simplifying config

[emrgnt-cmplxty]

Important

This pull request simplifies configuration management, enhances SDK functionalities, and updates core logic for graph extraction in the R2R codebase.

• SDK Enhancements:
  • Added createSample method in DocumentsSDK to ingest sample documents.
  • Renamed rawr to reasoning_agent in RetrievalSDK.
• Configuration Changes:
  • Updated r2r.toml and pyproject.toml to reflect new LLM settings and defaults.
  • Simplified configuration structure, removing deprecated keys and adding new ones like graph_extraction_prompt.
• Core Logic Updates:
  • Replaced KGExtractionStatus with GraphExtractionStatus and similar renames for consistency.
  • Updated GraphService and related classes to use new graph extraction logic.
• Testing and Validation:
  • Updated unit and integration tests to align with new configurations and SDK methods.
  • Ensured backward compatibility where possible, with deprecation warnings for removed features.

^{This description was created by for aa3bb61. It will automatically update as commits are pushed.}

[ellipsis-dev]

👍 Looks good to me! Reviewed everything up to aa3bb61 in 2 minutes and 36 seconds

More details

• Looked at 6930 lines of code in 105 files
• Skipped 1 files when reviewing.
• Skipped posting 14 drafted comments based on config settings.

1. py/core/providers/orchestration/simple.py:15

• Draft comment:
  Several methods (get_worker, step, workflow, failure, start_worker) are left unimplemented (using 'pass'). Ensure these are implemented or clearly documented as stubs.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

2. py/migrations/versions/8077140e1e99_v3_api_database_revision.py:16

• Draft comment:
  Migration script assumes table column renames and drops; verify that the schema matches production. Consider adding more comments if special handling is needed.
• Reason this comment was not posted:
  Confidence changes required: 50% <= threshold 50%
  None

3. py/sdk/base/base_client.py:24

• Draft comment:
  The _get_auth_header() method raises an exception if both access token and API key are set. Consider logging a detailed error message for easier debugging in production.
• Reason this comment was not posted:
  Confidence changes required: 50% <= threshold 50%
  None

4. py/shared/utils/base_utils.py:112

• Draft comment:
  There is a print(e) in the _handle_response() method. In production logging, use logger.error instead of print to avoid unwanted STDOUT.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

5. py/sdk/sync_methods/documents.py:108

• Draft comment:
  Consider handling file open errors (e.g., file not found) in the create() method to ensure resource cleanup is robust.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

6. py/sdk/sync_methods/retrieval.py:71

• Draft comment:
  In the completion() method, the FIXME comment indicates missing return type. It would be beneficial to specify and document the expected type.
• Reason this comment was not posted:
  Confidence changes required: 50% <= threshold 50%
  None

7. py/tests/integration/test_retrieval.py:90

• Draft comment:
  Consider using async consumption for streaming tests instead of a synchronous consume_stream() helper to properly test async generators.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

8. py/tests/unit/test_config.py:209

• Draft comment:
  In test_config_required_keys, consider handling cases when sections are not dicts more robustly instead of using hasattr().
• Reason this comment was not posted:
  Confidence changes required: 50% <= threshold 50%
  None

9. py/shared/abstractions/llm.py:104

• Draft comment:
  In the GenerationConfig init, consider checking for a provided model argument more explicitly to avoid unexpected behavior.
• Reason this comment was not posted:
  Confidence changes required: 50% <= threshold 50%
  None

10. py/core/providers/database/prompts/graph_extraction.yaml:11

• Draft comment:
  Typo: "entit" should be "entity" for clarity.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

11. py/migrations/versions/8077140e1e99_v3_api_database_revision.py:40

• Draft comment:
  Migration check: Ensure that checking for the presence of column 'id' in the collections table is sufficient to decide that migration is not needed. Consider edge cases with custom table structures.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

12. py/sdk/sync_methods/documents.py:104

• Draft comment:
  File handling: Consider using a 'with' statement to handle the temporary file to ensure it's closed properly even on exceptions.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

13. tests/integration/test_indices.py:26

• Draft comment:
  Test coverage: Several tests (e.g., create, delete index) are commented out. Re-enable these tests once stable to increase coverage.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

14. tests/integration/test_retrieval.py:90

• Draft comment:
  Streaming tests: Instead of using a synchronous consumption loop, consider using asyncio for streaming tests to better simulate async behavior.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

Workflow ID: wflow_umPj7VxWCfMk3mY7

---

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