Updare retrive creation

seminar_edition_ai.py

@@ -278,13 +278,18 @@ def predictArgumentQuestionBuild(questionAnswer, llmModelList = []):
       )
   global retriever
   global HISTORY_ANSWER
+  global embed_model
+
+  if embed_model == None:
+      llmBuilder = GeminiLLM()
+      embed_model = llmBuilder.getEmbeddingsModel()
 
   if retriever == None:
       doc = Document(page_content="text", metadata={"source": "local"})
 
       vectorstore = Chroma.from_documents(
           documents=[doc],
-          embedding=embed_model,
+          embedding = embed_model,
           persist_directory="chroma_db_dir_sermon",  # Local mode with in-memory storage only
           collection_name="sermon_lab_ai"
       )