File size: 1,779 Bytes
acc4ffe |
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 50 51 52 53 54 55 56 57 58 59 |
import gradio as gr
import numpy as np
import json
import os
import requests
header_key = os.environ["CVFIAHMED_KEY"]
def get_caption_onnx_api(imgf):
headers = {
'Content-Type': 'application/octet-stream',
'Ocp-Apim-Subscription-Key': header_key,
}
params = {
'features': 'description',
'model-version': 'latest',
'language': 'en',
'descriptionExclude': 'Celebrities,Landmarks',
}
with open(imgf, 'rb') as f:
data = f.read()
response = requests.post('https://cvfiahmed.cognitiveservices.azure.com/vision/v2022-07-31-preview/operations/imageanalysis:analyze', params=params, headers=headers, data=data)
return json.loads(response.content)['descriptionResult']['values'][0]['text']
def add_image(state, image):
cap_onnx = get_caption_onnx_api(image.name)
state = state + [(f"", cap_onnx)]
# print (image)
# print( np.fliplr(image) )
# print(state)
return state, state
def add_text(state, text):
state = state + [(text, text + "?")]
return state, state
with gr.Blocks(css="#chatbot .overflow-y-auto{height:500px}") as demo:
chatbot = gr.Chatbot(elem_id="chatbot")
state = gr.State([])
with gr.Row():
with gr.Column(scale=0.85):
txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter, or upload an image").style(container=False)
with gr.Column(scale=0.15, min_width=0):
btn = gr.UploadButton("Upload image here", file_types=["image", '.png', 'gif'])
txt.submit(add_text, [state, txt], [state, chatbot])
txt.submit(lambda :"", None, txt)
btn.upload(add_image, [state, btn], [state, chatbot])
demo.launch(share = False, server_name="0.0.0.0") |