diff --git a/models/index_model.py b/models/index_model.py
index 5345952..5e7965b 100644
--- a/models/index_model.py
+++ b/models/index_model.py
@@ -76,7 +76,7 @@ async def get_and_query(
             llm_predictor=llm_predictor,
             refine_template=CHAT_REFINE_PROMPT,
             embed_model=embed_model,
-            #optimizer=SentenceEmbeddingOptimizer(threshold_cutoff=0.7)
+            # optimizer=SentenceEmbeddingOptimizer(threshold_cutoff=0.7)
         )
     else:
         response = await index.aquery(
@@ -86,7 +86,7 @@ async def get_and_query(
             embed_model=embed_model,
             similarity_top_k=nodes,
             refine_template=CHAT_REFINE_PROMPT,
-            #optimizer=SentenceEmbeddingOptimizer(threshold_cutoff=0.7)
+            # optimizer=SentenceEmbeddingOptimizer(threshold_cutoff=0.7)
         )
     return response
 
@@ -922,7 +922,16 @@ class Index_handler:
         try:
             embedding_model = OpenAIEmbedding()
             embedding_model.last_token_usage = 0
-            response = await get_and_query(ctx.user.id, self.index_storage, query, response_mode, nodes, self.llm_predictor, embedding_model, child_branch_factor)
+            response = await get_and_query(
+                ctx.user.id,
+                self.index_storage,
+                query,
+                response_mode,
+                nodes,
+                self.llm_predictor,
+                embedding_model,
+                child_branch_factor,
+            )
             print("The last token usage was ", self.llm_predictor.last_token_usage)
             await self.usage_service.update_usage(
                 self.llm_predictor.last_token_usage, chatgpt=True
diff --git a/models/search_model.py b/models/search_model.py
index 5f3f77c..031d53a 100644
--- a/models/search_model.py
+++ b/models/search_model.py
@@ -455,9 +455,25 @@ class Search:
         embedding_model.last_token_usage = 0
 
         if not deep:
-            response = await index.aquery(query, embed_model=embedding_model, llm_predictor=llm_predictor, refine_template=CHAT_REFINE_PROMPT, similarity_top_k=nodes or DEFAULT_SEARCH_NODES, text_qa_template=self.qaprompt,  response_mode=response_mode)
+            response = await index.aquery(
+                query,
+                embed_model=embedding_model,
+                llm_predictor=llm_predictor,
+                refine_template=CHAT_REFINE_PROMPT,
+                similarity_top_k=nodes or DEFAULT_SEARCH_NODES,
+                text_qa_template=self.qaprompt,
+                response_mode=response_mode,
+            )
         else:
-            response = await index.aquery(query, embed_model=embedding_model, llm_predictor=llm_predictor, refine_template=CHAT_REFINE_PROMPT, similarity_top_k=nodes or DEFAULT_SEARCH_NODES, text_qa_template=self.qaprompt, response_mode=response_mode)
+            response = await index.aquery(
+                query,
+                embed_model=embedding_model,
+                llm_predictor=llm_predictor,
+                refine_template=CHAT_REFINE_PROMPT,
+                similarity_top_k=nodes or DEFAULT_SEARCH_NODES,
+                text_qa_template=self.qaprompt,
+                response_mode=response_mode,
+            )
 
         await self.usage_service.update_usage(
             llm_predictor.last_token_usage, chatgpt=True