Milvus-model

What's Changed
* Use onnx as default embedding function.
* Decouple model dependencies, installing them as needed.


**Full Changelog**: https://github.com/milvus-io/milvus-model/compare/v0.2.1...v0.2.2

What's Changed
* Fix BGERerankFunction call return type. by muazhari in https://github.com/milvus-io/milvus-model/pull/14
* feat: add JinaAI embedding and reranker models by JoanFM in https://github.com/milvus-io/milvus-model/pull/16
* Bugfixes by wxywb in https://github.com/milvus-io/milvus-model/pull/18
- Fix loading bm25 config on Windows.
- Convert sparse model output to csr_array explicitly.
- Upgrade protobuf version to 3.20.2.
* feat: Change BGE M3 to use float32 as return by default. by wxywb in https://github.com/milvus-io/milvus-model/pull/19

New Contributors
* muazhari made their first contribution in https://github.com/milvus-io/milvus-model/pull/14
* JoanFM made their first contribution in https://github.com/milvus-io/milvus-model/pull/16

**Full Changelog**: https://github.com/milvus-io/milvus-model/compare/v0.2.0...v0.2.1

What's Changed
* Add several rerankers to improve search accuracy and relevance.
**BGERerankFunction**
**CohereRerankFunction**
**CrossEncoderRerankFunction**
**VoyageRerankFunction**
* BGEM3EmbeddingFunction now can load the local model from folder path.
* Optimize SpladeEmbeddingFunction implementation and reduce memory footprint when inferencing.


**Full Changelog**: https://github.com/milvus-io/milvus-model/compare/v0.1.0...0.2.0