Update app.py

app.py

@@ -6,23 +6,25 @@ from openai import OpenAI
 from llama_index.node_parser import SemanticSplitterNodeParser
 from llama_index.embeddings import OpenAIEmbedding
 from llama_index.ingestion import IngestionPipeline
-from pinecone.grpc import PineconeGRPC
-from llama_index.vector_stores import PineconeVectorStore
-from llama_index import VectorStoreIndex
-from llama_index.retrievers import VectorIndexRetriever
-from llama_index.query_engine import RetrieverQueryEngine
+from pinecone import PineconeClient, Index, create_index
 
 # Set OpenAI API key from Streamlit secrets
+pinecone_api_key = os.getenv("PINECONE_API_KEY") 
 openai_api_key = os.getenv("OPENAI_API_KEY")
-pinecone_api_key = os.getenv("PINECONE_API_KEY")
 
 # Initialize OpenAI client
 client = OpenAI(api_key=openai_api_key)
 
 # Initialize Pinecone connection
-pc = PineconeGRPC(api_key=pinecone_api_key)
+pinecone_client = PineconeClient(api_key=pinecone_api_key)
 index_name = "annualreport"
-pinecone_index = pc.Index(index_name)
+
+# Check if the index exists, if not, create it
+if index_name not in pinecone_client.list_indexes():
+    create_index(name=index_name, dimension=1536)  # Dimension should match your embedding model
+
+# Initialize Pinecone index
+pinecone_index = Index(index_name)
 vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
 
 # Initialize vector index and retriever