Update app.py

app.py

@@ -1,79 +1,51 @@
-from openai import OpenAI  # Assuming Nvidia client is available in the same library, adjust if necessary
 import streamlit as st
 import os
-from datetime import datetime
+from openai import OpenAI
 
-# Initialize Nvidia client
-client = OpenAI(
-    base_url="https://integrate.api.nvidia.com/v1",  # Nvidia API endpoint
-    api_key=os.environ["NVIDIA_API_KEY"]  # Nvidia API Key from Streamlit secrets
+# Initialize the Nvidia API client using API Key stored in Streamlit secrets
+client =OpenAI(
+  base_url = "https://integrate.api.nvidia.com/v1",
+  api_key = os.getenv("NVIDIA_API_KEY")
 )
 
-st.title("ChatGPT-like clone with Nvidia Nemotron 70B Model")
+# Define Streamlit app layout
+st.title("AWS Well-Architected Review")
+st.write("Get recommendations for optimizing your AWS architecture.")
 
-# Sidebar with instructions and Clear Session button
-with st.sidebar:
-    # Instruction
-    st.markdown("### Instructions 🤖\nThis is a basic chatbot. Ask anything, and the AI will try to help you! The app is supported by Yiqiao Yin.")
-
-    # Add a section to ask the user for the response length
-    st.markdown("#### Select the desired length of the AI response:")
-    response_length = st.radio(
-        "How detailed do you want the response to be?",
-        ('Efficient', 'Medium', 'Academic')
-    )
-
-    # Set max_tokens based on user selection
-    if response_length == 'Efficient':
-        max_tokens = 100
-    elif response_length == 'Medium':
-        max_tokens = 600
-    else:  # 'Academic'
-        max_tokens = 1024
-
-    # Clear
-    if st.button("Clear Session"):
-        st.session_state.clear()
-    st.write(f"Copyright © 2010-{datetime.now().year} Present Yiqiao Yin")
-
-# Initialize session state variables if not already present
-if "nvidia_model" not in st.session_state:
-    st.session_state["nvidia_model"] = "nvidia/llama-3.1-nemotron-70b-instruct"
 
 if "messages" not in st.session_state:
-    # Adding the initial system message
-    st.session_state.messages = [{"role": "system", "content": "You are a helpful assistant."}]
-
-# Render the chat history
-for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.markdown(message["content"])
-
-# Get new user input
-if prompt := st.chat_input("What is up?"):
-    # Add user message to the session state
-    st.session_state.messages.append({"role": "user", "content": prompt})
-    with st.chat_message("user"):
-        st.markdown(prompt)
-
-    # Display assistant's message while waiting for the response
-    with st.chat_message("assistant"):
-        with st.spinner("The assistant is thinking... Please wait."):
-            # Create Nvidia completion request with full conversation history
-            stream = client.chat.completions.create(
-                model=st.session_state["nvidia_model"],
-                messages=st.session_state.messages,  # Include all previous messages in the API call
-                temperature=0.5,
-                top_p=0.7,
-                max_tokens=max_tokens,
-                stream=True,
-            )
-            response_chunks = []
-            for chunk in stream:
-                if chunk.choices[0].delta.content is not None:
-                    response_chunks.append(chunk.choices[0].delta.content)
-            response = "".join(response_chunks)
-            st.markdown(response)
-
-    # Store the assistant response in the session state
-    st.session_state.messages.append({"role": "assistant", "content": response})
+    st.session_state.messages = [
+        {"role": "system", "content": "You are an assistant that provides recommendations based on AWS Well-Architected Review best practices. Focus on the 5 pillars: Operational Excellence, Security, Reliability, Performance Efficiency, and Cost Optimization."}
+    ]
+
+# User input for AWS architecture description
+architecture_input = st.text_area("Describe your AWS architecture:")
+
+# Button to submit the input
+if st.button("Get Recommendations"):
+    if architecture_input:
+        # Add user input to the conversation
+        st.session_state.messages.append({"role": "user", "content": architecture_input})
+        
+        with st.chat_message("assistant"):
+            with st.spinner("Generating recommendations..."):
+                # Create Nvidia completion request with conversation history
+                stream = client.chat.completions.create(
+                    model="nvidia/llama-3.1-nemotron-70b-instruct",  # Nvidia model name
+                    messages=st.session_state.messages,  # Include all messages in the API call
+                    temperature=0.5,
+                    top_p=0.7,
+                    max_tokens=1024,
+                    stream=True,
+                )
+
+                response_chunks = []
+                for chunk in stream:
+                    if chunk.choices[0].delta.content is not None:
+                        response_chunks.append(chunk.choices[0].delta.content)
+                response = "".join(response_chunks)
+                
+                # Display the response as recommendations
+                st.markdown(f"**Recommendations:**\n\n{response}")
+                # Add response to conversation history
+        st.session_state.messages.append({"role": "assistant", "content": response})