Update app.py

app.py

@@ -14,25 +14,50 @@ text_analytics_client = TextAnalyticsClient(endpoint=azure_endpoint, credential=
 # Load Hugging Face chatbot model
 model_name = "microsoft/DialoGPT-medium"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+chat_model = AutoModelForCausalLM.from_pretrained(model_name)
 
-# Chatbot logic
-def chatbot_response(input_text):
-    # Hugging Face response
-    input_ids = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors="pt")
-    chat_output = model.generate(input_ids, max_length=50, pad_token_id=tokenizer.eos_token_id)
-    hf_response = tokenizer.decode(chat_output[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
 
-    # Azure Text Analytics: Analyze sentiment of user input
-    try:
-        response = text_analytics_client.analyze_sentiment([input_text])[0]
-        sentiment = response.sentiment
-        azure_analysis = f"The sentiment of your input is: {sentiment}."
-    except Exception as e:
-        azure_analysis = f"Error analyzing sentiment: {str(e)}"
 
-    # Combine responses
-    return f"Hugging Face response: {hf_response}\nAzure analysis: {azure_analysis}"
 
+print ("Defining funtion")
 
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens
+):
+    print ("Response: ")
 
+    messages = [{"role": "system", "content": system_message}]
+
+    messages.append({"role": "user", "content": message})
+
+    print ("Getting response", messages)
+
+    # response = chat_model(messages)
+
+    response = text_analytics_client.analyze_sentiment([messages])[0]
+
+
+    print ("Got response", response)
+
+    return response[-1]['generated_text'][-1]['content']
+
+
+
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
+     ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()