Update app.py

app.py

@@ -10,84 +10,73 @@ import streamlit as st
 from dotenv import load_dotenv
 
 load_dotenv()
-
 PINECONE_API_KEY = os.getenv('PINECONE_API_KEY')
 PINECONE_ENV = os.getenv('PINECONE_ENV')
 OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
 os.environ['OPENAI_API_KEY'] = OPENAI_API_KEY
 
-
-
 @st.cache_resource
 def embedding_db():
-    # we use the openAI embedding model
     embeddings = OpenAIEmbeddings()
-
-    # Initialize Pinecone: Correct Indentation
     pc = pinecone.init(
-        api_key=PINECONE_API_KEY, 
-        environment=PINECONE_ENV 
+        api_key=PINECONE_API_KEY,
+        environment=PINECONE_ENV
     )
 
+    # Check if index exists, create if needed
+    if 'langchain-demo-indexes' not in pc.list_indexes().names():
+        pc.create_index(
+            name='langchain-demo-indexes',
+            dimension=1536, # Adjust dimension if needed
+            metric='euclidean'        
+        )
+
+    docs_split = doc_preprocessing()  # Make sure this function is defined
+    doc_db = Pinecone.from_documents(
+        docs_split,
+        embeddings,
+        index_name='langchain-demo-indexes',
+        client=pc
+    )
+    return doc_db
+
 def doc_preprocessing():
     loader = DirectoryLoader(
         'data/',
-        glob='**/*.pdf',     # only the PDFs
+        glob='**/*.pdf', 
         show_progress=True
     )
     docs = loader.load()
     text_splitter = CharacterTextSplitter(
-        chunk_size=1000, 
+        chunk_size=1000,
         chunk_overlap=0
     )
     docs_split = text_splitter.split_documents(docs)
     return docs_split
 
-
-
-
-#     docs_split = doc_preprocessing()
-
-#     # Check if index exists, create if needed
-#     if 'langchain-demo-indexes' not in pc.list_indexes().names(): 
-#         pc.create_index(
-#            name='langchain-demo-indexes',
-#            dimension=1536, # Adjust dimension if needed
-#            metric='euclidean', 
-#            spec=ServerlessSpec(cloud='aws', region='us-west-2') 
-#         )
-
-#     doc_db = Pinecone.from_documents(
-#         docs_split,
-#         embeddings,
-#         index_name='langchain-demo-indexes',
-#         client=pc  # Pass the Pinecone object
-#     )
-#     return doc_db
-
-# llm = ChatOpenAI()
-# doc_db = embedding_db()
-
 def retrieval_answer(query):
-    chat_model = ChatOpenAI()  # Create the LLM instance
+    chat_model = ChatOpenAI() 
     qa = RetrievalQA.from_chain_type(
-        llm=chat_model,   # Pass the chat_model instance 
+        llm=chat_model,   
         chain_type='stuff',
         retriever=doc_db.as_retriever(),
-    )
-    query = query
+    )   
     result = qa.run(query)
     return result
 
 def main():
     st.title("Question and Answering App powered by LLM and Pinecone")
-
     text_input = st.text_input("Ask your query...") 
+
     if st.button("Ask Query"):
-        if len(text_input)>0:
+        if len(text_input) > 0:
             st.info("Your Query: " + text_input)
-            answer = retrieval_answer(text_input)
+
+            # Potential loading message
+            with st.spinner("Processing your query..."):
+                doc_db = embedding_db()  # Create the embedding database
+                answer = retrieval_answer(text_input)
             st.success(answer)
 
-if __name__ == "__main__":
-    main()
+if __name__ == "__main__":    
+    main()