Update app.py

app.py

@@ -1,33 +1,75 @@
+import os
 import gradio
-from transformers import pipeline
+from PIL import Image
+from timeit import default_timer as timer
+from tensorflow import keras
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+import numpy as np
 
 username = "runaksh"
 repo_name = "finetuned-sentiment-model"
 repo_path = username+ '/' + repo_name
-sentiment_model = pipeline(model= repo_path)
+model_1 = pipeline(model= repo_path)
+
+model_2 = AutoModelForSequenceClassification.from_pretrained("runaksh/Symptom-2-disease_distilBERT")
+tokenizer_2 = AutoTokenizer.from_pretrained("runaksh/Symptom-2-disease_distilBERT")
 
 # Function for response generation
 def predict_sentiment(text):
-    result = sentiment_model(text)
+    result = model_1(text)
     if result[0]['label'].endswith('0'):
         return 'Negative'
     else:
         return 'Positive'
 
+def predict(sample, validate=True):
+  classifier = pipeline("text-classification", model=model_2, tokenizer=tokenizer_2)
+  pred = classifier(sample)[0]['label']
+  return pred
+
 # Input from user
-in_prompt = gradio.components.Textbox(lines=10, placeholder=None, label='Enter review text')
+in_prompt_1 = gradio.components.Textbox(lines=10, placeholder=None, label='Enter review text')
 
 # Output response
-out_response = gradio.components.Textbox(type="text", label='Sentiment')
+out_response_1 = gradio.components.Textbox(type="text", label='Sentiment')
 
 # Gradio interface to generate UI link
-title = "Sentiment Classification"
-description = "Analyse sentiment of the given review"
+title_1 = "Sentiment Classification"
+description_1 = "Analyse sentiment of the given review"
+
+iface_1 = gradio.Interface(fn = predict_sentiment,
+                         inputs = [in_prompt_1],
+                         outputs = [out_response_1],
+                         title = title_1,
+                         description = description_1)
+
+title_2 = "Symptoms and Disease"
+description_2 = "Enter the Symptoms to know the disease"
+
+# Input from user
+in_prompt_2 = gradio.components.Textbox(lines=2, label='Enter the Symptoms')
+
+# Output response
+out_response_2 = gradio.components.Textbox(label='Disease')
+
+# Gradio interface to generate UI link
+iface_2 = gradio.Interface(fn=predict,
+                         inputs = in_prompt_2,
+                         outputs = out_response_2,
+                         title=title_2,
+                         description=description_2
+                         )
+
+combined_interface = gr.Interface(
+    [
+        iface_1,
+        iface_2
+    ],
+    title="Multiple Models Interface",
+    description="This interface showcases multiple models"
+)
 
-iface = gradio.Interface(fn = predict_sentiment,
-                         inputs = [in_prompt],
-                         outputs = [out_response],
-                         title = title,
-                         description = description)
+combined_interface.launch(debug = True)
 
-iface.launch(debug = True)#, server_name = "0.0.0.0", server_port = 8001) # Ref. for parameters: https://www.gradio.app/docs/interface
+#iface.launch(debug = True)#, server_name = "0.0.0.0", server_port = 8001) # Ref. for parameters: https://www.gradio.app/docs/interface