Update app.py

app.py

@@ -3,10 +3,10 @@ from huggingface_hub import InferenceClient
 import nltk
 import PyPDF2
 
-# Download necessary NLTK data
+# Download the necessary NLTK data (using the correct resource "punkt")
 nltk.download("punkt", quiet=True)
 
-# Hugging Face Inference Client
+# Initialize the Hugging Face Inference Client
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 # Function to split text into manageable chunks
@@ -31,7 +31,7 @@ def chunk_text(text, max_chunk_size=1500):
         chunks.append(current_chunk.strip())
     return chunks
 
-# Respond function for chunked responses
+# Function to provide responses for each text chunk
 def respond_chunked(message, history, system_message, max_tokens, temperature, top_p, file_content):
     if not file_content.strip():
         return "No file content available to provide context."
@@ -54,7 +54,7 @@ def respond_chunked(message, history, system_message, max_tokens, temperature, t
             combined_response += f"Error processing chunk: {e}\n"
     return combined_response.strip()
 
-# Parse uploaded files
+# Function to parse the uploaded file based on its extension
 def parse_file(file_obj):
     file_extension = file_obj.name.split('.')[-1].lower()
     if file_extension == "pdf":
@@ -69,21 +69,21 @@ def parse_file(file_obj):
         except Exception as e:
             return f"Error reading file: {e}"
 
-# Define the Gradio app layout
+# Define the Gradio app interface
 with gr.Blocks() as demo:
     gr.Markdown("# **Chat with File Context (Chunking for Large Files)**")
     gr.Markdown("Upload large files, and chat with AI using context derived from those files.")
 
-    # State variables to store file content and chat history
+    # States to store file content and chat history
     file_content_state = gr.State("")
     chat_history_state = gr.State([])
 
-    # File upload interface
+    # File upload component (accepts multiple files)
     file_input = gr.File(label="Upload File(s)", file_count="multiple", type="filepath")
     
     def handle_file_upload(files):
         """
-        Process uploaded files and store their content in the state.
+        Process uploaded files and store their content.
         """
         combined_text = ""
         for file in files:
@@ -97,10 +97,9 @@ with gr.Blocks() as demo:
 
     file_input.change(fn=handle_file_upload, inputs=file_input, outputs=file_content_state)
 
-    # Chat interface
+    # Chat interface components
     chatbot = gr.Chatbot(label="Conversation", type="messages")
     user_input = gr.Textbox(label="Your Message", placeholder="Ask something...", lines=2)
-
     system_prompt = gr.Textbox(label="System Prompt", value="You are a helpful AI assistant.", interactive=True)
     max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens")
     temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
@@ -109,15 +108,16 @@ with gr.Blocks() as demo:
     def chat_function(user_message, history, file_content, system_prompt, max_tokens, temperature, top_p):
         if not user_message.strip():
             return "", history
+        # Get the assistant's response using the chunking function
         assistant_response = respond_chunked(
             user_message, history, system_prompt, max_tokens, temperature, top_p, file_content
         )
-        # Append user and assistant messages in the correct format
+        # Append user and assistant messages to the conversation history
         history.append({"role": "user", "content": user_message})
         history.append({"role": "assistant", "content": assistant_response})
         return "", history
 
-    # Add send button for user input
+    # Button to send the user message
     send_button = gr.Button("Send")
     send_button.click(
         fn=chat_function,
@@ -125,6 +125,7 @@ with gr.Blocks() as demo:
         outputs=[user_input, chatbot]
     )
 
+    # Enable submission via the Enter key in the textbox
     user_input.submit(
         fn=chat_function,
         inputs=[user_input, chat_history_state, file_content_state, system_prompt, max_tokens, temperature, top_p],
@@ -132,4 +133,3 @@ with gr.Blocks() as demo:
     )
 
     demo.launch(server_name="0.0.0.0", server_port=7860, share=True, show_error=True)
-