Snowflake#

Platform V Vector DB (далее - Vector DB) поддерживает работу с моделями вложения текста от Snowflake. Все доступные модели можно найти на сайте HuggingFace.

Настройка Vector DB и моделей Snowflake#

from qdrant_client import QdrantClient
from fastembed import TextEmbedding

qclient = QdrantClient(":memory:")
embedding_model = TextEmbedding("snowflake/snowflake-arctic-embed-s")

texts = [
    "Qdrant is the best vector search engine!",
    "Loved by Enterprises and everyone building for low latency, high performance, and scale.",
]

import {QdrantClient} from '@qdrant/js-client-rest';
import { pipeline } from '@xenova/transformers';

const client = new QdrantClient({ url: 'http://localhost:6333' });

const extractor = await pipeline('feature-extraction', 'Snowflake/snowflake-arctic-embed-s');

const texts = [
    "Qdrant is the best vector search engine!",
    "Loved by Enterprises and everyone building for low latency, high performance, and scale.",
]

Следующий пример показывает, как внедрять документы с помощью модели snowflake-arctic-embed-s, которая генерирует векторные представления предложений размером 384.

Вложение документов#

embeddings = embedding_model.embed(texts)

const embeddings = await extractor(texts, { normalize: true, pooling: 'cls' });

Преобразование выходных данных модели в точки Vector DB#

from qdrant_client.models import PointStruct

points = [
    PointStruct(
        id=idx,
        vector=embedding,
        payload={"text": text},
    )
    for idx, (embedding, text) in enumerate(zip(embeddings, texts))
]

let points = embeddings.tolist().map((embedding, i) => {
    return {
        id: i,
        vector: embedding,
        payload: {
            text: texts[i]
        }
    }
});

Создание коллекции для вставки документов#

from qdrant_client.models import VectorParams, Distance

COLLECTION_NAME = "example_collection"

qclient.create_collection(
    COLLECTION_NAME,
    vectors_config=VectorParams(
        size=384,
        distance=Distance.COSINE,
    ),
)
qclient.upsert(COLLECTION_NAME, points)

const COLLECTION_NAME = "example_collection"

await client.createCollection(COLLECTION_NAME, {
    vectors: {
        size: 384,
        distance: 'Cosine',
    }
});

await client.upsert(COLLECTION_NAME, {
    wait: true,
    points
});

Поиск документов с использованием Vector DB#

После добавления документов можно искать наиболее релевантные из них.

query_embedding = next(embedding_model.query_embed("What is the best to use for vector search scaling?"))

qclient.search(
    collection_name=COLLECTION_NAME,
    query_vector=query_embedding,
)

const query_embedding = await extractor("What is the best to use for vector search scaling?", {
    normalize: true,
    pooling: 'cls'
});

await client.search(COLLECTION_NAME, {
    vector: query_embedding.tolist()[0],
});