Skip to content

chore: update destination example script configuration to use GitHub and state cache #659

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged

Conversation

aaronsteers
Copy link
Contributor

@aaronsteers aaronsteers commented Apr 16, 2025

Summary by CodeRabbit

  • New Features
    • Switched data source to GitHub repositories with support for personal access tokens.
    • Added the ability to select the "issues" stream explicitly.
    • Introduced a local DuckDB cache for state management during data sync operations.

@aaronsteers aaronsteers requested a review from Copilot April 16, 2025 06:04
@aaronsteers aaronsteers marked this pull request as ready for review April 16, 2025 06:04
Copy link
Contributor

@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

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

Copilot reviewed 1 out of 1 changed files in this pull request and generated 1 comment.

Copy link
Contributor

coderabbitai bot commented Apr 16, 2025

📝 Walkthrough

Walkthrough

The changes update the example script to use the "source-github" connector instead of "source-faker", requiring a repository list and GitHub credentials. The script now explicitly checks the source and selects the "issues" stream. A new function is introduced to create a local DuckDB cache, which is then used as the state_cache in the destination's write operation. The cache argument remains disabled.

Changes

File(s) Change Summary
examples/run_sync_to_destination_wo_cache.py Switched source from "source-faker" to "source-github" with repo list and credentials; added explicit stream selection and source check; introduced get_cache() function to create a local DuckDB cache; passed cache as state_cache in destination write.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant Source (GitHub)
    participant Cache (DuckDB)
    participant Destination

    User->>Source (GitHub): Initialize with repo list and credentials
    User->>Source (GitHub): check()
    User->>Source (GitHub): select_stream("issues")
    User->>Cache (DuckDB): get_cache()
    User->>Destination: write(source, state_cache=Cache, cache=False)
    Destination->>Cache (DuckDB): Use for state caching
    Destination->>Source (GitHub): Read issues stream
Loading

Tip

⚡💬 Agentic Chat (Pro Plan, General Availability)
  • We're introducing multi-step agentic chat in review comments and issue comments, within and outside of PR's. This feature enhances review and issue discussions with the CodeRabbit agentic chat by enabling advanced interactions, including the ability to create pull requests directly from comments and add commits to existing pull requests.
✨ Finishing Touches
  • 📝 Generate Docstrings

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
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

‼️ IMPORTANT
Auto-reply has been disabled for this repository in the CodeRabbit settings. The CodeRabbit bot will not respond to your replies unless it is explicitly tagged.

  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 0

🧹 Nitpick comments (2)
examples/run_sync_to_destination_wo_cache.py (2)

20-35: The GitHub configuration looks good, but is there a fail-safe needed?

The switch from Faker to GitHub source looks great, and I like the explicit stream selection. The assertion on line 22 will prevent the script from running with an empty token, which is good.

One small thought - should we add a friendlier error message if the token is missing or invalid? Something like assert str(github_pat), "GitHub token is required. Set the GITHUB_PERSONAL_ACCESS_TOKEN secret." might help users debug, wdyt?


63-67: Interesting approach with cache parameters

I notice you're setting cache=False while also providing a state_cache. This seems intentional based on the PR title (which mentions "wo_cache" while still using state cache).

Could we add a brief comment explaining this approach for clarity? Something like # Using state_cache for persistence while disabling in-memory cache might help users understand the distinction, wdyt?

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 1b339b2 and 41e1fbc.

📒 Files selected for processing (1)
  • examples/run_sync_to_destination_wo_cache.py (2 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
`examples/*`: These scripts are intended for demonstration purposes only. They are not meant to represent production code. For these scripts, you should prefer brevity over robust ...

examples/*: These scripts are intended for demonstration purposes only. They are not meant to represent production code. For these scripts, you should prefer brevity over robust error handling and handling of edge cases. These are demos - which should be as simple as possible to handle the 'blessed' use cases.

  • examples/run_sync_to_destination_wo_cache.py
⏰ Context from checks skipped due to timeout of 90000ms (7)
  • GitHub Check: Validate PR title
  • GitHub Check: Pytest (Fast)
  • GitHub Check: Pytest (All, Python 3.11, Windows)
  • GitHub Check: Pytest (All, Python 3.11, Ubuntu)
  • GitHub Check: Pytest (All, Python 3.10, Windows)
  • GitHub Check: Pytest (All, Python 3.10, Ubuntu)
  • GitHub Check: Pytest (No Creds)
🔇 Additional comments (2)
examples/run_sync_to_destination_wo_cache.py (2)

31-35: Nice improvement with explicit stream selection!

I like how you've changed from specifying streams in the constructor to explicitly selecting them after creating the source. This approach makes the code more flexible and easier to understand.


38-41: Good addition of the cache function

Creating a dedicated function for getting the cache instance is a clean approach. This makes the code more modular and easier to maintain.

For a demo script, this level of simplicity is appropriate since we're focusing on the "blessed" use case.

@aaronsteers aaronsteers enabled auto-merge (squash) April 16, 2025 06:05
@aaronsteers aaronsteers changed the title chore: update source configuration to use GitHub and select 'issues' stream chore: update destination example script configuration to use GitHub and state cache Apr 16, 2025
@aaronsteers aaronsteers disabled auto-merge April 16, 2025 06:39
@aaronsteers aaronsteers merged commit 49edd5a into main Apr 16, 2025
20 of 23 checks passed
@aaronsteers aaronsteers deleted the chore/update-example-script-for-destinations-wo-cache branch April 16, 2025 06:39
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.

1 participant