test cv extraction

app.py

@@ -104,32 +104,24 @@ def LLM_Inference(cv_text):
         )
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
+def process(file_path):
+    cv_text = read_pdf(file_path)
+    cv_summary = LLM_Inference(cv_text)
+    return cv_text, cv_summary
+
 # Create Gradio App
-pdf_interface = gr.Interface(
-    fn=read_pdf,
+interface = gr.Interface(
+    fn=process,
     inputs=gr.File(label="Upload a PDF file"),
-    outputs=#[
-        #gr.Textbox(label="PDF Content"),  # Display PDF content
-        gr.State(),  # Store PDF content in a shared state
-            #],
+    outputs=[
+        gr.Textbox(label="PDF Content"),  # Display PDF content
+        gr.Textbox(label="CV Summary"), 
+            ],
     title="PDF Processor",
     description="Upload a PDF file and extract its content."
 )
 
-# Create Gradio interface for Hugging Face inference
-llm_interface = gr.Interface(
-    fn=LLM_Inference,
-    inputs=gr.State(),
-    outputs=gr.Textbox(label="Hugging Face Output"),
-    title="Hugging Face Query",
-    description="Enter a query and get a response from the Hugging Face model."
-)
 
-# Combine both interfaces into a tabbed app
-interface = gr.TabbedInterface(
-    interface_list=[pdf_interface, llm_interface],
-    tab_names=["PDF Processor", "Hugging Face Query"]
-)
 # Launch the Gradio App
 if __name__ == "__main__":
     prepare()