Update app.py

app.py

@@ -3,12 +3,20 @@ import torch
 from transformers import pipeline
 import gradio as gr
 
+import PyPDF2
+
 import os
 
 
 from huggingface_hub import login, HfFolder
 from getpass import getpass
 
+# Load and preprocess the PDF content
+with open('/content/LTDOCS.pdf', 'rb') as file:
+      pdf_reader = PyPDF2.PdfReader(file)
+      pdf_content = ' '.join([page.extract_text() for page in pdf_reader.pages])
+      pdf_content = pdf_content.lower().strip()
+    
 def init_huggingface_auth():
     """
     Initialize Hugging Face authentication with multiple fallback options
@@ -51,67 +59,110 @@ if not init_huggingface_auth():
         
 print("Authentication successful - continuing with the application")
 
+
 # Initialize the pipeline
 pipe = pipeline(
     "text-generation",
     model="google/gemma-2-2b-jpn-it",
-    
+    model_kwargs={"torch_dtype": torch.bfloat16},
     device="cpu",  # replace with "mps" to run on a Mac device
 )
 
-# Define system context and bot personality
-SYSTEM_PROMPT = """You are Lugha Tausi chat bot assistant, an AI language assistant specialized in African languages, with a focus on Swahili. Your primary tasks are:
+# System prompt and welcome message (using your existing definitions)
+SYSTEM_PROMPT = f"""You Foton the chat bot assistant of the Company Lugha taussi, an AI language assistant specialized in African languages, with a focus on Swahili. Your primary tasks are:
 1. Providing accurate translations between Swahili and other languages
 2. Teaching Swahili vocabulary and grammar
 3. Explaining cultural context behind Swahili expressions
 4. Helping users practice Swahili conversation
+5. Based on the programing doc  for lughah Tausi Programing which is in swahili , the following information is relevant: {pdf_content} .assist users in programing and installing lugha tausi programing language"
 
-Always maintain a friendly and patient demeanor, and provide cultural context when relevant speak mostly english and change when asked.
+Always maintain a friendly and patient demeanor, and provide cultural context when relevant speak mostly swahili and change when asked.
 """
 
-WELCOME_MESSAGE = "**Welcome to Lugha Tausi!** I am Foton, your personal Swahili assistant. I'm here to help you learn, understand, and speak Swahili. **How can I assist you today?** Let's get started! 😊"
+WELCOME_MESSAGE = "**Karibu Lugha Tausi!** Mimi ni Foton, msaidizi wako wa kibinafsi wa Kiswahili. Niko hapa kukusaidia kujifunza, kuelewa, na kuzungumza Kiswahili. **Ninaweza kukusaidiaje leo?** Hebu tuanze! 😊"
 
 def format_chat_message(messages, system_prompt=SYSTEM_PROMPT):
     """Format the chat messages with system prompt"""
     formatted_prompt = f"{system_prompt}\n\n"
-    
-    # Add welcome message if this is the first interaction
-    if not messages:
-        formatted_prompt += f"Lugha Tausi: {WELCOME_MESSAGE}\n"
-    
+
     for message in messages:
-        if message["role"] == "user":
-            formatted_prompt += f"User: {message['content']}\nLugha Tausi: "
-        elif message["role"] == "assistant":
-            formatted_prompt += f"{message['content']}\n"
-    
+        if isinstance(message, tuple):
+            role, content = message
+            if role == "user":
+                formatted_prompt += f"User: {content}\nLugha Tausi: "
+            elif role == "assistant":
+                formatted_prompt += f"{content}\n"
+
     return formatted_prompt
 
-def get_bot_response(messages):
-    """Generate response from the bot"""
-    # Return welcome message if this is the first interaction
-    if not messages:
-        return WELCOME_MESSAGE
-        
+def chat_response(message, history):
+    """Generate response for Gradio chat interface"""
+    # Convert history to the format expected by the model
+    messages = []
+    for user_msg, bot_msg in history:
+        messages.append(("user", user_msg))
+        messages.append(("assistant", bot_msg))
+    messages.append(("user", message))
+
     formatted_input = format_chat_message(messages)
     outputs = pipe(
         formatted_input,
         return_full_text=False,
         max_new_tokens=256,
-        temperature=0.1,  # Lower temperature for more consistent responses
+        temperature=0.1,
         top_p=0.9,
         do_sample=True
     )
     return outputs[0]["generated_text"].strip()
 
-# Example usage
-messages = []
-print(get_bot_response(messages))  # This will print the welcome message
+# Create Gradio interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    chatbot = gr.Chatbot(
+        value=[(None, WELCOME_MESSAGE)],
+        height=600,
+        show_label=False
+    )
+    msg = gr.Textbox(
+        placeholder="Type your message here...",
+        show_label=False
+    )
+    clear = gr.Button("Clear Chat")
+
+    def user_input(message, history):
+        return "", history + [(message, None)]
+
+    def bot_response(history):
+        if len(history) == 0:
+            history.append((None, WELCOME_MESSAGE))
+            return history
 
-# Continue with conversation
-messages.append({"role": "user", "content": "How do you say 'hello' in Swahili?"})
-response = get_bot_response(messages)
-print(response)
+        user_message = history[-1][0]
+        bot_message = chat_response(user_message, history[:-1])
+        history[-1] = (user_message, bot_message)
+        return history
+
+    def clear_chat():
+        return [], [(None, WELCOME_MESSAGE)]
+
+    # Set up the message flow
+    msg.submit(
+        user_input,
+        [msg, chatbot],
+        [msg, chatbot],
+        queue=False
+    ).then(
+        bot_response,
+        chatbot,
+        chatbot
+    )
+
+    clear.click(
+        clear_chat,
+        None,
+        [chatbot],
+        queue=False
+    )
 
+# Launch the interface
 if __name__ == "__main__":
     demo.launch(share=True,pwa=True )