Update app.py

app.py

@@ -9,6 +9,7 @@ import base64
 import whisper
 import uuid
 import json
+from datetime import datetime
 from openai import OpenAI
 
 # Load Whisper model
@@ -27,105 +28,299 @@ CHAT_HISTORY_DIR = "chat_history"
 os.makedirs(CHAT_HISTORY_DIR, exist_ok=True)
 
 def extract_text_from_file(file):
-    name = file.name if hasattr(file, "name") else file
-    ext = os.path.splitext(name)[1].lower()
-
-    if ext == ".pdf":
-        with pdfplumber.open(file) as pdf:
-            text = "\n".join(page.extract_text() or "" for page in pdf.pages)
-    elif ext == ".docx":
-        doc = docx.Document(file)
-        text = "\n".join(p.text for p in doc.paragraphs)
-    elif ext == ".xlsx":
-        df = pd.read_excel(file)
-        text = df.to_string()
-    elif ext in [".png", ".jpg", ".jpeg"]:
-        img = Image.open(file)
-        buffer = BytesIO()
-        img.save(buffer, format="PNG")
-        encoded = base64.b64encode(buffer.getvalue()).decode("utf-8")
-        text = f"[Image uploaded: data:image/png;base64,{encoded[:100]}... (truncated)]"
-    else:
-        text = file.read().decode("utf-8", errors="ignore")
-
-    return text
+    """Extract text content from various file types"""
+    try:
+        if file is None:
+            return ""
+        
+        name = file.name if hasattr(file, "name") else str(file)
+        ext = os.path.splitext(name)[1].lower()
+
+        if ext == ".pdf":
+            with pdfplumber.open(file) as pdf:
+                text = "\n".join(page.extract_text() or "" for page in pdf.pages)
+        elif ext == ".docx":
+            doc = docx.Document(file)
+            text = "\n".join(p.text for p in doc.paragraphs)
+        elif ext == ".xlsx" or ext == ".xls":
+            df = pd.read_excel(file)
+            text = df.to_string()
+        elif ext == ".csv":
+            df = pd.read_csv(file)
+            text = df.to_string()
+        elif ext in [".png", ".jpg", ".jpeg", ".gif", ".bmp"]:
+            img = Image.open(file)
+            # For images, we'll include a description and base64 data
+            text = f"[Image uploaded: {name}]\nImage format: {img.format}\nImage size: {img.size}\nImage mode: {img.mode}"
+        elif ext in [".txt", ".md", ".py", ".js", ".html", ".css", ".json"]:
+            with open(file, 'r', encoding='utf-8', errors='ignore') as f:
+                text = f.read()
+        else:
+            # Try to read as text file
+            try:
+                with open(file, 'r', encoding='utf-8', errors='ignore') as f:
+                    text = f.read()
+            except:
+                text = f"[File uploaded: {name}] - Unable to extract text content"
+
+        return text
+    except Exception as e:
+        return f"Error processing file: {str(e)}"
 
 def transcribe_audio(audio_path):
-    result = whisper_model.transcribe(audio_path)
-    return result["text"]
+    """Transcribe audio file using Whisper"""
+    try:
+        if audio_path is None:
+            return ""
+        result = whisper_model.transcribe(audio_path)
+        return result["text"]
+    except Exception as e:
+        return f"Error transcribing audio: {str(e)}"
 
 def generate_reply(history):
-    messages = [{"role": "system", "content": "You are a helpful assistant."}]
-    for user_msg, bot_msg in history:
-        messages.append({"role": "user", "content": user_msg})
-        messages.append({"role": "assistant", "content": bot_msg})
-
-    response = client.chat.completions.create(
-        model="llama3-8b-8192",
-        messages=messages,
-        temperature=0.7
-    )
-    return response.choices[0].message.content
-
-def respond(message, history):
-    reply = generate_reply(history + [[message, ""]])
-    history.append([message, reply])
-    return history, ""
-
-def handle_file_upload(file, message):
-    if file is None:
-        return message
-    file_content = extract_text_from_file(file)
-    return f"{message}\n\n--- File Content Start ---\n{file_content}\n--- File Content End ---"
-
-def handle_audio_upload(audio, message):
-    if audio is None:
-        return message
-    transcription = transcribe_audio(audio)
-    return f"{message}\n\n--- Transcription ---\n{transcription}"
-
-def save_chat(history):
-    chat_id = str(uuid.uuid4())
-    path = os.path.join(CHAT_HISTORY_DIR, f"{chat_id}.json")
-    with open(path, "w", encoding="utf-8") as f:
-        json.dump(history, f, ensure_ascii=False, indent=2)
-    return f"Chat saved as {chat_id}.json"
-
-def load_chat(file):
-    if file is None:
-        return [], ""
-    path = file.name
-    with open(path, "r", encoding="utf-8") as f:
-        history = json.load(f)
-    return history, ""
-
-def reset_chat():
-    return [], ""
-
-with gr.Blocks(css="body { background-color: white; color: black }") as demo:
-    gr.Markdown("<h1 style='text-align: center;'>🧠 Neobot</h1>")
-    chatbot = gr.Chatbot(label="Chat", elem_id="chatbox", height=450)
-    history = gr.State([])
+    """Generate AI reply using the chat history"""
+    try:
+        messages = [{"role": "system", "content": "You are a helpful assistant. When users upload files or audio, acknowledge the content and provide relevant responses based on the uploaded material."}]
+        
+        for user_msg, bot_msg in history:
+            if user_msg:
+                messages.append({"role": "user", "content": user_msg})
+            if bot_msg:
+                messages.append({"role": "assistant", "content": bot_msg})
 
-    with gr.Row():
-        txt = gr.Textbox(placeholder="Type a message or edit file/transcription content...", scale=5, show_label=False)
-        send_btn = gr.Button("Send", scale=1)
+        response = client.chat.completions.create(
+            model="llama3-8b-8192",
+            messages=messages,
+            temperature=0.7,
+            max_tokens=2048
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"Error generating response: {str(e)}"
 
-    with gr.Row():
-        upload_btn = gr.File(label="📎 Upload File", file_types=[".pdf", ".docx", ".txt", ".xlsx", ".png", ".jpg", ".jpeg"])
-        audio_in = gr.Audio(label="🎙️ Upload Audio", type="filepath")
+def process_message_with_files(message, file_upload, audio_upload, history):
+    """Process user message along with any uploaded files or audio"""
+    full_message = message if message else ""
+    
+    # Process uploaded file
+    if file_upload is not None:
+        file_content = extract_text_from_file(file_upload)
+        if file_content:
+            file_name = file_upload.name if hasattr(file_upload, 'name') else 'uploaded_file'
+            full_message += f"\n\n📎 **File Upload: {file_name}**\n```\n{file_content}\n```"
+    
+    # Process uploaded audio
+    if audio_upload is not None:
+        transcription = transcribe_audio(audio_upload)
+        if transcription:
+            full_message += f"\n\n🎙️ **Audio Transcription:**\n{transcription}"
+    
+    if not full_message.strip():
+        return history, "", None, None, "Please enter a message or upload a file/audio."
+    
+    # Generate AI response
+    reply = generate_reply(history + [[full_message, ""]])
+    
+    # Update history
+    new_history = history + [[full_message, reply]]
+    
+    return new_history, "", None, None, ""
+
+def save_chat_history(history):
+    """Save chat history to a JSON file"""
+    try:
+        if not history:
+            return "No chat history to save."
+        
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        chat_id = f"chat_{timestamp}_{str(uuid.uuid4())[:8]}"
+        filename = f"{chat_id}.json"
+        filepath = os.path.join(CHAT_HISTORY_DIR, filename)
+        
+        chat_data = {
+            "timestamp": datetime.now().isoformat(),
+            "chat_id": chat_id,
+            "history": history
+        }
+        
+        with open(filepath, "w", encoding="utf-8") as f:
+            json.dump(chat_data, f, ensure_ascii=False, indent=2)
+        
+        return f"✅ Chat saved successfully as: {filename}"
+    except Exception as e:
+        return f"❌ Error saving chat: {str(e)}"
 
+def load_chat_history(file_upload):
+    """Load chat history from a JSON file"""
+    try:
+        if file_upload is None:
+            return [], "Please select a chat file to load."
+        
+        with open(file_upload.name, "r", encoding="utf-8") as f:
+            chat_data = json.load(f)
+        
+        # Handle both old and new format
+        if isinstance(chat_data, list):
+            history = chat_data
+        else:
+            history = chat_data.get("history", [])
+        
+        return history, f"✅ Chat loaded successfully from: {os.path.basename(file_upload.name)}"
+    except Exception as e:
+        return [], f"❌ Error loading chat: {str(e)}"
+
+def clear_chat():
+    """Clear the current chat"""
+    return [], "Chat cleared."
+
+def get_saved_chats():
+    """Get list of saved chat files"""
+    try:
+        files = [f for f in os.listdir(CHAT_HISTORY_DIR) if f.endswith('.json')]
+        files.sort(reverse=True)  # Most recent first
+        return files[:10]  # Return last 10 chats
+    except:
+        return []
+
+# Custom CSS for better styling
+custom_css = """
+.gradio-container {
+    max-width: 1200px !important;
+    margin: auto !important;
+}
+.chat-container {
+    height: 500px !important;
+}
+.upload-area {
+    border: 2px dashed #ccc !important;
+    border-radius: 10px !important;
+    padding: 20px !important;
+    text-align: center !important;
+}
+.button-row {
+    display: flex !important;
+    gap: 10px !important;
+    justify-content: center !important;
+}
+"""
+
+# Create the Gradio interface
+with gr.Blocks(css=custom_css, title="🧠 Neobot - Advanced Chatbot") as demo:
+    gr.Markdown("""
+    # 🧠 Neobot - Advanced AI Chatbot
+    
+    **Features:**
+    - 💬 Natural conversation with AI
+    - 📎 Upload and process various file types (PDF, DOCX, TXT, CSV, Excel, Images)
+    - 🎙️ Audio transcription and processing
+    - 💾 Save and load chat conversations
+    - 🆕 Start new conversations anytime
+    """)
+    
+    # Chat interface
+    chatbot = gr.Chatbot(
+        label="Chat History",
+        elem_id="chatbox",
+        height=500,
+        show_copy_button=True,
+        bubble_full_width=False
+    )
+    
+    # Message input area
     with gr.Row():
-        save_btn = gr.Button("💾 Save Chat")
-        new_btn = gr.Button("🆕 New Chat")
-        load_btn = gr.File(label="📂 Load Chat", file_types=[".json"])
-
-    # Events
-    send_btn.click(respond, [txt, history], [chatbot, txt])
-    upload_btn.change(handle_file_upload, [upload_btn, txt], txt)
-    audio_in.change(handle_audio_upload, [audio_in, txt], txt)
-    save_btn.click(lambda h: gr.Textbox.update(value=save_chat(h)), [history])
-    load_btn.change(load_chat, [load_btn], [history, txt])
-    new_btn.click(reset_chat, outputs=[history, txt, chatbot])
-
-demo.launch()
+        message_input = gr.Textbox(
+            placeholder="Type your message here...",
+            scale=4,
+            show_label=False,
+            container=False
+        )
+        send_button = gr.Button("Send 📤", scale=1, variant="primary")
+    
+    # File upload area
+    with gr.Row():
+        with gr.Column(scale=1):
+            file_upload = gr.File(
+                label="📎 Upload File",
+                file_types=[".pdf", ".docx", ".txt", ".xlsx", ".xls", ".csv", ".png", ".jpg", ".jpeg", ".gif", ".bmp", ".py", ".js", ".html", ".css", ".json", ".md"],
+                elem_classes="upload-area"
+            )
+        with gr.Column(scale=1):
+            audio_upload = gr.Audio(
+                label="🎙️ Upload Audio",
+                type="filepath",
+                elem_classes="upload-area"
+            )
+    
+    # Control buttons
+    with gr.Row(elem_classes="button-row"):
+        save_button = gr.Button("💾 Save Chat", variant="secondary")
+        clear_button = gr.Button("🆕 New Chat", variant="secondary")
+        
+    with gr.Row():
+        load_file = gr.File(
+            label="📂 Load Saved Chat",
+            file_types=[".json"]
+        )
+    
+    # Status message
+    status_message = gr.Textbox(
+        label="Status",
+        interactive=False,
+        visible=True
+    )
+    
+    # State management
+    chat_history = gr.State([])
+    
+    # Event handlers
+    send_button.click(
+        fn=process_message_with_files,
+        inputs=[message_input, file_upload, audio_upload, chat_history],
+        outputs=[chat_history, message_input, file_upload, audio_upload, status_message]
+    ).then(
+        fn=lambda history: history,
+        inputs=[chat_history],
+        outputs=[chatbot]
+    )
+    
+    message_input.submit(
+        fn=process_message_with_files,
+        inputs=[message_input, file_upload, audio_upload, chat_history],
+        outputs=[chat_history, message_input, file_upload, audio_upload, status_message]
+    ).then(
+        fn=lambda history: history,
+        inputs=[chat_history],
+        outputs=[chatbot]
+    )
+    
+    save_button.click(
+        fn=save_chat_history,
+        inputs=[chat_history],
+        outputs=[status_message]
+    )
+    
+    clear_button.click(
+        fn=clear_chat,
+        outputs=[chat_history, status_message]
+    ).then(
+        fn=lambda: [],
+        outputs=[chatbot]
+    )
+    
+    load_file.change(
+        fn=load_chat_history,
+        inputs=[load_file],
+        outputs=[chat_history, status_message]
+    ).then(
+        fn=lambda history: history,
+        inputs=[chat_history],
+        outputs=[chatbot]
+    )
+
+if __name__ == "__main__":
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=False,
+        debug=True
+    )