Error Fix

app.py

@@ -13,6 +13,9 @@ import plotly.io as pio
 import traceback
 import base64
 from io import BytesIO
+import speech_recognition as sr
+from gtts import gTTS
+import re
 
 # Load environment variables
 load_dotenv()
@@ -129,11 +132,8 @@ interpret_prompt = ChatPromptTemplate.from_messages(
 
 def process_text_query(query, history):
     """Process a text query and update chat history"""
-    global current_plot
-    current_plot = None  # Reset the plot
-    
     if not query:
-        return "", history, None
+        return "", history
     
     # Add the user's query to history
     history.append({"role": "user", "content": query})
@@ -225,11 +225,13 @@ def process_text_query(query, history):
                                     # Regular data - use bar chart
                                     fig = px.bar(result_df, x=x_col, y=y_cols[0], title="Data Visualization")
                                 
-                                # Convert the figure to HTML and embed it directly in the response
-                                plot_html = pio.to_html(fig, full_html=False, include_plotlyjs='cdn')
+                                # Convert the figure to an image and encode it as base64
+                                img_bytes = fig.to_image(format="png", width=800, height=500)
+                                encoded = base64.b64encode(img_bytes).decode("ascii")
+                                img_src = f"data:image/png;base64,{encoded}"
                                 
-                                # Add the HTML directly to the response
-                                response += f"\n\n<div style='width:100%;height:400px;'>{plot_html}</div>"
+                                # Add the image directly to the response
+                                response += f"\n\n<img src='{img_src}' width='100%' />"
                                 
                                 # Add note about visualization
                                 response += "\n\n**A visualization has been generated and is displayed above.**"
@@ -263,7 +265,7 @@ def process_text_query(query, history):
     # Add the response to history
     history.append({"role": "assistant", "content": response})
     
-    return "", history, current_plot
+    return "", history
 
 def process_file_upload(files):
     """Process uploaded files and index them"""
@@ -404,8 +406,25 @@ def process_voice_input(audio_path):
     if audio_path is None:
         return "No audio recorded"
     
-    # Since we don't have VoiceAssistant, return a placeholder message
-    return "Voice transcription is not available"
+    try:
+        # Initialize recognizer
+        r = sr.Recognizer()
+        
+        # Load the audio file
+        with sr.AudioFile(audio_path) as source:
+            # Read the audio data
+            audio_data = r.record(source)
+            
+            # Recognize speech using Google Speech Recognition
+            text = r.recognize_google(audio_data)
+            
+            return text
+    except sr.UnknownValueError:
+        return "Could not understand audio"
+    except sr.RequestError as e:
+        return f"Error with speech recognition service: {e}"
+    except Exception as e:
+        return f"Error processing audio: {str(e)}"
 
 def text_to_speech_output(text):
     """Convert text to speech"""
@@ -422,8 +441,25 @@ def text_to_speech_output(text):
     if not last_message:
         return None
     
-    # Since we don't have VoiceAssistant, return None
-    return None
+    try:
+        # Clean the text (remove markdown and HTML)
+        clean_text = re.sub(r'<.*?>', '', last_message)  # Remove HTML tags
+        clean_text = re.sub(r'\*\*(.*?)\*\*', r'\1', clean_text)  # Remove bold markdown
+        clean_text = re.sub(r'\n\n', ' ', clean_text)  # Replace double newlines with space
+        clean_text = re.sub(r'```.*?```', 'Code block removed for speech.', clean_text, flags=re.DOTALL)  # Replace code blocks
+        
+        # Create a temporary file
+        temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+        temp_file.close()
+        
+        # Generate speech
+        tts = gTTS(text=clean_text, lang='en', slow=False)
+        tts.save(temp_file.name)
+        
+        return temp_file.name
+    except Exception as e:
+        print(f"Error generating speech: {str(e)}")
+        return None
 
 def create_test_visualization():
     """Create a test visualization to verify plotting works"""
@@ -508,10 +544,19 @@ with gr.Blocks(title="AI Document Analysis & Voice Assistant") as demo:
     gr.Markdown("Upload documents, ask questions, and get voice responses!")
     
     with gr.Tab("Chat"):
-        chatbot = gr.Chatbot(height=400, type="messages")
+        # Use a custom CSS to ensure images are displayed properly
+        gr.HTML("""
+        <style>
+        .chatbot-container img {
+            max-width: 100%;
+            height: auto;
+            display: block;
+            margin: 10px 0;
+        }
+        </style>
+        """)
         
-        # Add a plot component
-        plot_output = gr.HTML(label="Data Visualization", visible=True, elem_id="plot_container")
+        chatbot = gr.Chatbot(height=500, type="messages", elem_classes="chatbot-container")
         
         with gr.Row():
             with gr.Column(scale=8):
@@ -540,18 +585,16 @@ with gr.Blocks(title="AI Document Analysis & Voice Assistant") as demo:
         submit_btn.click(
             process_text_query, 
             inputs=[msg, chatbot], 
-            outputs=[msg, chatbot, plot_output],
-            postprocess=lambda _, __, fig: gr.update(value=fig, visible=fig is not None)
+            outputs=[msg, chatbot]
         )
         
         msg.submit(
             process_text_query, 
             inputs=[msg, chatbot], 
-            outputs=[msg, chatbot, plot_output],
-            postprocess=lambda _, __, fig: gr.update(value=fig, visible=fig is not None)
+            outputs=[msg, chatbot]
         )
         
-        clear_btn.click(lambda: [None, None, gr.update(visible=False)], None, [chatbot, plot_output, plot_output], queue=False)
+        clear_btn.click(lambda: None, None, [chatbot], queue=False)
         clear_context_btn.click(clear_context, inputs=[], outputs=[chatbot])
         
         voice_btn.click(
@@ -575,16 +618,15 @@ with gr.Blocks(title="AI Document Analysis & Voice Assistant") as demo:
         )
     
     with gr.Tab("Document Upload"):
-        file_upload = gr.File(
-            label="Upload Documents",
-            file_types=[".pdf", ".txt", ".docx", ".csv", ".xlsx"],
-            file_count="multiple"
-        )
-        
         with gr.Row():
-            upload_button = gr.Button("Process & Index Documents", scale=2)
-            flush_db_btn_doc = gr.Button("🗑️ Flush All Databases", variant="stop", scale=1)
+            file_upload = gr.File(
+                label="Upload Documents",
+                file_types=[".pdf", ".txt", ".docx", ".csv", ".xlsx"],
+                file_count="multiple"
+            )
+            flush_db_btn_doc = gr.Button("🗑️ Flush All Databases", variant="stop")
         
+        upload_button = gr.Button("Process & Index Documents")
         upload_output = gr.Textbox(label="Upload Status")
         
         upload_button.click(
@@ -609,8 +651,10 @@ with gr.Blocks(title="AI Document Analysis & Voice Assistant") as demo:
         )
     
     with gr.Tab("Settings"):
-        gr.Markdown("## Database Management")
-        flush_db_btn = gr.Button("🗑️ Flush All Databases", variant="stop", scale=1, min_width=200)
+        with gr.Row():
+            gr.Markdown("## Database Management")
+            flush_db_btn = gr.Button("🗑️ Flush All Databases", variant="stop", scale=1)
+        
         flush_result = gr.Textbox(label="Flush Result")
         
         flush_db_btn.click(

requirements.txt

@@ -10,4 +10,5 @@ langchain-community>=0.0.10
 langchain-groq>=0.0.5
 plotly>=5.14.0 
 gtts>=2.3.1
-SpeechRecognition>=3.10.0
+SpeechRecognition>=3.10.0
+kaleido>=0.2.1