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

Updated 3 years ago

ann-search

Operator: ANN Search: Faiss

author: shiyu


Desription

Search embedding in Faiss, please make sure you have inserted data to Faiss before search.


Code Example

Insert data into Faiss first

import numpy as np
import towhee

vec = np.random.random((10, 100)).astype('float32')
ids = list(i for i in range(10))

x = towhee.dc['id'](ids) \
    .runas_op['id', 'vec'](func=lambda x: vec[x]) \
    .to_faiss['id', 'vec'](findex='index.bin')

Example

Write the pipeline in simplified style:

query = vec[0:2]
towhee.dc(query) \
    .ann_search.faiss(findex='index.bin')

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

query = vec[0:2]
towhee.dc['vec'](query) \
    .ann_search.faiss['vec', 'results'](findex='index.bin') \
    .show()


Factory Constructor

Create the operator via the following factory method:

ann_search.faiss(findex)


Parameters:

findex: str or faiss.INDEX

The path to faiss index file or faiss index.


Interface

Parameters:

query: list

Query embeddings in Faiss


Returns: Entity

Return the results in Faiss with key and score.

shiyu22 914cb2ffec Update README 4 Commits
file-icon .gitattributes
1.1 KiB
download-icon
Initial commit 3 years ago
file-icon README.md
1.3 KiB
download-icon
Update README 3 years ago
file-icon __init__.py
87 B
download-icon
Add ann_search.faiss 3 years ago
file-icon faiss.py
2.0 KiB
download-icon
Add ann_search.faiss 3 years ago
file-icon requirements.txt
22 B
download-icon
Add ann_search.faiss 3 years ago
file-icon result.png
56 KiB
download-icon
Add ann_search.faiss 3 years ago