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

Chunk CRUD #1483

Merged
merged 5 commits into from
Oct 25, 2024
Merged

Chunk CRUD #1483

merged 5 commits into from
Oct 25, 2024

Conversation

NolanTrem
Copy link
Collaborator

@NolanTrem NolanTrem commented Oct 24, 2024

Introduces a number of improvements over chunk management.


Important

Introduces CRUD operations for chunks, including new API endpoints, database updates, and integration tests.

  • Behavior:
    • Adds CRUD operations for chunks, including ingestion, updating, and deletion.
    • New API endpoints in ingestion_router.py for ingest_chunks, update_chunk, and delete.
    • Integration tests added in runner_sdk.py for chunk operations.
  • Database:
    • Updates PostgresVectorHandler in vector.py to support chunk retrieval and updates.
    • Adds get_chunk() and modifies get_document_chunks() to order by chunk_order.
  • Services:
    • Implements update_chunk_ingress() in ingestion_service.py for updating chunk content and metadata.
    • Adds parse_update_chunk_input() in IngestionServiceAdapter.
  • Orchestration:
    • Adds workflows for chunk operations in ingestion_workflow.py and simple/ingestion_workflow.py.
  • SDK:
    • Adds updateChunk() method in r2rClient.ts and update_chunks() in ingestion.py for chunk updates.
  • Misc:
    • Updates action.yml to include tests for chunk operations.

This description was created by Ellipsis for 578971a. It will automatically update as commits are pushed.

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 578971a in 40 seconds

More details
  • Looked at 893 lines of code in 14 files
  • Skipped 0 files when reviewing.
  • Skipped posting 3 drafted comments based on config settings.
1. py/tests/integration/runner_sdk.py:1801
  • Draft comment:
    Consider adding assertions or checks to verify the success of the chunk ingestion operation. This will help ensure that the operation performs as expected and any issues are caught early.
  • Reason this comment was not posted:
    Confidence changes required: 50%
    The test functions for chunk operations (ingest, update, delete) do not include assertions or checks to verify the success of the operations. This could lead to silent failures if the operations do not perform as expected.
2. py/tests/integration/runner_sdk.py:1855
  • Draft comment:
    Consider adding assertions or checks to verify the success of the chunk update operation. This will help ensure that the operation performs as expected and any issues are caught early.
  • Reason this comment was not posted:
    Confidence changes required: 50%
    The test functions for chunk operations (ingest, update, delete) do not include assertions or checks to verify the success of the operations. This could lead to silent failures if the operations do not perform as expected.
3. py/tests/integration/runner_sdk.py:1902
  • Draft comment:
    Consider adding assertions or checks to verify the success of the chunk deletion operation. This will help ensure that the operation performs as expected and any issues are caught early.
  • Reason this comment was not posted:
    Confidence changes required: 50%
    The test functions for chunk operations (ingest, update, delete) do not include assertions or checks to verify the success of the operations. This could lead to silent failures if the operations do not perform as expected.

Workflow ID: wflow_0lQQqxPBp5zoVLcV


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

Copy link

vercel bot commented Oct 24, 2024

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

Name Status Preview Comments Updated (UTC)
yc_demo ✅ Ready (Inspect) Visit Preview 💬 Add feedback Oct 24, 2024 11:48pm
yc-demo ✅ Ready (Inspect) Visit Preview 💬 Add feedback Oct 24, 2024 11:48pm
1 Skipped Deployment
Name Status Preview Comments Updated (UTC)
recommendation_platform ⬜️ Ignored (Inspect) Oct 24, 2024 11:48pm

@emrgnt-cmplxty emrgnt-cmplxty merged commit 734083e into dev-minor Oct 25, 2024
11 of 22 checks passed
emrgnt-cmplxty added a commit that referenced this pull request Oct 25, 2024
* Feature/port kg to handler rebased (#1478)

* up

* up

* add back database

* merge

* merge

* removing prompt provider (#1479)

* removing prompt provider

* migrate prompt provider

* update lock file

* rm file provider

* refactor imports (#1481)

* making types more explicit across codebase (#1482)

* cleanup prompt handler

* cleanup prompt handler

* add kg create tables

* Feature/dev minor rebased (#1485)

* Update pyproject.toml (#1471)

* add alembic migrations to pypi release (#1472)

* add alembic migrations to pypi release

* modify path

* run on main (#1474)

* minor kg-search bug (#1476)

* minor kg-search bug

* fix

* Update pyproject.toml

* Move to psycopg binary (#1477)

---------

Co-authored-by: Shreyas Pimpalgaonkar <[email protected]>
Co-authored-by: Nolan Tremelling <[email protected]>

* Chunk CRUD (#1483)

* check in

* Finish ingest chunks, delete, and testing

* Docs and JS tests

* Ensure that we retrieve KG Status for documents in collection (#1484)

* Update pyproject.toml (#1471)

* add alembic migrations to pypi release (#1472)

* add alembic migrations to pypi release

* modify path

* run on main (#1474)

* minor kg-search bug (#1476)

* minor kg-search bug

* fix

* Update pyproject.toml

* Move to psycopg binary (#1477)

* Ensure that we retrieve KG Status for documents in collection

* github sucks

---------

Co-authored-by: emrgnt-cmplxty <[email protected]>
Co-authored-by: Shreyas Pimpalgaonkar <[email protected]>

---------

Co-authored-by: Shreyas Pimpalgaonkar <[email protected]>
Co-authored-by: Nolan Tremelling <[email protected]>
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.

2 participants