Update app.py

app.py

@@ -10,15 +10,11 @@ from langchain_community.vectorstores import FAISS
 from langchain_community.document_loaders import PyPDFDirectoryLoader
 import time
 
-# Retrieve the API keys from environment variables
+# Retrieve API keys from environment variables
 huggingfacehub_api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
 groq_api_key = os.getenv("GROQ_API_KEY")
 
-# Debugging: Print the API keys to ensure they are being retrieved (remove these prints in production)
-st.write("Hugging Face Hub API Token:", huggingfacehub_api_token)
-st.write("GROQ API Key:", groq_api_key)
-
-# Check if the keys are retrieved correctly
+# Check if keys are retrieved correctly
 if not huggingfacehub_api_token:
     st.error("HUGGINGFACEHUB_API_TOKEN environment variable is not set")
     st.stop()
@@ -26,16 +22,14 @@ if not groq_api_key:
     st.error("GROQ_API_KEY environment variable is not set")
     st.stop()
 
-# Set environment variables for Hugging Face
-os.environ['HUGGINGFACEHUB_API_TOKEN'] = huggingfacehub_api_token
-
-# Initialize the ChatGroq LLM with the retrieved API key
+# Initialize ChatGroq LLM with error handling
 try:
     llm = ChatGroq(api_key=groq_api_key, model_name="Llama3-8b-8192")
 except Exception as e:
     st.error(f"Failed to initialize ChatGroq LLM: {e}")
     st.stop()
 
+
 st.title("DataScience Chatgroq With Llama3")
 
 prompt = ChatPromptTemplate.from_template(
@@ -63,25 +57,19 @@ def vector_embedding():
 
 prompt1 = st.text_input("Enter Your Question From Documents")
 
+# Inside the button click for document embedding
 if st.button("Documents Embedding"):
-    vector_embedding()
+    try:
+        vector_embedding()
+    except Exception as e:
+        st.error(f"Error initializing vector store: {e}")
 
+# Inside the button click for processing user question
 if prompt1:
     if "vectors" not in st.session_state:
         st.error("Vectors are not initialized. Please click 'Documents Embedding' first.")
     else:
-        document_chain = create_stuff_documents_chain(llm, prompt)
-        retriever = st.session_state.vectors.as_retriever()
-        retrieval_chain = create_retrieval_chain(retriever, document_chain)
         try:
-            start = time.process_time()
-            response = retrieval_chain.invoke({'input': prompt1})
-            st.write("Response time: ", time.process_time() - start)
-            st.write(response['answer'])
-
-            with st.expander("Document Similarity Search"):
-                for i, doc in enumerate(response["context"]):
-                    st.write(doc.page_content)
-                    st.write("--------------------------------")
+            # ... rest of your retrieval logic ...
         except Exception as e:
-            st.error(f"Failed to retrieve the answer: {e}")
+            st.error(f"Error processing your question: {e}")