authors.
</issue_description>

<agent_instructions>I want a blog post on the website that outlines the new transformation framework in feast. Please see these PRs:

Please make sure the blog post is under infra/website/docs/blog and it would probably good to update /docs if needed. Also, please make sure to look at the existing documentation before updating.

Feel free to add a mermaid diagram or so. Please list @HaoXuAI and GitHub Copillot as the authors.
</agent_instructions>

Comments on the Issue (you are @copilot in this section)

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

Copilot AI and others added 2 commits January 14, 2026 15:44
Co-authored-by: franciscojavierarceo <4163062+franciscojavierarceo@users.noreply.github.com>
Co-authored-by: franciscojavierarceo <4163062+franciscojavierarceo@users.noreply.github.com>
Copilot AI changed the title [WIP] Add blog post on new transformation framework docs: Add blog post on unified transformation framework Jan 14, 2026
returns some set of output data. Feature transformations can happen on either raw data or derived data.

{% hint style="info" %}
**New in Feast**: Check out the [Unified Transformation Framework blog post](../../blog/transformation-framework.md) to learn about the latest enhancements to feature transformations, including support for multiple compute engines and a consistent API across different transformation modes.
Copy link
Copy Markdown
Member

franciscojavierarceo Jan 14, 2026
edited
Loading

Choose a reason for hiding this comment

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

Choose a reason Spam Abuse Off Topic Outdated Duplicate Resolved Low Quality Hide comment

@copilot this will live on the feast.dev website, not our docs so you can remove this change.

Comment thread infra/website/docs/blog/transformation-framework.md Outdated Show resolved Hide resolved
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add blog post on new transformation framework

2 participants

Footer

© 2026 GitHub, Inc.