Update app.py

app.py

@@ -10,10 +10,10 @@ from llama_index.core import Settings
 import os
 import base64
 
-# Load environment variables for HuggingFace API
+# Load environment variables for HuggingFace API tokens
 load_dotenv()
 
-# Configure the Llama index settings
+# Setup HuggingFace API for llama_index (used in the PDF chat functionality)
 Settings.llm = HuggingFaceInferenceAPI(
     model_name="google/gemma-1.1-7b-it",
     tokenizer_name="google/gemma-1.1-7b-it",
@@ -26,42 +26,29 @@ Settings.embed_model = HuggingFaceEmbedding(
     model_name="BAAI/bge-small-en-v1.5"
 )
 
-# Define directories for persistent storage and data
+# Paths for file storage
 PERSIST_DIR = "./db"
 DATA_DIR = "data"
 
-# Ensure data directory exists
 os.makedirs(DATA_DIR, exist_ok=True)
 os.makedirs(PERSIST_DIR, exist_ok=True)
 
-# Function to display PDF in Streamlit
-def displayPDF(file):
-    with open(file, "rb") as f:
-        base64_pdf = base64.b64encode(f.read()).decode('utf-8')
-    pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="600" type="application/pdf"></iframe>'
-    st.markdown(pdf_display, unsafe_allow_html=True)
-
-# Function to handle PDF ingestion
+# PDF data ingestion function
 def data_ingestion():
     documents = SimpleDirectoryReader(DATA_DIR).load_data()
     storage_context = StorageContext.from_defaults()
     index = VectorStoreIndex.from_documents(documents)
     index.storage_context.persist(persist_dir=PERSIST_DIR)
 
-# Function to handle user queries
+# PDF query handler
 def handle_query(query):
     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
     index = load_index_from_storage(storage_context)
     chat_text_qa_msgs = [
-    (
-        "user",
-        """You are a Q&A assistant named AskAI, created by Vatsa. You have a specific response programmed for when users ask about your creator, Suriya. The response is: "I was created by Suriya, an enthusiast in Artificial Intelligence."
-        Context:
-        {context_str}
-        Question:
-        {query_str}
-        """
-    )
+        (
+            "user",
+            """You are a Q&A assistant named AskAI, created by Vatsa. You provide AI-powered answers to PDF documents."""
+        )
     ]
     text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
     
@@ -75,40 +62,110 @@ def handle_query(query):
     else:
         return "Sorry, I couldn't find an answer."
 
-# Streamlit interface
-st.title("Integrated App: Gradio & Streamlit")
-st.markdown("### PDF Q&A + Machine Health Prediction")
+# Machine Health Predictor Gradio App
+def create_gradio_app():
+    with open('logistic_regression_model.pkl', 'rb') as model_file:
+        model = pickle.load(model_file)
+
+    with open('feature_columns.pkl', 'rb') as col_file:
+        feature_columns = pickle.load(col_file)
 
-# Gradio App via iframe
-st.markdown("#### Machine Health Prediction App (Gradio)")
-gradio_app_url = "http://localhost:7860"  # URL where Gradio app is running
-st.markdown(f'<iframe src="{gradio_app_url}" width="100%" height="800"></iframe>', unsafe_allow_html=True)
+    def predict_status(air_temp, proc_temp, speed, torque, tool_wear):
+        sample_input = {
+            "Air temperature [K]": air_temp,
+            "Process temperature [K]": proc_temp,
+            "Rotational speed [rpm]": speed,
+            "Torque [Nm]": torque,
+            "Tool wear [min]": tool_wear
+        }
+        sample_df = pd.DataFrame([sample_input])
+        for col in feature_columns:
+            if col not in sample_df.columns:
+                sample_df[col] = 0
+        sample_df = sample_df[feature_columns]
+        prediction = model.predict(sample_df)[0]
 
-# Streamlit section for PDF upload and chat
-st.markdown("#### PDF Chatbot App (Streamlit)")
+        reasons = []
+        acceptable_ranges = {
+            "Air temperature [K]": (150, 500),
+            "Process temperature [K]": (150, 500),
+            "Rotational speed [rpm]": (500, 1500),
+            "Torque [Nm]": (100, 800),
+            "Tool wear [min]": (50, 300)
+        }
 
-if 'messages' not in st.session_state:
-    st.session_state.messages = [{'role': 'assistant', "content": 'Hello! Upload a PDF and ask me anything about its content.'}]
+        if air_temp < 150:
+            reasons.append("• The air temperature is too low.")
+        elif air_temp > 500:
+            reasons.append("• The air temperature is too high.")
+        if proc_temp < 150:
+            reasons.append("• The process temperature is below normal.")
+        elif proc_temp > 500:
+            reasons.append("• The process temperature is too high.")
+        if speed < 500:
+            reasons.append("• The rotational speed is too low.")
+        elif speed > 1500:
+            reasons.append("• The rotational speed is too high.")
+        if torque < 100:
+            reasons.append("• The torque is too low.")
+        elif torque > 800:
+            reasons.append("• The torque is too high.")
+        if tool_wear < 50:
+            reasons.append("• Tool wear is minimal.")
+        elif tool_wear > 300:
+            reasons.append("• Tool wear is high.")
 
-with st.sidebar:
-    st.title("Menu:")
-    uploaded_file = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button")
-    if st.button("Submit & Process"):
-        with st.spinner("Processing..."):
-            filepath = "data/saved_pdf.pdf"
+        if prediction == 0:
+            result_message = "🔴 Machine is NOT working.\n" + "\n".join(reasons) if reasons else "No specific reason."
+        else:
+            result_message = "🟢 Machine is working fine."
+
+        return result_message
+
+    return gr.Interface(
+        fn=predict_status,
+        inputs=[
+            gr.Slider(label="Air Temperature (K)", minimum=0, maximum=1000, step=0.01, value=300),
+            gr.Slider(label="Process Temperature (K)", minimum=0, maximum=1000, step=0.01, value=300),
+            gr.Slider(label="Rotational Speed (rpm)", minimum=0, maximum=2000, step=1, value=1000),
+            gr.Slider(label="Torque (Nm)", minimum=0, maximum=1000, step=0.1, value=500),
+            gr.Slider(label="Tool Wear (min)", minimum=0, maximum=1000, step=1, value=100)
+        ],
+        outputs="text",
+        title="Smart Machine Health Predictor",
+        description="Provide machine parameters to predict machine status."
+    )
+
+# Display Gradio App in Streamlit
+def run_gradio_app():
+    app = create_gradio_app()
+    app.launch(share=True)
+
+# Streamlit Application - Combining Gradio and PDF Chatbot
+def main():
+    st.title("Integrated Gradio & PDF Chat App")
+    st.sidebar.title("Choose Application")
+
+    app_choice = st.sidebar.selectbox("Select App", ("Machine Health Prediction (Gradio)", "PDF Chat (Streamlit)"))
+
+    if app_choice == "Machine Health Prediction (Gradio)":
+        st.write("Running the Machine Health Prediction app...")
+        run_gradio_app()
+    elif app_choice == "PDF Chat (Streamlit)":
+        st.write("PDF Chatbot Application")
+        uploaded_file = st.sidebar.file_uploader("Upload PDF")
+        
+        if uploaded_file:
+            filepath = os.path.join(DATA_DIR, "saved_pdf.pdf")
             with open(filepath, "wb") as f:
                 f.write(uploaded_file.getbuffer())
-            # displayPDF(filepath)  # Display the uploaded PDF
-            data_ingestion()  # Process PDF every time new file is uploaded
-            st.success("Done")
-
-user_prompt = st.chat_input("Ask me anything about the content of the PDF:")
-if user_prompt:
-    st.session_state.messages.append({'role': 'user', "content": user_prompt})
-    response = handle_query(user_prompt)
-    st.session_state.messages.append({'role': 'assistant', "content": response})
+            data_ingestion()
+            st.success("PDF processed.")
 
-for message in st.session_state.messages:
-    with st.chat_message(message['role']):
-        st.write(message['content'])
+        user_prompt = st.chat_input("Ask me anything about the PDF:")
+        if user_prompt:
+            response = handle_query(user_prompt)
+            st.write(response)
 
+if __name__ == "__main__":
+    main()