Upload app.py with huggingface_hub

app.py

@@ -71,7 +71,7 @@ from datetime import datetime
 # Fetch secrets from Hugging Face Spaces
 api_key = os.environ["API_KEY"]
 endpoint = os.environ["OPENAI_API_BASE"]
-llama_api_key = os.environ['GROQ_API_KEY']
+llama_api_key = os.environ['LLAMA_API_KEY']
 mem0_api_key = os.environ['mem0']
 
 # Initialize the OpenAI embedding function for Chroma
@@ -122,7 +122,7 @@ class AgentState(TypedDict):
 
 def expand_query(state):
     """
-    Expands the user query to improve retrieval of nutrition disorder-related information.
+    Expands the user query to improve retrieval of climate-related information.
 
     Args:
         state (Dict): The current state of the workflow, containing the user query.
@@ -131,8 +131,8 @@ def expand_query(state):
         Dict: The updated state with the expanded query.
     """
     print("---------Expanding Query---------")
-    system_message = '''You are a climate change domain expert assisting in answering questions related to climate change mitigation and climate change solutions information.
-Convert the user query into something that an environment professional would understand. Use domain related words.
+    system_message = '''You are a domain expert assisting in answering questions related to climate-related information.
+Convert the user query into something that a climate professional would understand. Use domain related words.
 Perform query expansion on the question received. If there are multiple common ways of phrasing a user question \
 or common synonyms for key words in the question, make sure to return multiple versions \
 of the query with the different phrasings.
@@ -210,7 +210,7 @@ def retrieve_context(state):
 
 def craft_response(state: Dict) -> Dict:
     """
-    Generates a response using the retrieved context, focusing on nutrition disorders.
+    Generates a response using the retrieved context, focusing on climate solutions.
 
     Args:
         state (Dict): The current state of the workflow, containing the query and retrieved context.
@@ -219,7 +219,7 @@ def craft_response(state: Dict) -> Dict:
         Dict: The updated state with the generated response.
     """
     print("---------craft_response---------")
-    system_message = '''you are a smart nutrition disorder specialist. Use the context and feedback to respond to the query.
+    system_message = '''you are a smart climate specialist. Use the context and feedback to respond to the query.
     The answer you provide must come from the context and feedback provided.
     If information provided is not enough to answer the query response with 'I don't know the answer. Not in my records'''
 
@@ -498,13 +498,13 @@ def agentic_rag(query: str):
 #================================ Guardrails ===========================#
 llama_guard_client = Groq(api_key=llama_api_key)
 # Function to filter user input with Llama Guard
-def filter_input_with_llama_guard(user_input, model="llama-guard-3-8b"):
+def filter_input_with_llama_guard(user_input, model="llama-guard-4-12b"):
     """
     Filters user input using Llama Guard to ensure it is safe.
 
     Parameters:
     - user_input: The input provided by the user.
-    - model: The Llama Guard model to be used for filtering (default is "llama-guard-3-8b").
+    - model: The Llama Guard model to be used for filtering (default is "llama-guard-4-12b").
 
     Returns:
     - The filtered and safe input.
@@ -524,7 +524,7 @@ def filter_input_with_llama_guard(user_input, model="llama-guard-3-8b"):
 
 #============================= Adding Memory to the agent using mem0 ===============================#
 
-class climateBot:
+class ClimateBot:
     def __init__(self):
         """
         Initialize the NutritionBot class, setting up memory, the LLM client, tools, and the agent executor.
@@ -586,7 +586,7 @@ class AgentState(TypedDict):
 
 def expand_query(state):
     """
-    Expands the user query to improve retrieval of nutrition disorder-related information.
+    Expands the user query to improve retrieval of climate-related information.
 
     Args:
         state (Dict): The current state of the workflow, containing the user query.
@@ -595,8 +595,8 @@ def expand_query(state):
         Dict: The updated state with the expanded query.
     """
     print("---------Expanding Query---------")
-    system_message = '''You are a climate expert assisting in answering questions related to climate change mitigation strategies and information.
-Convert the user query into something that a healthcare professional would understand. Use domain related words.
+    system_message = '''You are a domain expert assisting in answering questions related to climate-related information.
+Convert the user query into something that a climate professional would understand. Use domain related words.
 Perform query expansion on the question received. If there are multiple common ways of phrasing a user question \
 or common synonyms for key words in the question, make sure to return multiple versions \
 of the query with the different phrasings.
@@ -675,7 +675,7 @@ def retrieve_context(state):
 
 def craft_response(state: Dict) -> Dict:
     """
-    Generates a response using the retrieved context, focusing on nutrition disorders.
+    Generates a response using the retrieved context, focusing on climate solutions.
 
     Args:
         state (Dict): The current state of the workflow, containing the query and retrieved context.
@@ -684,7 +684,7 @@ def craft_response(state: Dict) -> Dict:
         Dict: The updated state with the generated response.
     """
     print("---------craft_response---------")
-    system_message = '''you are a smart nutrition disorder specialist. Use the context and feedback to respond to the query.
+    system_message = '''you are a smart climate specialist. Use the context and feedback to respond to the query.
     The answer you provide must come from the context and feedback provided.
     If information provided is not enough to answer the query response with 'I don't know the answer. Not in my records'''
 
@@ -964,13 +964,13 @@ def agentic_rag(query: str):
 #================================ Guardrails ===========================#
 llama_guard_client = Groq(api_key=llama_api_key)
 # Function to filter user input with Llama Guard
-def filter_input_with_llama_guard(user_input, model="llama-guard-3-8b"):
+def filter_input_with_llama_guard(user_input, model="llama-guard-4-12b"):
     """
     Filters user input using Llama Guard to ensure it is safe.
 
     Parameters:
     - user_input: The input provided by the user.
-    - model: The Llama Guard model to be used for filtering (default is "llama-guard-3-8b").
+    - model: The Llama Guard model to be used for filtering (default is "llama-guard-4-12b").
 
     Returns:
     - The filtered and safe input.
@@ -990,10 +990,10 @@ def filter_input_with_llama_guard(user_input, model="llama-guard-3-8b"):
 
 #============================= Adding Memory to the agent using mem0 ===============================#
 
-class climateBot:
+class ClimateBot:
     def __init__(self):
         """
-        Initialize the climateBot class, setting up memory, the LLM client, tools, and the agent executor.
+        Initialize the ClimateBot class, setting up memory, the LLM client, tools, and the agent executor.
         """
 
 # Initialize a memory client to store and retrieve customer interactions
@@ -1011,17 +1011,17 @@ class climateBot:
         tools = [agentic_rag]
 
         # Define the system prompt to set the behavior of the chatbot
-        system_prompt = """You are a caring and knowledgeable Climate Agent, specializing in climate change mitigation strategies and climate action recommendations. Your goal is to provide accurate, empathetic, and tailored nutritional recommendations while ensuring a seamless customer experience.
+        system_prompt = """You are a caring and knowledgeable Climate Agent, specializing in climate-related guidance. Your goal is to provide accurate, empathetic, and tailored climate related solutions while ensuring a seamless customer experience.
                           Guidelines for Interaction:
                           Maintain a polite, professional, and reassuring tone.
-                          Show genuine empathy for customer concerns and health challenges.
+                          Show genuine empathy for customer concerns and climate challenges.
                           Reference past interactions to provide personalized and consistent advice.
-                          Engage with the customer by asking about their location, top climate business priorities and company size before offering recommendations.
+                          Engage with the customer by asking about their company size, industry, and location before offering recommendations.
                           Ensure consistent and accurate information across conversations.
                           If any detail is unclear or missing, proactively ask for clarification.
-                          Always use the agentic_rag tool to retrieve up-to-date and evidence-based climate solution insights.
+                          Always use the agentic_rag tool to retrieve up-to-date and evidence-based climate insights.
                           Keep track of ongoing issues and follow-ups to ensure continuity in support.
-                          Your primary goal is to help customers make informed climate solution decisions that align with their specific circumstances and business preferences.
+                          Your primary goal is to help customers make informed climate impact decisions that align with their company size, industry and location.
 
         """
 
@@ -1141,10 +1141,10 @@ class climateBot:
 #=====================User Interface using streamlit ===========================#
 def climate_streamlit():
     """
-    A Streamlit-based UI for the Climate Agent.
+    A Streamlit-based UI for the Climate Specialist Agent.
     """
-    st.title("ClimateBot")
-    st.write("Ask me anything about climate solutions and actions to help your business achieve net zero.")
+    st.title("Climate Specialist")
+    st.write("Ask me anything about climate change, causes, impact, solutions and more.")
     st.write("Type 'exit' to end the conversation.")
 
     # Initialize session state for chat history and user_id if they don't exist
@@ -1162,7 +1162,7 @@ def climate_streamlit():
                 st.session_state.user_id = user_id
                 st.session_state.chat_history.append({
                     "role": "assistant",
-                    "content": f"Welcome, {user_id}! How can I help you climate action recommendations today?"
+                    "content": f"Welcome, {user_id}! How can I help you with climate solutions today?"
                 })
                 st.session_state.login_submitted = True  # Set flag to trigger rerun
         if st.session_state.get("login_submitted", False):
@@ -1181,7 +1181,7 @@ def climate_streamlit():
                 st.session_state.chat_history.append({"role": "user", "content": "exit"})
                 with st.chat_message("user"):
                     st.write("exit")
-                goodbye_msg = "Goodbye! Feel free to return if you have more questions about climate action recommendations."
+                goodbye_msg = "Goodbye! Feel free to return if you have more questions about climate change."
                 st.session_state.chat_history.append({"role": "assistant", "content": goodbye_msg})
                 with st.chat_message("assistant"):
                     st.write(goodbye_msg)
@@ -1201,7 +1201,7 @@ def climate_streamlit():
             if filtered_result in ["safe", "unsafe S6", "unsafe S7"]:  # Blanks #3, #4, #5: Fill in with allowed safe statuses (e.g., "safe", "unsafe S7", "unsafe S6")
                 try:
                     if 'chatbot' not in st.session_state:
-                        st.session_state.chatbot = climateBot()  # Blank #6: Fill in with the chatbot class initialization (e.g., NutritionBot)
+                        st.session_state.chatbot = ClimateBot()  # Blank #6: Fill in with the chatbot class initialization (e.g., ClimateBot)
                     response = st.session_state.chatbot.handle_customer_query(st.session_state.user_id, user_query)
                     # Blank #7: Fill in with the method to handle queries (e.g., handle_customer_query)
                     st.write(response)