logo
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Readme
Files and versions

76 lines
1.0 KiB

# ANN Search Operator: Faiss
3 years ago
*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(findex='index.bin')) \
.map('rows', ('id', 'score'), lambda x: (x[0], x[1], x[2])) \
.output('id', 'score')
p(<your-vector>)
```
<br />
## Factory Constructor
Create the operator via the following factory method:
***ann_search.faiss(findex)***
<br />
**Parameters:**
***findex:*** *str* or *faiss.INDEX*
The path to faiss index file or faiss index.
<br />
## Interface
**Parameters:**
***query:*** *list*
Query embeddings in Faiss
<br />
**Returns:** *Entity*
Return the results in Faiss with `key` and `score`.