EmbedInDB

Embedin - memberdayakan AI dengan ingatan yang gigih

EmpedIn adalah basis data vektor sumber terbuka dan perpustakaan yang efisien yang secara mulus mengubah basis data populer seperti MySQL, PostgreSQL, dan MS SQL Server menjadi database vektor dengan upaya nol.

Embedin adalah solusi ideal untuk aplikasi AI seperti pemrosesan bahasa alami, pengenalan gambar, dan sistem rekomendasi, menawarkan pengindeksan dan pengambilan cepat. Bahasa API dan permintaannya yang sederhana memastikan kemudahan penggunaan dan integrasi yang mulus.

Persyaratan minimum

Python 3.7 atau lebih tinggi.

Instalasi

pip install embedin

Awal yang cepat

Simpan embeddings dalam memori

 from embedin import Embedin

client = Embedin ( collection_name = "test_collection" , texts = [ "This is a test" , "Hello world!" ])
result = client . query ( "These are tests" , top_k = 1 )  # Query the most similar text from the collection
print ( result )

Simpan embeddings di sqlite

 from embedin import Embedin

url = 'sqlite:///test.db'
client = Embedin ( collection_name = "test_collection" , texts = [ "This is a test" , "Hello world!" ], url = url )
result = client . query ( "These are tests" , top_k = 1 )

Simpan Embeddings di PostgreSQL

Mulai Wadah Docker PostgreSQL

 cd docker
docker-compose up embedin-postgres

contoh

 import os

from embedin import Embedin

url = os . getenv ( 'EMBEDIN_POSGRES_URL' , "postgresql+psycopg2://embedin:embedin@localhost/embedin_db" )
client = Embedin ( collection_name = "test_collection" , texts = [ "This is a test" , "Hello world!" ], url = url )
result = client . query ( "These are tests" , top_k = 1 )

Simpan embeddings di mysql

Mulai wadah Docker MySQL

 cd docker
docker-compose up embedin-mysql

contoh

 import os

from embedin import Embedin

url = os . getenv ( 'EMBEDIN_MYSQL_URL' , "mysql+pymysql://embedin:embedin@localhost/embedin_db" )
client = Embedin ( collection_name = "test_collection" , texts = [ "This is a test" , "Hello world!" ], url = url )
result = client . query ( "These are tests" , top_k = 1 )

Simpan Embeddings di SQL Server

Mulai Kontainer Docker SQL Server

 cd docker
docker-compose up embedin-mssql

contoh

 import os

from embedin import Embedin

url = os . getenv ( 'EMBEDIN_MSSQL_URL' , "mssql+pymssql://sa:StrongPassword123@localhost/tempdb" )
client = Embedin ( collection_name = "test_collection" , url = url )
client . add_data ( texts = [ "This is a test" ], meta_data = [{ "source" : "abc4" }])
result = client . query ( "These are tests" , top_k = 1 )

Lebih banyak referensi

• Referensi API

Menyumbang

Silakan merujuk panduan kontributor

Todo

• Uji unit gagal pada indeks FAISS (Kesalahan Segmentasi)