Delete app.py

app.py

@@ -1,95 +0,0 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-import os
-
-# Mock vector database creation
-vector_db_created = False
-
-def create_vector_db(uploaded_files):
-    global vector_db_created
-    if uploaded_files:
-        vector_db_created = True
-        return "Vector database created successfully. You can now chat with your documents!"
-    return "Please upload a file first."
-
-# Initialize Chat Model
-client = InferenceClient("meta-llama/Llama-3.2-3B-Instruct")
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    if not vector_db_created:
-        yield "Error: Please create the vector database first."
-        return
-    
-    messages = [{"role": "system", "content": system_message}]
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-    messages.append({"role": "user", "content": message})
-    response = ""
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
-
-# Custom CSS
-css = """
-#drop-area { border: 2px dashed #42B3CE; border-radius: 10px; padding: 20px; }
-.error-message { color: red; font-weight: bold; }
-.vector-btn { background-color: #42B3CE !important; color: white; }
-.chat-submit { background-color: #06688E !important; color: white; }
-.chat-clear { background-color: #e0e0e0 !important; color: black; }
-"""
-
-def main():
-    with gr.Blocks(css=css) as demo:
-        gr.Markdown("""# **RAG PDF Chatbot**
-        Query your PDF documents! Upload, initialize, and chat using an AI assistant.
-        """)
-
-        # Step 1: File upload and database initialization
-        with gr.Row():
-            with gr.Column():
-                pdf_upload = gr.File(label="Upload PDF documents", file_types=[".pdf"], type="file")
-                create_db_btn = gr.Button("Create vector database", elem_classes=["vector-btn"])
-                db_status = gr.Textbox("Not initialized", interactive=False)
-
-            with gr.Column():
-                gr.Markdown("**Step 2 - Chat with your Document**")
-                chatbot = gr.ChatInterface(
-                    respond,
-                    additional_inputs=[
-                        gr.Textbox(
-                            value="You are a helpful assistant...",
-                            label="System Message",
-                            visible=False
-                        ),
-                        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens", visible=False),
-                        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature", visible=False),
-                        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p", visible=False),
-                    ],
-                    submit_btn="Submit",
-                    clear_btn="Clear",
-                )
-
-        # Button events
-        create_db_btn.click(create_vector_db, inputs=[pdf_upload], outputs=[db_status])
-
-    demo.launch(share=True)
-
-if __name__ == "__main__":
-    main()