Update app.py

app.py

@@ -2,24 +2,24 @@ import gradio as gr
 import pandas as pd
 from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
 
-# Initialize the Hugging Face pipeline
-model_name = "gpt2"  # Using GPT-2 to ensure compatibility
+# Initialize the Hugging Face pipeline with GPT-4 model
+model_name = "EleutherAI/gpt-neo-2.7B"  # Change to your desired GPT-4 model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 def generate_solutions(query):
     # Use the language model to generate solutions
-    response = generator(query, max_length=100, num_return_sequences=3)
+    responses = generator(query, max_length=100, num_return_sequences=3)
     
     # Extract the generated texts
-    solutions = [{"Solution": r['generated_text']} for r in response]
+    solutions = [{"Solution": response['generated_text'].strip(), "Link": "https://example.com"} for response in responses]
     
     # Convert solutions to a DataFrame
     df = pd.DataFrame(solutions)
     
-    # Convert DataFrame to HTML table
-    table_html = df.to_html(escape=False, index=False)
+    # Convert DataFrame to HTML table with clickable links
+    table_html = df.to_html(escape=False, index=False, render_links=True)
     
     return table_html
 
@@ -29,7 +29,7 @@ iface = gr.Interface(
     inputs=gr.Textbox(lines=2, placeholder="Describe the problem with the machine..."), 
     outputs=gr.HTML(),
     title="Oroz: Your Industry Maintenance Assistant",
-    description="Describe the problem with your machine, and get an organized table of suggested solutions."
+    description="Describe the problem with your machine, and get an organized table of suggested solutions with web links."
 )
 
 iface.launch(share=True)