Update app.py

app.py

@@ -1,64 +1,31 @@
-from azure.ai.textanalytics import TextAnalyticsClient
-from azure.core.credentials import AzureKeyCredential
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
-
-
-# Azure Text Analytics setup
-azure_endpoint = "https://t6langservice.cognitiveservices.azure.com/"
-azure_api_key = "3CU1gpUszvl7pLb90Ivdp1Kd5WZc56savzdXOK5GV40JHebnxnxoJQQJ99BAACYeBjFXJ3w3AAAaACOGkRT5"
-
-# Authenticate client
-text_analytics_client = TextAnalyticsClient(endpoint=azure_endpoint, credential=AzureKeyCredential(azure_api_key))
-
-
-# Load Hugging Face chatbot model
-model_name = "microsoft/DialoGPT-medium"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-chat_model = AutoModelForCausalLM.from_pretrained(model_name)
-
-
-
-
-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")
-     ],
-)
-
+from transformers import pipeline
+
+def load_model():
+    # Load a pre-trained HuggingFace pipeline for sentiment analysis
+    model_pipeline = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
+    return model_pipeline
+
+def classify_text(model, text):
+    # Use the loaded model to classify text
+    result = model(text)
+    return result
+
+def main():
+    # Load the model
+    model = load_model()
+
+    # Define the Gradio interface
+    interface = gr.Interface(
+        fn=lambda text: classify_text(model, text),
+        inputs=gr.Textbox(lines=2, placeholder="Enter Text Here..."),
+        outputs="json",
+        title="Text Classification with HuggingFace",
+        description="This interface uses a HuggingFace model to classify text sentiments. Enter a sentence to see its classification."
+    )
+
+    # Launch the Gradio app
+    interface.launch()
 
 if __name__ == "__main__":
-    demo.launch()
+    main()