fix: apply collection configuration during Qdrant upsert

[majiayu000]

Summary

Fixes #5030

The "Additional Collection Configuration" parameter (qdrantCollectionConfiguration) was properly applied in the init() method but completely ignored in the upsert() method. When upserting documents to a non-existent collection, the collection was created with default Qdrant settings (e.g., replication_factor: 1) instead of user-specified values (e.g., replication_factor: 3, shard_number: 4).

This fix extracts and merges qdrantCollectionConfiguration into dbConfig.collectionConfig in the upsert() method, using the same pattern already used in init().

Changes

• packages/components/nodes/vectorstores/Qdrant/Qdrant.ts: Extract qdrantCollectionConfiguration in upsert() and merge it into dbConfig.collectionConfig
• packages/components/nodes/vectorstores/Qdrant/Qdrant.test.ts: Add 4 tests covering JSON string config, object config, no config (defaults), and vectors merging

Test plan

• New unit tests pass (4 test cases)
• Existing tests unaffected
• Verified shard_number and replication_factor are included in collectionConfig
• Verified vector size and distance settings are preserved alongside collection config
• Verified default behavior is unchanged when no collection configuration is provided

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a critical bug in the Qdrant vector store integration where custom collection configurations, such as shard_number or replication_factor, were not being honored when new collections were created during the document upsert process. Previously, these settings were only applied during initialization, leading to collections being created with default Qdrant parameters. The fix ensures that user-defined collection configurations are consistently applied whenever documents are upserted, providing greater control over Qdrant collection creation.

Highlights

• Configuration Fix: Fixed an issue where Qdrant's "Additional Collection Configuration" was not applied during document upsert operations, causing new collections to be created with default settings instead of user-specified ones.
• Implementation Detail: Implemented logic in the upsert() method to correctly parse and merge qdrantCollectionConfiguration into dbConfig.collectionConfig, mirroring the existing init() method's behavior.
• Test Coverage: Added four new unit tests to ensure proper handling of collection configurations provided as JSON strings, objects, no configuration, and correct merging of vector settings.

Changelog

• packages/components/nodes/vectorstores/Qdrant/Qdrant.test.ts
  • Added a new test file with four test cases to verify the correct application and merging of Qdrant collection configurations during upsert, covering JSON string, object, and undefined configurations, as well as vector merging.
• packages/components/nodes/vectorstores/Qdrant/Qdrant.ts
  • Introduced qdrantCollectionConfiguration as an input to the upsert method.
  • Added logic to parse qdrantCollectionConfiguration (if provided as a string) and merge it with existing dbConfig.collectionConfig, ensuring vector settings are preserved.

Activity

• New unit tests were added and passed successfully.
• Existing tests were confirmed to be unaffected by the changes.
• Verified that shard_number and replication_factor are correctly included in collectionConfig.
• Confirmed that vector size and distance settings are preserved alongside collection configuration.
• Validated that default behavior remains unchanged when no collection configuration is provided.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly identifies and addresses the issue of qdrantCollectionConfiguration being ignored during upsert. The approach of mirroring the logic from the init method is sound for consistency. However, this change introduces a critical vulnerability: providing an invalid JSON string as configuration will cause an unhandled exception and crash the process. My review includes a critical comment with a suggested fix to move the new logic inside the existing try...catch block. Additionally, I've provided feedback on the new tests. While they cover the happy paths, they use an inaccurate mock for parseJsonBody that masks the aforementioned crash and are tightly coupled to the implementation, which could lead to maintenance issues. Addressing these points will make the fix more robust and the tests more reliable.