Create app.py

app.py

@@ -0,0 +1,77 @@
+import os
+# Set up OpenAI API credentials
+import openai
+openai.api_key = "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"
+import gradio as gr
+
+def get_completion(prompt, model="gpt-3.5-turbo"):
+    messages = [{"role": "user", "content": prompt}]
+    response = openai.ChatCompletion.create(
+        model=model,
+        messages=messages,
+        temperature=0, # this is the degree of randomness of the model's output
+    )
+    return response.choices[0].message["content"]
+
+def choose_topic(prompt, model="gpt-3.5-turbo"):
+    messages = [{"role": "user", "content": prompt}]
+    response = openai.ChatCompletion.create(
+        model=model,
+        messages=messages,
+        temperature=0.9, # this is the degree of randomness of the model's output
+    )
+    return response.choices[0].message["content"]
+
+def generate_topic(aiquotient,response):
+  prompt_sum = f"""
+  Generate a question that evaluates the understanding of AI concepts of a person.  Ensure that the question challenges the {aiquotient} of the person and is connected to the response {response}. Limit it to at the max 20 words. Here are some examples:
+  What is reinforcement learning? How is it different from supervised and unsupervised learning?
+  What is the difference between a model and an algorithm?
+  Explain the concept of "overfitting" in machine learning and its potential impact on model performance.
+  Explain how natural language processing (NLP) is employed in virtual assistants like Siri or Alexa.
+  Explain how Uber uses Machine Learning with an example
+  How does ChatGPT work?
+  Describe the ethical implications of using AI in autonomous vehicles and potential biases in facial recognition systems.
+  What is Bias-Variance tradeoff?
+  What is the importance of p-value?
+  What are the assumptions under which Linear Regression works?
+  What are the limitations of K-Nearest Neighbors algorithm?
+"""
+
+  response_sum = choose_topic(prompt_sum)
+  return response_sum
+
+def evaluate(response):
+  prompt_sum = f"""
+  Imagine you are Alan Turing, the scientist who devised Turing test. Analyze the user's response {response} and figure out the question. Then identify areas of improvement, provide the ideal answer and calculate AI Quotient. 
+  Your response should be:
+  [AI Quotient, Areas of Improvement, Ideal Answer] 
+"""
+
+  response_sum = get_completion(prompt_sum)
+  return response_sum
+
+import gradio as gr
+def transcribe(audio):
+    print(audio)
+
+#   Whisper API
+
+    audio_file = open(audio, "rb")
+    transcript = openai.Audio.transcribe("whisper-1", audio_file)
+
+
+    print(transcript)
+    eval = evaluate(transcript)
+
+    return eval
+
+question = generate_topic(aiquotient=100,response='I am an expert in Machine Learning. Ask me a difficult question')
+
+inputs = gr.Audio(source="microphone", type="filepath",label=question)
+
+bot = gr.Interface(fn=transcribe, inputs=inputs, outputs="text", title="Ask Turing: Improve your AI Quotient",
+    description="This is a gradio app",
+    article="Visit aiquotient.app for more details")
+
+bot.launch()