Skip to content
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

Dev minor #1148

Merged
merged 37 commits into from
Sep 13, 2024
Merged

Dev minor #1148

merged 37 commits into from
Sep 13, 2024

Conversation

emrgnt-cmplxty
Copy link
Contributor

@emrgnt-cmplxty emrgnt-cmplxty commented Sep 12, 2024

🚀 This description was created by Ellipsis for commit 198f872

feat: add Docker build workflow and enhance prompt management

Summary:

Add Docker build workflow, enhance prompt management, and update file types and configurations.

Key points:

  • GitHub Workflows: Add build-docker.yml for Docker image build and publish on dev and dev-minor branches; remove build-main.yml and update publish-to-pypi.yml.
  • Dockerfiles: Update Dockerfile and Dockerfile.dev with tesseract-ocr and libreoffice; add Unstructured models initialization.
  • Prompt Management: Add created_at and updated_at timestamps to Prompt in r2r_prompts.py; update prompt loading logic.
  • Parsing and Chunking: Update supported file types in parsing_and_chunking.mdx and document.py to include BMP, EPUB, HEIC, etc.
  • Configuration: Change chunking strategy to auto in r2r.toml; add line item reference reminder in rag_agent.yaml.

Generated with ❤️ by ellipsis.dev

emrgnt-cmplxty and others added 21 commits September 11, 2024 12:40
* improve telemetry

* finish telemetry tweaks
* improve telemetry

* finish telemetry tweaks

* up
* improve telemetry

* finish telemetry tweaks

* up

* fallback to main
* add system diagram

* rm multi

* fix overview

* cleanup and fix

* fix syntax
* cleanups

* bump pkg
* rm unstructured tag, add auto build on dev and dev-minor

* delete old Dockerfile

* add retries
* adding test pypi

* make unstructured docker file

* add on-push effects for dev

* tweak workflows
Copy link

vercel bot commented Sep 12, 2024

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Skipped Deployment
Name Status Preview Comments Updated (UTC)
recommendation_platform ⬜️ Ignored (Inspect) Sep 13, 2024 0:27am

@emrgnt-cmplxty emrgnt-cmplxty marked this pull request as ready for review September 13, 2024 00:25
Copy link
Contributor

@ellipsis-dev ellipsis-dev bot left a comment

Choose a reason for hiding this comment

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

👍 Looks good to me! Reviewed everything up to 2d460c9 in 48 seconds

More details
  • Looked at 2389 lines of code in 30 files
  • Skipped 8 files when reviewing.
  • Skipped posting 1 drafted comments based on config settings.
1. py/core/providers/prompts/r2r_prompts.py:199
  • Draft comment:
    Consider documenting the choice of uuid5 with NAMESPACE_DNS for generating prompt IDs. This ensures consistency but might need explanation for future maintainers.
  • Reason this comment was not posted:
    Confidence changes required: 50%
    The use of uuid5 with NAMESPACE_DNS for generating prompt IDs is a good choice for consistency, but it should be documented or explained why this specific method is chosen over others.

Workflow ID: wflow_WXZmloVtgp1LAu9G


You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

Copy link
Contributor

@ellipsis-dev ellipsis-dev bot left a comment

Choose a reason for hiding this comment

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

👍 Looks good to me! Incremental review on 198f872 in 49 seconds

More details
  • Looked at 13 lines of code in 1 files
  • Skipped 0 files when reviewing.
  • Skipped posting 0 drafted comments based on config settings.

Workflow ID: wflow_E6S34t6w5ySgJhly


You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

@@ -185,6 +185,7 @@ async def parse(
**self.config.chunking_config.extra_fields,
)

iteration = 0 # if there are no chunks
Copy link
Collaborator

Choose a reason for hiding this comment

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

Should we not be failing if a document has no chunks?

@emrgnt-cmplxty emrgnt-cmplxty merged commit 0b3806f into main Sep 13, 2024
8 of 11 checks passed
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.

4 participants