Tagline

Text Embeddings

Enhance your semantic search capabilities

Book a Demo

Faster Searches

Use output tensors for quicker, more efficient semantic searches

LLM Search

Improve Language Model related search tasks with precise text embeddings

Token Management

Manage token limitations for context windows effectively, optimizing your processes

Getting Started

Input a string I'd like to use to search later, after inputting it into your vector database.

API Integration

Want to use this via API? Sign up here to get your API token and Account ID! Try out the following code examples to get this model integrated into your app quickly:

Run via CURL

curl --location --request POST 'https://predict.pyqai.com/' --header 'Authorization: <YOUR API TOKEN HERE>' --header 'Content-Type: application/json' --data-raw '{"model": "136", "version": "451", "account": "<YOUR ACCOUNT ID HERE>", "input_sequence": "Your input goes here", "candidate_labels": ["a class","another class"]}'


import requests
import json

headers = { 'Authorization': "",'Content-Type': 'application/json'}
json_input = { "model": 136, "version": 451, "account": ,"input_sequence": "Your input goes here", "candidate_labels": ["a class","another class"]}
url = "https://predict.pyqai.com"

response = requests.post(headers=headers, json = json_input, url = url )
print(json.loads(response.content))


var myHeaders = new Headers();
myHeaders.append("Authorization", "");
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
  "model": 136,
  "version": 451,
  "account": ,
  "input_sequence": "Your input here",
  "candidate_labels": [
    "a category",
    "another category"
  ]
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

fetch("https://predict.pyqai.com", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

Reach out to us to get started with this model.

Click here to onboard