diff --git a/application/api/answer/routes.py b/application/api/answer/routes.py
index 6a4a0929..aba2b88e 100644
--- a/application/api/answer/routes.py
+++ b/application/api/answer/routes.py
@@ -455,7 +455,7 @@ class Answer(Resource):
 
         try:
             question = data["question"]
-            history = data.get("history", [])
+            history = str(limit_chat_history(json.loads(data.get("history", []))))
             conversation_id = data.get("conversation_id")
             prompt_id = data.get("prompt_id", "default")
             chunks = int(data.get("chunks", 2))
diff --git a/application/retriever/brave_search.py b/application/retriever/brave_search.py
index 1fd844b2..4601d352 100644
--- a/application/retriever/brave_search.py
+++ b/application/retriever/brave_search.py
@@ -2,7 +2,6 @@ import json
 from application.retriever.base import BaseRetriever
 from application.core.settings import settings
 from application.llm.llm_creator import LLMCreator
-from application.utils import num_tokens_from_string
 from langchain_community.tools import BraveSearch
 
 
@@ -73,15 +72,7 @@ class BraveRetSearch(BaseRetriever):
             yield {"source": doc}
 
         if len(self.chat_history) > 1:
-            tokens_current_history = 0
-            # count tokens in history
             for i in self.chat_history:
-                if "prompt" in i and "response" in i:
-                    tokens_batch = num_tokens_from_string(i["prompt"]) + num_tokens_from_string(
-                        i["response"]
-                    )
-                    if tokens_current_history + tokens_batch < self.token_limit:
-                        tokens_current_history += tokens_batch
                         messages_combine.append(
                             {"role": "user", "content": i["prompt"]}
                         )
diff --git a/application/retriever/classic_rag.py b/application/retriever/classic_rag.py
index 42e318d2..75b2b576 100644
--- a/application/retriever/classic_rag.py
+++ b/application/retriever/classic_rag.py
@@ -3,7 +3,6 @@ from application.core.settings import settings
 from application.vectorstore.vector_creator import VectorCreator
 from application.llm.llm_creator import LLMCreator
 
-from application.utils import num_tokens_from_string
 
 
 class ClassicRAG(BaseRetriever):
@@ -73,15 +72,7 @@ class ClassicRAG(BaseRetriever):
             yield {"source": doc}
 
         if len(self.chat_history) > 1:
-            tokens_current_history = 0
-            # count tokens in history
             for i in self.chat_history:
-                if "prompt" in i and "response" in i:
-                    tokens_batch = num_tokens_from_string(i["prompt"]) + num_tokens_from_string(
-                        i["response"]
-                    )
-                    if tokens_current_history + tokens_batch < self.token_limit:
-                        tokens_current_history += tokens_batch
                         messages_combine.append(
                             {"role": "user", "content": i["prompt"]}
                         )
diff --git a/application/retriever/duckduck_search.py b/application/retriever/duckduck_search.py
index 6ae56226..80717e7d 100644
--- a/application/retriever/duckduck_search.py
+++ b/application/retriever/duckduck_search.py
@@ -1,7 +1,6 @@
 from application.retriever.base import BaseRetriever
 from application.core.settings import settings
 from application.llm.llm_creator import LLMCreator
-from application.utils import num_tokens_from_string
 from langchain_community.tools import DuckDuckGoSearchResults
 from langchain_community.utilities import DuckDuckGoSearchAPIWrapper
 
@@ -89,16 +88,8 @@ class DuckDuckSearch(BaseRetriever):
         for doc in docs:
             yield {"source": doc}
 
-        if len(self.chat_history) > 1:
-            tokens_current_history = 0
-            # count tokens in history
+        if len(self.chat_history) > 1:      
             for i in self.chat_history:
-                if "prompt" in i and "response" in i:
-                    tokens_batch = num_tokens_from_string(i["prompt"]) + num_tokens_from_string(
-                        i["response"]
-                    )
-                    if tokens_current_history + tokens_batch < self.token_limit:
-                        tokens_current_history += tokens_batch
                         messages_combine.append(
                             {"role": "user", "content": i["prompt"]}
                         )
diff --git a/frontend/package-lock.json b/frontend/package-lock.json
index 7b6f11d6..f96a17d4 100644
--- a/frontend/package-lock.json
+++ b/frontend/package-lock.json
@@ -1649,7 +1649,7 @@
       "version": "18.3.0",
       "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.3.0.tgz",
       "integrity": "sha512-EhwApuTmMBmXuFOikhQLIBUn6uFg81SwLMOAUgodJF14SOBOCMdU04gDoYi0WOJJHD144TL32z4yDqCW3dnkQg==",
-      "devOptional": true,
+      "dev": true,
       "dependencies": {
         "@types/react": "*"
       }