Perplexity: Embed V1 0.6B perplexity/pplx-embed-v1-0.6b

О модели Perplexity: Embed V1 0.6B

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...

Использование Perplexity: Embed V1 0.6B через НейроГейт

OpenAI-совместимый эндпоинт https://api.neuralgate.ru/v1 — замени base_url в любом SDK и используй модель по её id.

# Chat completion
curl https://api.neuralgate.ru/v1/chat/completions \
  -H "Authorization: Bearer $NEURALGATE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perplexity/pplx-embed-v1-0.6b",
    "messages": [{"role":"user","content":"Привет!"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="sk-...your-neuralgate-key...",
    base_url="https://api.neuralgate.ru/v1",
)
response = client.chat.completions.create(
    model="perplexity/pplx-embed-v1-0.6b",
    messages=[{"role": "user", "content": "Привет!"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.NEURALGATE_API_KEY,
  baseURL: "https://api.neuralgate.ru/v1",
});
const resp = await client.chat.completions.create({
  model: "perplexity/pplx-embed-v1-0.6b",
  messages: [{ role: "user", content: "Привет!" }],
});
console.log(resp.choices[0].message.content);

Похожие модели

Сравнить Perplexity: Embed V1 0.6B с другими

Кейсы использования

Где Perplexity: Embed V1 0.6B часто применяется: