Update the app

app.py

@@ -229,7 +229,7 @@ def answer_questions(question: str, github: str, **kwargs) -> Response:
                 [StreamingGradioCallbackHandler(q)]
             ),
         )
-        qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever)
+        qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever, max_tokens_limit=16000)
         chat_history = []
 
     except Exception as e:
@@ -345,7 +345,7 @@ def generateDocumentationPerFolder(dir, github):
             verbose=True,
             streaming=True,  # Pass `streaming=True` to make sure the client receives the data.
         )
-        qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever)
+        qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever, max_tokens_limit=16000)
         chat_history = []
         return qa({"question": prompt, "chat_history": chat_history})["answer"]
 
@@ -399,7 +399,7 @@ def solveGithubIssue(ticket, history) -> Response:
                 [StreamingGradioCallbackHandler(q)]
             ),
         )
-        qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever,max_tokens_limit=8000)
+        qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever, max_tokens_limit=16000)
 
     except Exception as e:
         return [[str(e), None]]
@@ -445,7 +445,7 @@ def bot(history, **kwargs):
                 [StreamingGradioCallbackHandler(q)]
             ),
         )
-        qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever)
+        qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever, max_tokens_limit=16000)
         chat_history = []
 
     except Exception as e: