test(relationships): add test for standalone file yielding no extra c…

[Ahmath-Gadji]

Fix: exclude standalone files from relationship expansion

Ensures files without a relationship_id are not incorrectly expanded with related or ancestor chunks.

Changes:

• get_file_ancestors in utils.py now filters out rows where relationship_id is None
• Added TestStandaloneFileNoExpansion test class covering: no related files returned, only the file itself as ancestor, and correct storage of falsy relationship_id

Summary by CodeRabbit

• Bug Fixes

  • Fixed handling of standalone files in relationship queries to exclude files without relationships.

• Tests

  • Added tests for relationship handling and data model serialization to ensure reliability.

[coderabbitai]

Warning

Rate limit exceeded

@Ahmath-Gadji has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 9 minutes and 11 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 06f84aa2-f907-4d42-ad81-cdd74f9fcf90

📥 Commits

Reviewing files that changed from the base of the PR and between a2920bf and 5cfd4f5.

📒 Files selected for processing (2)

• openrag/components/indexer/vectordb/utils.py
• openrag/components/test_relationships.py

📝 Walkthrough

Walkthrough

The changes fix a behavior in get_file_ancestors to filter out entries lacking a relationship_id, ensuring only files part of a relationship are included. Corresponding tests verify that standalone files without relationships do not produce extra related chunks and that the to_dict method includes relationship fields.

Changes

Cohort / File(s)	Summary
Relationship Filter Fix openrag/components/indexer/vectordb/utils.py	Updated get_file_ancestors to filter out entries without a relationship_id, ensuring only related files are included in results.
Test Coverage for Standalone Files openrag/components/test_relationships.py	Added TestStandaloneFileNoExpansion class with test validating that files without relationship_id do not expand to extra related chunks; added test_to_dict_includes_relationship_fields test to verify relationship fields are serialized correctly.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Suggested labels

fix

Poem

🐰 A lone file hops without a tie,
No relationship to multiply,
We filter clean, keep ancestors true,
Each connection now shines through! ✨

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately reflects the main change: adding a test for standalone files that should not produce extra chunks. The truncated title ('test(relationships): add test for standalone file yielding no extra c…') is concise and directly related to the PR's primary objective.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch fix/get_files_by_relationship

📝 Coding Plan

• Generate coding plan for human review comments

---

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

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

openrag/components/indexer/vectordb/utils.py (1)

571-582: ⚠️ Potential issue | 🔴 Critical

Preserve the target row for standalone files in get_file_ancestors().

At Line 581, filtering only on row.relationship_id is not None drops the depth-0 target row when the file is standalone, so this method returns [] instead of returning the file itself.

💡 Proposed fix

             return [
                 {
                     "file_id": row.file_id,
                     "partition": row.partition_name,
                     "parent_id": row.parent_id,
                     "relationship_id": row.relationship_id,
                     "depth": row.depth,
                     **(row.file_metadata or {}),
                 }
                 for row in result
-                if row.relationship_id is not None  # Only include files that are part of a relationship
+                if row.depth == 0 or row.relationship_id is not None
             ]

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In `@openrag/components/indexer/vectordb/utils.py` around lines 571 - 582,
get_file_ancestors() currently filters out rows with relationship_id == None
which drops the depth-0 target row for standalone files; update the list
comprehension filter to include the target row by allowing rows where
row.relationship_id is not None OR row.depth == 0 (i.e., change the condition to
"if row.relationship_id is not None or row.depth == 0") so standalone files at
depth 0 are preserved in the returned list.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@openrag/components/test_relationships.py`:
- Around line 587-624: The test
test_no_extra_chunks_for_file_without_relationship_id relies on
PartitionFileManagerHelper.get_file_ancestors which does not implement the new
ancestor filtering added in openrag/components/indexer/vectordb/utils.py; update
the test to exercise the same production logic by calling the actual function
that contains the new filter (or by invoking the production helper in
openrag/components/indexer/vectordb/utils.py that performs ancestor filtering)
instead of the helper stub, or modify
PartitionFileManagerHelper.get_file_ancestors to replicate the exact filter
logic used in the vectordb utils so the test validates the real ancestor
behavior introduced in this PR.

---

Outside diff comments:
In `@openrag/components/indexer/vectordb/utils.py`:
- Around line 571-582: get_file_ancestors() currently filters out rows with
relationship_id == None which drops the depth-0 target row for standalone files;
update the list comprehension filter to include the target row by allowing rows
where row.relationship_id is not None OR row.depth == 0 (i.e., change the
condition to "if row.relationship_id is not None or row.depth == 0") so
standalone files at depth 0 are preserved in the returned list.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 717f6ad6-a889-4384-879f-3075c0a57df2

📥 Commits

Reviewing files that changed from the base of the PR and between 5f05d37 and a2920bf.

📒 Files selected for processing (2)

• openrag/components/indexer/vectordb/utils.py
• openrag/components/test_relationships.py