Update app.py

app.py

@@ -13,6 +13,7 @@ from langchain_aws import ChatBedrock
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.runnables import RunnablePassthrough
 from langchain_core.output_parsers import StrOutputParser
+from qdrant_client import QdrantClient
 import re
 import json
 
@@ -50,10 +51,15 @@ def load_wikipedia_documents():
 @st.cache_resource
 def split_documents(_documents):
     """Split documents into chunks."""
-    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    chunks = splitter.split_documents(_documents)
-    logger.info(f"Split into {len(chunks)} chunks")
-    return chunks
+    try:
+        splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+        chunks = splitter.split_documents(_documents)
+        logger.info(f"Split into {len(chunks)} chunks")
+        return chunks
+    except Exception as e:
+        logger.error(f"Error splitting documents: {e}")
+        st.error(f"Failed to split documents: {e}")
+        return []
 
 @st.cache_resource
 def initialize_embeddings():
@@ -72,16 +78,42 @@ def initialize_embeddings():
 
 @st.cache_resource
 def store_in_qdrant(_chunks, _embeddings):
-    """Store document chunks in a hosted Qdrant instance."""
+    """Store document chunks in a hosted Qdrant instance after deleting existing collection."""
     try:
+        # Initialize Qdrant client
+        client = QdrantClient(
+            url=os.getenv("QDRANT_URL"),
+            api_key=os.getenv("QDRANT_API_KEY")
+        )
+        
+        # Delete existing collection if it exists
+        collection_name = "wikipedia_chunks"
+        try:
+            client.delete_collection(collection_name)
+            logger.info(f"Deleted existing Qdrant collection: {collection_name}")
+        except Exception as e:
+            logger.warning(f"No existing collection {collection_name} to delete or error: {e}")
+
+        # Create and populate new collection
         vector_store = Qdrant.from_documents(
             documents=_chunks,
             embedding=_embeddings,
             url=os.getenv("QDRANT_URL"),
             api_key=os.getenv("QDRANT_API_KEY"),
-            collection_name="wikipedia_chunks"
+            collection_name=collection_name
         )
-        logger.info(f"Stored {len(_chunks)} chunks in Qdrant at {os.getenv('QDRANT_URL')}")
+        
+        # Verify storage by checking collection size
+        collection_info = client.get_collection(collection_name)
+        stored_points = collection_info.points_count
+        logger.info(f"Stored {stored_points} chunks in Qdrant at {os.getenv('QDRANT_URL')}")
+        if stored_points == 0:
+            logger.error("No documents stored in Qdrant collection")
+            st.error("No documents stored in Qdrant collection")
+            return None
+        if stored_points != len(_chunks):
+            logger.warning(f"Expected {len(_chunks)} chunks, but stored {stored_points} in Qdrant")
+        
         return vector_store
     except Exception as e:
         logger.error(f"Error storing in Qdrant: {e}")