Skip to content

Conversation

@HenryHengZJ
Copy link
Contributor

No description provided.

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @HenryHengZJ, 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 significantly refactors the Chroma vector store component to enhance its integration with Langchain's core VectorStore abstraction. It modernizes the way Chroma client parameters are configured, improves the handling of document metadata, and updates the underlying ChromaDB client library to a newer version. These changes aim to provide a more robust, maintainable, and feature-rich Chroma vector store experience.

Highlights

  • Chroma Integration Refactor: The custom ChromaExtended class has been removed and its core functionality integrated into a new Chroma class. This new class now directly extends VectorStore from @langchain/core/vectorstores, aligning with Langchain's standard abstractions.
  • Updated Chroma Client Parameters: The handling of Chroma client configuration has been modernized. Instead of individual chromaApiKey, chromaTenant, and chromaDatabase properties, these are now consolidated within a clientParams object, allowing for more flexible configuration including host, port, ssl, tenant, and database. A dedicated chromaCloudAPIKey is used for cloud authentication headers.
  • Enhanced Metadata Handling: Document metadata processing has been improved, specifically for location information. loc.lines.from and loc.lines.to are now mapped to top-level locFrom and locTo properties when documents are added to Chroma, and then correctly re-mapped upon retrieval, ensuring better data consistency and structure.
  • ChromaDB Dependency Update: The chromadb dependency has been updated from version ^1.10.0 to 3.1.6, bringing in the latest features and fixes from the ChromaDB client library.
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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the Chroma vector store integration. It replaces the custom ChromaExtended class with a more complete, self-contained Chroma implementation in core.ts, which seems to be adapted from a newer version of LangChain's Chroma vector store. This change accommodates updates in the Chroma client API. The chromadb dependency version is also updated accordingly. The main node file Chroma.ts is updated to use the new core implementation and its connection parameter structure.

My review focuses on the maintainability of the new code. I've identified significant code duplication in Chroma.ts where the connection configuration object is built in three separate methods (upsert, delete, and init). I've recommended refactoring this into a single helper method to improve code quality and make future changes easier.

@HenryHengZJ HenryHengZJ merged commit b405c96 into main Nov 30, 2025
5 checks passed
@chungyau97 chungyau97 requested review from chungyau97 and removed request for chungyau97 December 1, 2025 10:33
davehamptonusa pushed a commit to davehamptonusa/Flowise that referenced this pull request Dec 8, 2025
* update chroma

* refactor Chroma configuration handling

* refactor Chroma configuration handling
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