Create app_functions.py

app_functions.py

@@ -1,3 +1,4 @@
+# app_functions.py
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 def Get_DialoGPT_Response(input_text, no_words, user_type):
@@ -13,3 +14,31 @@ def Get_DialoGPT_Response(input_text, no_words, user_type):
         return response
     except Exception as e:
         return f"Error during DialoGPT model execution: {str(e)}"
+
+def Get_DistilGPT_Response(input_text, no_words, user_type):
+    model_name = "Rabbiaaa/DistilGPT"
+    try:
+        tokenizer = AutoTokenizer.from_pretrained(model_name)
+        model = AutoModelForCausalLM.from_pretrained(model_name)
+
+        prompt = f"Give an answer for {user_type} of the text given that is '{input_text}' within {no_words} words."
+        inputs = tokenizer(prompt, return_tensors="pt")
+        outputs = model.generate(inputs["input_ids"], max_new_tokens=int(no_words), do_sample=True, top_k=50)
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return response
+    except Exception as e:
+        return f"Error during DistilGPT model execution: {str(e)}"
+
+def Get_MedGPT_Response(input_text, no_words, user_type):
+    model_name = "Rabbiaaa/MedGPT"
+    try:
+        tokenizer = AutoTokenizer.from_pretrained(model_name)
+        model = AutoModelForCausalLM.from_pretrained(model_name)
+
+        prompt = f"Give an answer for {user_type} of the text given that is '{input_text}' within {no_words} words."
+        inputs = tokenizer(prompt, return_tensors="pt")
+        outputs = model.generate(inputs["input_ids"], max_new_tokens=int(no_words), do_sample=True, top_k=50)
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return response
+    except Exception as e:
+        return f"Error during MedGPT model execution: {str(e)}"