Update app.py

app.py

@@ -7,6 +7,7 @@ For more information on `huggingface_hub` Inference API support, please check th
 """
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+
 def extract_text_from_pdf(pdf_path):
     # Open the provided PDF file
     doc = fitz.open(pdf_path)
@@ -19,14 +20,8 @@ def extract_text_from_pdf(pdf_path):
     doc.close()  # Ensure the PDF file is closed
     return text
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -51,6 +46,7 @@ def respond(
         print(f"Token: {token}")  # Debugging statement to trace tokens
         yield response  # Yield the complete response up to this point
 
+
 def process_resume_and_respond(pdf_file, message, history, system_message, max_tokens, temperature, top_p):
     # Extract text from the PDF file
     resume_text = extract_text_from_pdf(pdf_file.name)
@@ -61,23 +57,30 @@ def process_resume_and_respond(pdf_file, message, history, system_message, max_t
     response = "".join([token for token in response_gen])
     return response
 
+
 # Store the uploaded PDF content globally
 uploaded_resume_text = ""
 
+
 def upload_resume(pdf_file):
     global uploaded_resume_text
     uploaded_resume_text = extract_text_from_pdf(pdf_file.name)
     return "Resume uploaded successfully!"
 
+
 def respond_with_resume(message, history, system_message, max_tokens, temperature, top_p):
     global uploaded_resume_text
     # Combine the uploaded resume text with the user message
     combined_message = f"Resume:\n{uploaded_resume_text}\n\nUser message:\n{message}"
     # Respond using the combined message
     response_gen = respond(combined_message, history, system_message, max_tokens, temperature, top_p)
-    response = "".join([token for token in response_gen])
+    # Collect all tokens generated
+    response = ""
+    for token in response_gen:
+        response = token  # Update the response with the latest token
     return response
 
+
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
@@ -108,5 +111,6 @@ demo = gr.TabbedInterface(
     ["Upload Resume", "Chat with Job Advisor"]
 )
 
+
 if __name__ == "__main__":
     demo.launch()