ModelEngine-Group / ModelEngine-Group/nexent
Proposal: optional Milvus backend for VectorDatabaseCore
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5.9k
- Forks
- 731
- Avg merge
- 19h 34m
- Merged PRs (30d)
- 172
Description
Hi maintainers,
I noticed the Nexent SDK has a VectorDatabaseCore abstraction and documentation/comments indicating multiple backend possibilities, including Milvus. The current public wiring appears to expose Elasticsearch / DataMate paths, while Milvus is not yet available as a selectable backend.
Would you be open to adding Milvus as an optional vector database backend under the existing VectorDatabaseCore direction?
A possible scoped approach:
- Keep the current Elasticsearch / DataMate behavior unchanged.
- Clarify the backend selection surface for vector database implementations.
- Add a Milvus implementation behind an optional dependency and config value.
- Support Milvus Lite for local development and Milvus server / Zilliz Cloud for production deployments.
- Add focused SDK tests for create/upsert/search/delete behavior without requiring the full application stack.
This seems aligned with the existing vector database abstraction, but I wanted to confirm the preferred route before proposing code. Would this fit Nexent's roadmap?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Locate the VectorDatabaseCore abstraction and current Elasticsearch/DataMate wiring first. Then review how backend selection, optional dependencies, and configuration are represented. Done means a selectable optional Milvus path with Milvus Lite and server/Zilliz Cloud support, plus focused SDK tests for create, upsert, search, and delete without the full application stack.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- databases
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100