Hi can anyone help me solve the below error
openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens. However, your messages resulted in 36614 tokens. Please reduce the length of the messages.

In getting structured output does llama index calls openai to format our data?

Hi I want to finetune my index so that it will give me response in desired format. How do I do it in a simple way

can we have chat continuation feature in queryengine?

Hi
I have a list of vectorstore index I want to create a chat engine using all the indices, when I try to create one it is giving error.
here's my code snippet:
memory = ChatMemoryBuffer.from_defaults(token_limit=2500)
timea = time.time()

collections = UserIndexes.objects.filter(
user_id=user_id)
timeb = time.time()
print("filtering collections", timeb-timea)
indices = []
for collection in collections:
if collection.file_name != "":
timec = time.time()
index = get_indexes(collection)
indices.append(index)
timed = time.time()
print("getting index", timed-timec)
timee = time.time()
index = GPTListIndex[indices]
print("getting all indices", timee-timeb)

return index.as_chat_engine()