Updare retrive creation

seminar_edition_ai.py

@@ -278,6 +278,19 @@ def predictArgumentQuestionBuild(questionAnswer, llmModelList = []):
       )
   global retriever
   global HISTORY_ANSWER
+
+  if retriever == None:
+      doc = Document(page_content="text", metadata={"source": "local"})
+
+      vectorstore = Chroma.from_documents(
+          documents=[doc],
+          embedding=embed_model,
+          persist_directory="chroma_db_dir_sermon",  # Local mode with in-memory storage only
+          collection_name="sermon_lab_ai"
+      )
+      retriever = vectorstore.as_retriever(
+          search_kwargs={"k": 3}
+      )
   answer = askQuestionEx(
      "",
       chain,