מריה די בי וקטור אדישן: מיועד ללמידת מכונה

# Pull the latest release

docker pull quay.io/mariadb-foundation/mariadb-devel:11.6-vector-preview

​

# Update password

docker run -d --name mariadb_vector -e MYSQL_ROOT_PASSWORD=<replace_password> quay.io/mariadb-foundation/mariadb-devel:11.6-vector-preview

​

import mysql.connector

import numpy as np

from sentence_transformers import SentenceTransformer

​

model = SentenceTransformer('paraphrase-MiniLM-L6-v2')

​

# I already have a database created with a name vectordb

connection = mysql.connector.connect(

        host="localhost",

        user="root",

        password="<password>", # Replace me

        database="vectordb"

    )

cursor = connection.cursor()

​

# Create a table to store customer reviews with sentiment score and embeddings.

cursor.execute("""

    CREATE TABLE IF NOT EXISTS customer_reviews (

            id INT PRIMARY KEY AUTO_INCREMENT,

            product_name INT,

            customer_review TEXT,

            customer_sentiment_score FLOAT,

            customer_review_embedding BLOB,

            INDEX vector_idx (customer_review_embedding) USING HNSW

    ) ENGINE=ColumnStore;

    """)

​

# Sample reviews

reviews = [

        (1, "This product exceeded my expectations. Highly recommended!", 0.9),

        (1, "Decent quality, but pricey.", 0.6),

        (2, "Terrible experience. The product does not work.", 0.1),

        (2, "Average product, ok ok", 0.5),

        (3, "Absolutely love it! Best purchase I have made this year.", 1.0)

    ]

​

# Load sample reviews into vector DB

for product_id, review_text, sentiment_score in reviews:

    embedding = model.encode(review_text)

    cursor.execute(

        "INSERT INTO customer_reviews (product_id, review_text, sentiment_score, review_embedding) VALUES (%s, %s, %s, %s)",

        (product_id, review_text, sentiment_score, embedding.tobytes()))

​

connection.commit()

connection.close()

# Convert the target customer review into vector

target_review_embedding = model.encode("I am super satisfied!")

​

# Find top 2 similar reviews using MariaDB's VEC_Distance_Euclidean function

cursor.execute("""

        SELECT review_text, sentiment_score, VEC_Distance_Euclidean(review_embedding, %s) AS similarity

        FROM customer_reviews

        ORDER BY similarity

        LIMIT %s

    """, (target_review_embedding.tobytes(), 2))

​

similar_reviews = cursor.fetchall()

​