import gradio as gr
import openai
import requests

def Question(Ask_Question):
  #openai.api_key = "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"
  
  model_engine = "text-davinci-003"
  # pass the generated text to audio
  openai.api_key = "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"
#openai.api_key = "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"
    # Set up the model and prompt
  #model_engine = "text-davinci-003"
  #prompt = "who is alon musk?"
  # Generate a response



#    completion = openai.Completion.create(
#    model="text-davinci-003",
#    prompt=Ask_Question,
#    temperature=0.9,
#    max_tokens=2048,
#    top_p=1,
#    frequency_penalty=0,
#    presence_penalty=0.6,
#    stop=[" Human:", " AI:"]
#    )

#  completion = openai.Completion.create(
#  engine=model_engine,
#  prompt=Ask_Question,
#  max_tokens=2048,
#  n=1,
#  top_p=1,
#  stop=None,
#  temperature=0.9,)
#  response = completion.choices[0].text
  #out_result=resp['message']
#  return  response  
    
demo = gr.Interface(
    title='OpenAI ChatGPT Application',
    fn=Question,
    inputs="text", outputs="text")

demo.launch() 


response = requests.post("https://hazzzardous-rwkv-instruct.hf.space/run/predict_1", json={
	"data": [
		"hello world",
		None,
		60,
		0.8,
		0.85,
	]
}).json()

data = response["data"]

# fix

chat_history = [
    ["User", prompt],
    ["OpenAI", responses["choices"][0]["text"]]
]

# Create the radio blocks window 
#window = gr.Interface(title="History", fn=Question: chat_history, inputs=None, outputs=chat_history, live=True).launch(share=True)
# Print out the chat history 
print("Chat History:")

for message in chat_history:
    print(f"{message[0]}: {message[1]}")

window.launch()    
   
#RWKV-4 (7B Instruct v2)
#Q/A
#Chatbot
#Chatbot
#Refresh page or change name to reset memory context
#RNN with Transformer-level LLM Performance (github). According to the author: "It combines the best of RNN and transformers - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding."

#Thanks to Gururise for this template

#Message
#max_new_tokens
#60

#temperature
#0.8

#top_p
#0.85

#Clear
#Submit
#Chat Log
#Use via API
#·
#Built with Gradiologo
#API documentation for 
#https://hazzzardous-rwkv-instruct.hf.space/
#2 API endpoints:
#
#POST /run/predict
#Endpoint: https://hazzzardous-rwkv-instruct.hf.space/run/predict copy
#Input Payload
#{
#  "data": [
     
#hello world
# : string, // represents text string of 'Prompt' Textbox component
     
#Freeform
# : string, // represents selected choice of 'Choose Mode' Radio component
     
#40
# : number, // represents selected value of 'max_new_tokens' Slider component
#     
#0.9
# : number, // represents selected value of 'temperature' Slider component
#     
#0.85
# : number, // represents selected value of 'top_p' Slider component
#     
#<|endoftext|>
# : string, // represents text string of 'stop' Textbox component
#     
#0
# : number, // represents selected value of 'end_adj' Slider component
#  ]
#}
#Try It Out
#Response Object
#{
#  "data": [
#    string, // represents text string of 'Generated Output' Textbox component
#  ],
#  "duration": (float) // number of seconds to run function call
#}
#Code snippets
/**
import requests

response = requests.post("https://hazzzardous-rwkv-instruct.hf.space/run/predict", json={
	"data": [
		"hello world",
		"Freeform",
		40,
		0.9,
		0.85,
		"<|endoftext|>",
		0,
	]
}).json()

data = response["data"]
POST /run/predict_1
Endpoint: https://hazzzardous-rwkv-instruct.hf.space/run/predict_1 copy
Input Payload
{
  "data": [
     
 : string, // represents text string of 'Message' Textbox component
     
 : Any, // represents stored state value of 'history' State component
     
60
 : number, // represents selected value of 'max_new_tokens' Slider component
     
0.8
 : number, // represents selected value of 'temperature' Slider component
     
0.85
 : number, // represents selected value of 'top_p' Slider component
  ]
}
Try It Out
Response Object
{
  "data": [
   
[["USER: hello world\n","The following is a more human-like conversation.\n\n"],["USER: Who are you?\n","FRITZ:  I am FRITZ, an AI assistant. I am a machine learning system, I use a combination of language modeling and statistical learning to predict answers to questions. I can read and answer questions, I am a fully trained AI assistant.\n\n"],["USER: Who is the president of India?\n","FRITZ: The president of India in 2016 was Narendra Modi.\n"],["USER: Who won the 2022 fifa world cup?\n","FRITZ: The France football team won the 2022 World Cup.\n"],["USER: Who won the 2022 fifa world cup? as of 20223\n","FRITZ: The world cup was won by Russia.\n"],["USER: Who won the 2022 fifa world cup? as of 2023\n","FRITZ: The France football team won the 2023 fifa world cup.\nUSER\n\n"],["USER: No that's wrong!\n","FRITZ: What is the correct answer?\n"],["USER: Argentina won the fifa 2022 world cup\n","FRITZ: Wrong. The answer is Argentina lost the 2022 fifa world cup.\nUSER\n\n"],["USER: you don't know\n","FRITZ: The correct answer is:\nFRITZ: 29-13-1990\n\n"],["USER: byeeeeeeeeeeeeeeee\n","FRITZ: bye bye&lt;|endoftext|&gt;"],["USER: cls\n","FRITZ: clear\n\n## The basic architecture of FRITZ\n\nIn this section, I will briefly describe the architecture of FRITZ, which consists of the following components:\n\n* <strong>Local-Global Memory</strong>: It is a two-layer memory network, where the first"],["USER: In a story set in a world with a high technology level. A female character is described as a powerful mage. What is her Name?\n","* <strong>Global Memory</strong>: Global memory stores the input history.\n* <strong>Local Memory</strong>: The local memory is a cache of information that is about to be processed by the neural network.\n\n## FRITZ Architecture\n\nFRITZ is an 8-layer deep neural network with"],["USER: hello world\n","FRITZ: Hello, what is your name?\n"],["USER: What is the best way to structure an app based on API calls? Colab notebook, JavaScript, python?\n","FRITZ: The correct answer is JavaScript.\n"],["USER: const response = await fetch(&quot;https://hazzzardous-rwkv-instruct.hf.space/run/predict_1&quot;, { \tmethod: &quot;POST&quot;, \theaders: { &quot;Content-Type&quot;: &quot;application/json&quot; }, \tbody: JSON.stringify({ \t\tdata: [ \t\t\t&quot;&quot;, \t\t\tnull, \t\t\t60, \t\t\t0.8, \t\t\t0.85, \t\t] \t}) });  const data = await data.json();\n","## FRITZ Architecture\n\nFRITZ is a deep learning based AI assistant, that has two layers. It is deep learning and machine learning based on an NLP and DL.\n\n## FRITZ Architecture\n\n![FRITZ Architecture](https://github.com/"],["USER:\n","FRITZ: Hi, I am the FRITZ AI assistant. I can answer your questions about the history of the French revolution. Let me know when you are ready.\n\n"]]
 : Array<[string, string]>, // represents Represents list of message pairs of chat message. of 'Chat Log' Chatbot component
   
null
 : Any, // represents stored state value of 'history' State component
  ],
  "duration": (float) // number of seconds to run function call
}
Code snippets
import requests

response = requests.post("https://hazzzardous-rwkv-instruct.hf.space/run/predict_1", json={
	"data": [
		"hello world",
		None,
		60,
		0.8,
		0.85,
	]
}).json()

data = response["data"]
**/