Update gradio_exit.py

gradio_exit.py

@@ -1,26 +1,3 @@
-#https://stackoverflow.com/questions/75286784/how-do-i-gracefully-close-terminate-gradio-from-within-gradio-blocks
-#https://levelup.gitconnected.com/bringing-your-ai-models-to-life-an-introduction-to-gradio-ae051ca83edf
-#Bringing Your AI Models to Life: An Introduction to Gradio - How to demo your ML model quickly without any front-end hassle.
-#pipreqs . --encoding=utf-8
-
-#https://huggingface.co/blog/inference-endpoints
-#Getting Started with Hugging Face Inference Endpoints
-
-#https://www.gradio.app/guides/using-hugging-face-integrations
-Using Hugging Face Integrations
-
-#在app.py的根目录下cmd命令行窗口中运行：gradio deploy，将会出现如下提示：
-#To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .
-#Token can be pasted using 'Right-Click'.
-#Token:先将HF_API_TOKEN拷贝到剪贴板之后，邮件单击即可
-#Add token as git credential? (Y/n) n
-#Token is valid (permission: write).
-#Your token has been saved to C:\Users\lenovo\.cache\huggingface\token
-#Login successful
-#Creating new Spaces Repo in 'D:\ChatGPTApps\Gradio_HF_Apps'. Collecting metadata, press Enter to accept default value.
-#Enter Spaces app title [Gradio_HF_Apps]:
-
-
 import os
 import io
 import requests
@@ -33,22 +10,12 @@ from dotenv import load_dotenv, find_dotenv
 _ = load_dotenv(find_dotenv()) # read local .env file
 hf_api_key ="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"
 
-#model_id = "sentence-transformers/all-MiniLM-L6-v2"
 model_id = "shleifer/distilbart-cnn-12-6"
-#hf_token = "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"
 
-#ENDPOINT_URL='https://api-inference.huggingface.co/models/DunnBC22/flan-t5-base-text_summarization_data'
 api_url ='https://api-inference.huggingface.co/models/DunnBC22/flan-t5-base-text_summarization_data'
-#api_url = f"https://api-inference.huggingface.co/pipeline/feature-extraction/{model_id}"
-#pipeline的api-inference/Endpoint是对应于transformers（用于生成向量Embeddings）的！
-#headers = {"Authorization": f"Bearer {hf_token}"}
-headers = {"Authorization": f"Bearer {hf_api_key}"}
 
-#def query(texts):
-#    response = requests.post(api_url, headers=headers, json={"inputs": texts, "options":{"wait_for_model":True}})
-#    return response.json()
+headers = {"Authorization": f"Bearer {hf_api_key}"}
 
-#可以不使用ENDPOINT_URL，而是使用api_url（或者两个是一回事？）：https://huggingface.co/blog/getting-started-with-embeddings
 def get_completion(inputs, parameters=None, ENDPOINT_URL=api_url): 
     headers = {
       "Authorization": f"Bearer {hf_api_key}",
@@ -72,7 +39,7 @@ text = (
     '''He was undefeated in battle and is widely considered to be one of history's greatest and most successful military commanders.[3][4]'''
 )
 
-get_completion(text)   #api_url中的model_id = "sentence-transformers/all-MiniLM-L6-v2"时，返回的结果是浮点数（即向量Embeddings）
+get_completion(text) 
 
 import gradio as gr
 
@@ -89,9 +56,4 @@ demo = gr.Interface(fn=summarize,
                     description="Summarize any text using the `shleifer/distilbart-cnn-12-6` model under the hood!"
                    )
 
-#demo.launch(share=True, server_port=int(os.environ['PORT2']))
-#demo.launch(share=True)
-demo.launch()
-
-
-
+demo.launch()