Perplexity: Embed V1 0.6Bembedding

Описание

pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency...

Модальности

Характеристики

API и примеры кода

from openai import OpenAI

client = OpenAI(
    base_url="https://infergate.ru/api/v1",
    api_key="ig-•••",
)

resp = client.embeddings.create(
    model="perplexity/pplx-embed-v1-0.6b",
    input="Текст для векторизации",
)
print(resp.data[0].embedding[:8])

Поддерживаемые параметры запроса