perhaps is a stupid question .... but ... can anyone explain me the difference of LLm tokens and embeddings token ...?? its something that must improve in my algortims??

mmmm how can i find an example ??

hi ... somebody with this problem ??

INFO:openai:error_code=None error_message="This model's maximum context length is 4097 tokens,

witch one is the correct for use ... llama_index o or gpt_index ... yesterday i upgrade llama_index to 0.5.4 and break all my code ... nothink work as spected ... this happend to anyone ???

how i can extract the llama_index.token_counter.token_counter form a index.query ?? i need to know how mutch i consume of them in every query

are you train to count the tokens that que query use ???