File size: 1,547 Bytes
5b4f208 4cc6483 5b4f208 bc8b062 5b4f208 6c07832 5b4f208 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
import gradio as gr
import requests
import json
import os
API_KEY = os.getenv('API_KEY')
headers = {
"Authorization": f"Bearer {API_KEY}",
"Accept": "application/json",
}
def generate_embedding(input_text, model_type, encoding_format):
invoke_url = "https://api.nvcf.nvidia.com/v2/nvcf/pexec/functions/091a03bb-7364-4087-8090-bd71e9277520"
payload = {
"input": input_text,
"model": model_type,
"encoding_format": encoding_format
}
session = requests.Session()
response = session.post(invoke_url, headers=headers, json=payload)
while response.status_code == 202:
request_id = response.headers.get("NVCF-REQID")
fetch_url = "https://api.nvcf.nvidia.com/v2/nvcf/pexec/status/" + request_id
response = session.get(fetch_url, headers=headers)
response.raise_for_status()
response_body = response.json()
embedding = response_body["data"][0]["embedding"]
return json.dumps(embedding, indent=2)
# Criação da interface Gradio
iface = gr.Interface(
fn=generate_embedding,
inputs=[
gr.Textbox(label="Input Text"),
gr.Radio(choices=["query", "passage"], value="query", label="Model Type"),
gr.Radio(choices=["float", "base64"], value="float", label="Encoding Format")
],
outputs=[gr.Textbox(label="Embedding")],
title="NVIDIA Retrieval QA Embedding Generator",
description="Generate embeddings for your text using NVIDIA's Retrieval QA Embedding model."
)
# Executar a aplicação Gradio
iface.launch()
|