feat: Add Apache Doris vector store support

[dataroaring]

This commit adds Apache Doris as a new vector database option for Dify's RAG system.

Features:

• Vector similarity search using cosine distance
• Full-text search with BM25 scoring and inverted indexes
• Hybrid search combining vector and text search
• High-performance bulk data loading via StreamLoad
• Connection pooling for efficient resource management
• Support for multi-tenant isolation

Components added:

• DorisVector: Main vector database implementation with cleaned code
• DorisConfig: Configuration model with validation
• DorisConnectionPool: Thread-safe connection management
• DorisVectorFactory: Factory for creating Doris instances
• DORIS_SETUP.md: Complete setup guide in English

Important

1. Make sure you have read our contribution guidelines
2. Ensure there is an associated issue and you have been assigned to it
3. Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

Screenshots

Before	After
...	...

Checklist

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[gemini-code-assist]

Summary of Changes

Hello @dataroaring, 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 integrates Apache Doris as a new vector database option within the Dify RAG system. This enhancement provides Dify users with an additional robust and scalable solution for managing and querying document embeddings, supporting advanced search functionalities like vector similarity, full-text, and hybrid search. The implementation focuses on performance and ease of configuration, leveraging Doris's native capabilities for efficient data handling.

Highlights

• Apache Doris Integration: Adds Apache Doris as a new vector database option for Dify's RAG system, expanding the supported vector store ecosystem.
• Vector Similarity Search: Implements vector similarity search using cosine distance, enabling semantic retrieval of documents.
• Full-Text Search: Supports full-text search with BM25 scoring and inverted indexes, allowing for keyword-based document retrieval.
• Hybrid Search Capabilities: Enables combining both vector and text search for more comprehensive and relevant results.
• Efficient Data Loading: Utilizes Apache Doris's StreamLoad HTTP API for high-performance bulk data insertion, optimizing the indexing process.
• Connection Management: Includes a thread-safe connection pool for managing database connections, ensuring efficient resource handling and scalability.
• Comprehensive Configuration and Setup: Introduces a dedicated configuration model (DorisVectorConfig) and a detailed setup guide (DORIS_SETUP.md) for easy integration and deployment.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 introduces support for Apache Doris as a vector store, which is a significant feature addition. The implementation is well-structured, covering vector search, full-text search, and efficient data loading via StreamLoad. I've provided several suggestions to improve configurability, documentation clarity, and the robustness of the implementation, particularly around Doris-specific settings and the StreamLoad process. Addressing these points will make the integration more flexible and reliable for users with different Doris setups.

[Copilot]

Pull request overview

This PR adds Apache Doris as a new vector database option for Dify's RAG system, enabling vector similarity search, full-text search with BM25 scoring, and hybrid search capabilities. The implementation uses StreamLoad for high-performance bulk data loading and includes connection pooling for efficient resource management.

Key Changes:

• New DorisVector implementation with vector and full-text search capabilities
• Configuration model with connection pooling support
• Integration with existing vector factory pattern and database configuration system

Reviewed changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 11 comments.

Show a summary per file

File	Description
api/core/rag/datasource/vdb/vector_type.py	Added DORIS enum value to VectorType
api/core/rag/datasource/vdb/vector_factory.py	Added case for DORIS in vector factory switch statement
api/core/rag/datasource/vdb/doris/doris_vector.py	Main implementation including DorisVector class, DorisConfig, DorisConnectionPool, and DorisVectorFactory
api/core/rag/datasource/vdb/doris/__init__.py	Module exports for Doris vector database components
api/configs/middleware/vdb/doris_config.py	Pydantic configuration settings for Doris connection parameters
api/configs/middleware/__init__.py	Integrated DorisVectorConfig into middleware and added 'doris' as DB_TYPE option
DORIS_SETUP.md	Comprehensive setup guide with configuration examples and troubleshooting

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[crazywoola]

Please fix the errors in the lint and add the tests for this PR accordingly :)

[crazywoola]

Please click Resolve if you think those comments are not necessary.

[dataroaring]

Please fix the errors in the lint and add the tests for this PR accordingly :)

done