faiss-index/README.md

# ANN Search Operator: Faiss

*author: shiyu*

<br />



## Desription

Search embedding in [Faiss](https://github.com/facebookresearch/faiss), **please make sure you have inserted data to Faiss before search**.

<br />



## Code Example

> please insert data into faiss first.

### Example

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

```python
from towhee.dc2 import pipe, ops

p = pipe.input('vec')  \
    .flat_map('vec', 'rows', ops.ann_search.faiss('./data_dir', 5))  \
    .map('rows', ('id', 'score'), lambda x: (x[0], x[1]))  \
    .output('id', 'score')

p(<your-vector>)
```

<br />



## Factory Constructor

Create the operator via the following factory method:

***ops.ann_search.faiss_index('./data_dir', 5)***

<br />



**Parameters:**

***data_dir:*** *str*

The path to faiss index and meta data.


<br />



## Interface

**Parameters:**

***query:*** *ndarray*

Query embedding in Faiss

<br />



**Returns:** *Entity*

Return the results in Faiss with `key` and `score`.