# ANN Insert Operator: Milvus

*author: shiyu*

<br />



## Desription

Insert data into Milvus collections. **Please make sure you have [created Milvus Collection](https://milvus.io/docs/v2.0.x/create_collection.md) before loading the data.**

<br />



## Code Example

### Example

*Write the pipeline in simplified style:*

```python
import towhee

towhee.dc(your_embeddings) \
    .ann_insert.milvus(uri='tcp://<milvus-host>:<milvus-port>/<collection-name>')
```

*Write a same pipeline with explicit inputs/outputs name specifications:*

```python
import towhee

towhee.dc['vec'](your_embeddings) \
    .ann_insert.milvus['vec', 'results'](uri='tcp://<milvus-host>:<milvus-port>/<collection-name>') \
    .show()
```

<img src="./result.png" height="150px"/>

### Load Collection

> Please load the Collection after inserted data.

```python
collection.load()
```

<br />



## Factory Constructor

Create the operator via the following factory method:

***ann_insert.milvus(collection)***

<br />




**Parameters:**

***uri:*** *str*

The uri for Milvus Collection, such as `tcp://<milvus-host>:<milvus-port>/<collection-name>`.


<br />



## Interface

**Parameters:**

***data:*** *list*

The embedding data to be inserted.

<br />



**Returns:** *mr*

Return milvus results with `milvus.insert`.


# More Resources

- [Introducing Milvus 2.3.4 - Zilliz blog](https://zilliz.com/blog/what-is-new-in-milvus-2-3-4): Introducing Milvus 2.3.4 with the support for Access Logs, Parquet File imports, expanded collections/partitions, and more!
- [Milvus vs Pgvector | Zilliz](https://zilliz.com/comparison/milvus-vs-pgvector): Compare Milvus vs. Pgvector by the following set of capabilities. We want you to choose the best database for you, even if it’s not us.
- [Optimizing Data Communication: Milvus Embraces NATS Messaging - Zilliz blog](https://zilliz.com/blog/optimizing-data-communication-milvus-embraces-nats-messaging): Introducing the integration of NATS and Milvus, exploring its features, setup and migration process, and performance testing results.
- [Milvus | Open-source Vector Databse created by Zilliz](https://zilliz.com/what-is-milvus): Milvus, built by the Zilliz team, is a high-performance open-source vector database designed to handle billions of vectors for AI applications.
- [An Engineering Perspective: Why Milvus is Compelling for Your Apps?  - Zilliz blog](https://zilliz.com/blog/engineering-perspective-why-milvus-compelling-option-for-apps): Explore Milvus 2.3 from three crucial angles: database selection, development experience, and system reliability.
- [Spring AI and Milvus: Using Milvus as a Spring AI Vector Store - Zilliz blog](https://zilliz.com/blog/spring-ai-and-milvus-using-milvus-as-spring-ai-vector-store): A comprehensive guide on how to use Milvus as a Spring AI vector store