Update app.py

app.py

@@ -1,49 +1,45 @@
 import pandas as pd
 import gradio as gr
-from transformers import GPT2Tokenizer, GPT2LMHeadModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Load the model and tokenizer for GPT-2
-tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
-model = GPT2LMHeadModel.from_pretrained('gpt2')
+# Load the model and tokenizer for Meta LLaMA 3.1
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B")
 
+# Load and preprocess the DataFrame
 df = pd.read_csv('anomalies.csv')
-df['Feedback'] = ""  # Initialize with empty strings instead of None for consistency
+df['Feedback'] = ""
+df['ds'] = pd.to_datetime(df['ds']).dt.strftime('%Y-%m-%d')
+df['real'] = df['real'].apply(lambda x: f"{x:.2f}")
 
-# Preprocessing steps
-df['ds'] = pd.to_datetime(df['ds']).dt.strftime('%Y-%m-%d')  # Format the datetime values
-df['real'] = df['real'].apply(lambda x: f"{x:.2f}")  # Format the float values to two decimal places
-
-# Convert each row into a structured natural language sentence
+# Convert data rows to sentences
 def tokenize_row(row):
     return f"On {row['ds']}, the expense in the group '{row['Group']}' was ${row['real']}."
 
-# Apply the tokenization function to each row
 df['tokenized'] = df.apply(tokenize_row, axis=1)
 print(df)
 
-# Function to respond to questions with GPT-2
-def answer_question_with_gpt(question):
+# Function to generate a response based on the latest data entries
+def answer_question_with_llama(question):
     if tokenizer.pad_token is None:
         tokenizer.pad_token = tokenizer.eos_token
 
-    # Simplify the prompt to avoid exceeding token limits
-    latest_entries = df['tokenized'].tail(10).tolist()  # Limit to the last 10 entries for context
+    latest_entries = df['tokenized'].tail(10).tolist()
     prompt = f"Based on the following data: {' '.join(latest_entries)} Question: {question} Answer:"
     inputs = tokenizer(prompt, return_tensors='pt', padding='max_length', truncation=True, max_length=512)
     attention_mask = inputs['attention_mask']
     input_ids = inputs['input_ids']
-    
+
     generated_ids = model.generate(
         input_ids,
         attention_mask=attention_mask,
-        max_length=len(input_ids[0]) + 100,
-        temperature=0.3,
+        max_length=512,  # Adjusted to match typical model capacity
+        temperature=0.7,  # Adjust temperature for diversity
         top_p=0.9,
         no_repeat_ngram_size=2
     )
     
     generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
-    # Extract the response after "Answer:"
     response_part = generated_text.split("Answer:")[1] if "Answer:" in generated_text else "No answer found."
     final_response = response_part.split(".")[0] + "."
     return final_response
@@ -70,7 +66,7 @@ with gr.Blocks() as demo:
             feedback_result = gr.Textbox(label="Feedback Result", interactive=False)
             submit_button = gr.Button("Submit Feedback")
 
-    ask_button.click(fn=answer_question_with_gpt, inputs=question_input, outputs=answer_output)
+    ask_button.click(fn=answer_question_with_llama, inputs=question_input, outputs=answer_output)
     submit_button.click(fn=add_feedback, inputs=[name_input, feedback_input], outputs=feedback_result)
 
 demo.launch()