Update app.py

This is the best version that can be run. If this doesn't work, you can always use the previous setting which is the MVP

app.py

@@ -194,8 +194,8 @@ from collections import Counter
 
 def extract_problem_domains(df, 
                             text_column='Processed_ProblemDescription_forDomainExtraction',
-                            cluster_range=(6, 8), 
-                            top_words=7):
+                            cluster_range=(3, 17), 
+                            top_words=10):
     consoleMessage_and_Print("Extracting Problem Domains...")
     
     # Sentence Transformers approach
@@ -276,8 +276,8 @@ def text_processing_for_location(text):
 def extract_location_clusters(df, 
                               text_column1='Processed_LocationText_forClustering', # Extracted through NLP
                               text_column2='Geographical_Location', # User Input
-                              cluster_range=(3, 5),
-                              top_words=3):
+                              cluster_range=(3, 17),
+                              top_words=10):
     # Combine the two text columns
     text_column = "Combined_Location_Text"
     df[text_column] = df[text_column1] + ' ' + df[text_column2]
@@ -361,17 +361,17 @@ from transformers import GPTNeoForCausalLM, GPT2Tokenizer
 def generate_project_proposal(prompt): # Generate the proposal
     default_proposal = "Hyper-local Sustainability Projects would lead to Longevity of the self and Prosperity of the community. Therefore UNSDGs coupled with Longevity initiatives should be focused upon."
 
-    # model_Name = "EleutherAI/gpt-neo-2.7B"
-    # tempareCHUR = uniform(0.3,0.6)
+    model_Name = "EleutherAI/gpt-neo-2.7B"
+    tempareCHUR = uniform(0.3,0.6)
     
-    model_Name = "EleutherAI/gpt-neo-1.3B"
-    tempareCHUR = uniform(0.5,0.8)
+    # model_Name = "EleutherAI/gpt-neo-1.3B"
+    # tempareCHUR = uniform(0.5,0.8)
 
     consoleMessage_and_Print(f"Trying to access {model_Name} model. The Prompt is: \n{prompt}")
     
     model = GPTNeoForCausalLM.from_pretrained(model_Name)
     tokenizer = GPT2Tokenizer.from_pretrained(model_Name)
-    model_max_token_limit = 1500 #2048
+    model_max_token_limit = 2048 #1500
         
     try:
         # input_ids = tokenizer.encode(prompt, return_tensors="pt")
@@ -457,9 +457,8 @@ def create_project_proposals(budget_cluster_df, problem_cluster_df, location_clu
                 
                 random.shuffle(shuffled_descriptions)
                 # Prepare the prompt
-                # problems_summary = "; \n".join(problem_descriptions)  # Join all problem descriptions
-                # problems_summary = "; \n".join(problem_descriptions[:3])  # Limit to first 3 for brevity
-                problems_summary = "; \n".join(shuffled_descriptions[:7])
+                # problems_summary = "; \n".join(shuffled_descriptions[:7]) # Limit to first 3 for brevity
+                problems_summary = "; \n".join(shuffled_descriptions) # Join all problem descriptions
                 
                 
                 # prompt = f"Generate a solution oriented project proposal for the following:\n\nLocation: {location}\nProblem Domain: {problem_domain}\nProblems: {problems_summary}\n\nProject Proposal:"
@@ -767,9 +766,9 @@ def process_excel(file):
 
 
 example_files = []
-example_files.append('#TaxDirection (Responses)_BasicExample.xlsx')
+# example_files.append('#TaxDirection (Responses)_BasicExample.xlsx')
 # example_files.append('#TaxDirection (Responses)_IntermediateExample.xlsx')
-# example_files.append('#TaxDirection (Responses)_UltimateExample.xlsx')
+example_files.append('#TaxDirection (Responses)_UltimateExample.xlsx')
 
 
 import random