https://github.com/milvus-io/milvus-model
A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.
https://github.com/milvus-io/milvus-model
ai embedding nlp rag reranker
Last synced: 3 months ago
JSON representation
A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.
- Host: GitHub
- URL: https://github.com/milvus-io/milvus-model
- Owner: milvus-io
- License: apache-2.0
- Created: 2024-03-19T11:29:57.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-31T08:45:02.000Z (6 months ago)
- Last Synced: 2025-06-07T15:49:13.638Z (4 months ago)
- Topics: ai, embedding, nlp, rag, reranker
- Language: Python
- Homepage: https://milvus.io/docs/embeddings.md
- Size: 127 KB
- Stars: 42
- Watchers: 11
- Forks: 27
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Milvus Model Lib
The `milvus-model` library provides the integration with common embedding and reranker models for Milvus, a high performance open-source vector database built for AI applications. `milvus-model` lib is included as a dependency in `pymilvus`, the Python SDK of Milvus.
`milvus-model` supports embedding and reranker models from service providers like OpenAI, Voyage AI, Cohere, and open-source models through SentenceTransformers or Hugging Face [Text Embeddings Inference (TEI)](https://github.com/huggingface/text-embeddings-inference) .
`milvus-model` supports Python 3.8 and above.
## Installation
If you use `pymilvus`, you can install `milvus-model` through its alias `pymilvus[model]`:
```bash
pip install pymilvus[model]
# or pip install "pymilvus[model]" for zsh.
```
You can also install it directly:
```bash
pip install pymilvus.model
```
To upgrade milvus-model to the latest version, use:
```
pip install pymilvus.model --upgrade
```
If milvus-model was initially installed as part of the PyMilvus optional components, you should also upgrade PyMilvus to ensure compatibility. This can be done with:
```
pip install pymilvus[model] --upgrade
```
If you need to install a specific version of milvus-model, specify the version number:
```bash
pip install pymilvus.model==0.3.0
```
This command installs version 0.3.0 of milvus-model.