Test/add document summary retriever tests

[F0rJay]

Description

This PR adds missing test cases for DocumentSummaryIndex retrievers. The original test file tests/indices/document_summary/test_retrievers.py only contained an empty test_retrieve_default function with a TODO comment.

Changes Made

• Added test_retrieve_default: Tests the DEFAULT retriever mode (DocumentSummaryIndexRetriever) which uses LLM-based choice selection to retrieve relevant summaries
• Added test_retrieve_embedding: Tests the EMBEDDING retriever mode (DocumentSummaryIndexEmbeddingRetriever) which uses embedding similarity to retrieve summaries
• Implemented proper mocks:
  • mock_llmpredictor_predict_for_choice_select: Mocks LLM predictor for choice select prompts with correct format expected by default_parse_choice_select_answer_fn
  • _get_embeddings: Mocks embedding function for embedding-based retrieval

The tests follow the existing patterns used in other retriever tests (e.g., tests/indices/list/test_retrievers.py) and ensure both retriever modes are properly covered.

Fixes # (N/A - this is a test coverage improvement, not fixing a specific issue)

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

• Yes
• No (Not applicable - this is a test addition)

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• Yes
• No (Not applicable - test-only change)

Type of Change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Test improvement (adding missing test coverage)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

• I added new unit tests to cover this change
• I believe this change is already covered by existing unit tests

Test Coverage:

• test_retrieve_default: Tests that the DEFAULT retriever mode correctly retrieves nodes using LLM-based choice selection
• test_retrieve_embedding: Tests that the EMBEDDING retriever mode correctly retrieves nodes using embedding similarity

Both tests:

• Create a DocumentSummaryIndex with test documents
• Use appropriate mocks for LLM predictions and embeddings
• Verify that retrieved nodes are returned correctly
• Follow existing test patterns in the codebase

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation (Not needed - test-only change)
• I have added Google Colab support for the newly added notebooks. (Not applicable)
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes (Pending - need to run tests after dependencies are installed)
• I ran uv run make format; uv run make lint to appease the lint gods (Pending - will run before final submission)

Additional Notes

This contribution addresses the TODO comment in the original test file and improves test coverage for the DocumentSummaryIndex retrievers. The implementation:

• Uses proper mock functions that match the expected formats
• Tests both retriever modes (DEFAULT and EMBEDDING)
• Follows the existing code style and test patterns
• Adds meaningful assertions to verify correct behavior

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[logan-markewich]

The commits seem pretty out of whack here