Update app.py

app.py

@@ -11,16 +11,16 @@ import random
 
 #import pyodbc
 
+'''
 import pkg_resources
 
-
 # Get a list of installed packages and their versions
 installed_packages = {pkg.key: pkg.version for pkg in pkg_resources.working_set}
 
 # Print the list of packages
 for package, version in installed_packages.items():
     print(f"{package}=={version}")
-
+'''
 
 '''
 # Replace the connection parameters with your SQL Server information
@@ -47,8 +47,8 @@ df = pd.read_sql_query(query, conn)
 conn.close()
 '''
 
-# Create a sample DataFrame with 3,000 records and 20 columns
 '''
+# Create a sample DataFrame with 3,000 records and 20 columns
 num_records = 100
 num_columns = 20
 
@@ -133,17 +133,6 @@ def sqlquery(input): #, history=[]):
     sql_outputs = sql_model.generate(**sql_encoding)
     sql_response = sql_tokenizer.batch_decode(sql_outputs, skip_special_tokens=True)
 
-    
-    #global conversation_history
-    '''
-    # Maintain the conversation history
-    conversation_history.append("User: " + input + "\n")
-    conversation_history.append("Bot: " + " ".join(sql_response) + "\n" )
-
-    output = " ".join(conversation_history)
-    return output
-    '''
-
     #history.append((input, sql_response))
     conversation_history.append(("User", input))
     conversation_history.append(("Bot", sql_response))
@@ -153,7 +142,7 @@ def sqlquery(input): #, history=[]):
     conversation = "\n".join([f"{sender}: {msg}" for sender, msg in conversation_history])
     
     return conversation
-    
+    #return sql_response
     #return sql_response, history
 
     '''
@@ -164,8 +153,6 @@ def sqlquery(input): #, history=[]):
     html += "</div>"
     return html
     '''
-    #return sql_response
-
 
 chat_interface = gr.Interface(
     fn=chat,
@@ -211,4 +198,37 @@ combine_interface = gr.TabbedInterface(
 
 if __name__ == '__main__':
     combine_interface.launch()
-    #iface.launch(debug=True)
+    #iface.launch(debug=True)
+
+
+'''
+batch_size = 10  # Number of records in each batch
+num_records = 3000  # Total number of records in the dataset
+
+for start_idx in range(0, num_records, batch_size):
+    end_idx = min(start_idx + batch_size, num_records)
+    
+    # Get a batch of records
+    batch_data = dataset[start_idx:end_idx]  # Replace with your dataset
+    
+    # Tokenize the batch
+    tokenized_batch = tokenizer.batch_encode_plus(
+        batch_data, padding=True, truncation=True, return_tensors="pt"
+    )
+    
+    # Perform inference
+    with torch.no_grad():
+        output = model.generate(
+            input_ids=tokenized_batch["input_ids"],
+            max_length=1024,
+            pad_token_id=tokenizer.eos_token_id,
+        )
+    
+    # Decode the output and process the responses
+    responses = [tokenizer.decode(ids, skip_special_tokens=True) for ids in output]
+    
+    # Process responses and maintain conversation context
+    # ...
+
+
+'''