Upload folder using huggingface_hub

main.py

@@ -1,133 +1,11 @@
 import os
 import gradio as gr
-from dotenv import load_dotenv
-import traceback
-from gradio_client import Client
+from dotenv import load_dtenv
 
-# Load environment variables
 load_dotenv()
+HF_TOKEN=os.environ.get('HF_TOKEN')
 
-# Get the Hugging Face token from environment variables
-HF_TOKEN = os.environ.get("HF_TOKEN")
-
-def load_private_space():
-    try:
-        client = Client(
-            "jjia11/MentorMatch-Demo",  # Replace with your actual private space name
-            hf_token=HF_TOKEN,
-        )
-        print("Private space loaded successfully")
-        return client
-    except Exception as e:
-        print(f"Error loading private space: {str(e)}")
-        return None
-
-private_space = load_private_space()
-
-def process_cv(file, num_candidates):
-    if private_space is None:
-        return "Error: Unable to connect to private space", "", [["Error", "Unable to connect to private space"]], None
-    
-    try:
-        result = private_space.predict(
-            file.name,
-            num_candidates,
-            api_name="/api/search_cv"  # This should match the api_name in your private space
-        )
-        
-        # Assuming the result is already in the correct format
-        mentee_summary, mentor_table_html, evaluated_matches, csv_data = result
-
-        # Format evaluated_matches for chatbot
-        chatbot_matches = [
-            [f"Match {i+1}", str(match)] for i, match in enumerate(evaluated_matches)
-        ] if evaluated_matches else [["Info", "No matches found"]]
-
-        return mentee_summary, mentor_table_html, chatbot_matches, csv_data
-    
-    except Exception as e:
-        error_msg = f"Error in process_cv: {str(e)}\n{traceback.format_exc()}"
-        print(error_msg)
-        return f"Error processing CV: {str(e)}", "", [["Error", str(e)]], None
-
-def download_csv(csv_data):
-    if private_space is None:
-        return None
-    
-    try:
-        download = private_space.predict(
-            csv_data,
-            api_name="/api/download_csv"  # This should match the api_name in your private space
-        )
-        return download
-    except Exception as e:
-        error_msg = f"Error in download: {str(e)}\n{traceback.format_exc()}"
-        print(error_msg)
-        return None
-
-def chat(message, history, index_choice):
-    if private_space is None:
-        return [[message, "Error: Unable to connect to private space"]]
-    
-    try:
-        result = private_space.predict(
-            message,
-            history,
-            index_choice,
-            api_name="/api/chat"  # This should match the api_name in your private space
-        )
-        return result
-    except Exception as e:
-        error_msg = f"Error in chat: {str(e)}\n{traceback.format_exc()}"
-        print(error_msg)
-        return [[message, f"Error occurred in chat: {str(e)}"]]
-
-# Create the public Gradio interface
 with gr.Blocks() as demo:
-    gr.HTML("<h1>TCH Mentor-Mentee Matching System (Public Interface)</h1>")
-    
-    with gr.Tab("Mentor Search"):
-        with gr.Row():
-            with gr.Column(scale=1):
-                file = gr.File(label="Upload Mentee CV (PDF)")
-            with gr.Column(scale=1):
-                num_candidates = gr.Number(label="Number of Candidates", value=5, minimum=1, maximum=100, step=1)
-                submit_btn = gr.Button("Submit")
-
-        summary = gr.Textbox(label="Student CV Summary")
-        mentor_table = gr.HTML(label="Matching Mentors Table")
-        matches_chatbot = gr.Chatbot(label="Evaluated Matches")
-        download_btn = gr.Button("Download Results as CSV")
-
-        csv_output = gr.File(label="Download CSV")
-
-        csv_data = gr.State()
-
-        submit_btn.click(
-            fn=process_cv,
-            inputs=[file, num_candidates],
-            outputs=[summary, mentor_table, matches_chatbot, csv_data]
-        )
-
-        download_btn.click(
-            fn=download_csv,
-            inputs=[csv_data],
-            outputs=[csv_output]
-        )
-
-    with gr.Tab("Chat"):
-        chatbot = gr.Chatbot()
-        msg = gr.Textbox(label="Type your message here...")
-        clear = gr.Button("Clear Chat")
-
-        chat_index_choice = gr.Dropdown(
-            choices=["Assistant Professors and Above", "Above Assistant Professors"],
-            label="Select Index for Chat",
-            value="Assistant Professors and Above"
-        )
-
-        msg.submit(chat, inputs=[msg, chatbot, chat_index_choice], outputs=[chatbot])
-        clear.click(lambda: [], outputs=[chatbot])
+    gr.load('jjia11/MentorMatch-Demo', src = 'spaces', hf_token = HF_TOKEN)
 
-if __name__ == "__main__":
-    demo.launch(show_error=True)
+demo.launch()