Update app.py

app.py

@@ -6,26 +6,16 @@ from langchain.prompts import ChatPromptTemplate
 from langchain_groq import ChatGroq
 from langchain_community.embeddings import HuggingFaceEmbeddings
 
-# --- Load Environment Variables ---
-# This line loads the variables from a .env file during local development.
-# On Hugging Face Spaces, secrets are set in the repository settings.
 load_dotenv()
 
-# --- App Configuration ---
 st.set_page_config(
     page_title="AgriChat",
     page_icon="🌱",
     layout="centered"
 )
 
-# --- Model and Embeddings Setup ---
 @st.cache_resource
 def load_resources():
-    """
-    Load the language model, embeddings, and vector store.
-    Using st.cache_resource ensures these heavy resources are loaded only once.
-    """
-    # Initialize HuggingFace embeddings for vectorization
     model_name = "sentence-transformers/all-mpnet-base-v2"
     try:
         hf_embeddings = HuggingFaceEmbeddings(
@@ -37,15 +27,12 @@ def load_resources():
         st.error(f"Failed to load embeddings model. Error: {e}")
         return None, None, None
 
-    # Load the FAISS vector store from the local directory
-    # Ensure the 'faiss_index_datamodel' directory is in the same folder as this script
     try:
         vectorstore = FAISS.load_local("faiss_index_datamodel", hf_embeddings, allow_dangerous_deserialization=True)
     except Exception as e:
         st.error(f"Failed to load the vector store. Make sure 'faiss_index_datamodel' is present. Error: {e}")
         return hf_embeddings, None, None
 
-    # Initialize the Groq LLM, fetching the API key from environment variables
     groq_api_key = os.getenv("GROQ_API_KEY")
     if not groq_api_key:
         st.error("GROQ_API_KEY not found. Please add it to your repository secrets on Hugging Face Spaces.")
@@ -58,11 +45,8 @@ def load_resources():
     )
     return hf_embeddings, vectorstore, llm
 
-# Load the resources and handle potential loading errors
 hf_embeddings, vectorstore, llm = load_resources()
 
-# --- Prompt Template ---
-# This template guides the LLM on how to structure its response.
 prompt_template = ChatPromptTemplate.from_template(
     """You are a knowledgeable and helpful agricultural expert. Your task is to provide clear, concise, and accurate answers to questions on various agricultural topics.
     **Guidelines:**
@@ -87,54 +71,39 @@ prompt_template = ChatPromptTemplate.from_template(
     **Answer:**"""
 )
 
-# Create the processing chain only if all components loaded successfully
 if llm and prompt_template:
     chain = prompt_template | llm
 else:
     chain = None
 
-# --- Streamlit UI ---
 st.title("🌱 AgriChat")
 st.markdown("Your AI assistant for agricultural questions, powered by Llama 3.1.")
 
-# Initialize chat history in session state
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
-# Display chat messages from history on app rerun
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-# Main chat input and response logic
 if prompt := st.chat_input("Ask your agricultural question:"):
-    # Ensure the app is fully loaded before processing input
     if not chain or not vectorstore:
         st.warning("The application is not fully initialized. Please check for error messages above and ensure your API key is set correctly.")
     else:
-        # Add user message to chat history and display it
         st.session_state.messages.append({"role": "user", "content": prompt})
         with st.chat_message("user"):
             st.markdown(prompt)
 
-        # Process the prompt and display the assistant's response
         with st.chat_message("assistant"):
             with st.spinner("Finding the best answer..."):
-                # Retrieve relevant documents from the vector store
                 relevant_documents = vectorstore.similarity_search_with_score(prompt, k=4)
                 context = "\n\n".join([doc[0].page_content for doc in relevant_documents])
-
-                # Invoke the LLM chain to get the response
                 response = chain.invoke({"context": context, "question": prompt})
                 response_content = response.content
-
             st.markdown(response_content)
 
-        # Add assistant response to chat history
         st.session_state.messages.append({"role": "assistant", "content": response_content})
 
-
-# --- Sidebar Instructions ---
 st.sidebar.header("How to Use")
 st.sidebar.markdown("""
 - This app is designed to answer your farming and agriculture-related questions.