i tried to set this



but I am still getting this error using llama2-13B, the default one



Any ideas what I am doing wrongly?

hi, I have a use case wherein my company wants to have questions answered by exact text we feed in to the LLM. Is this even possible? how can it be done? it is a document chat/query use case.

Hi, we are trying to summarize very long text. Use case is we will extract the entire chat conversation between our customer and our customer service agent then get a summary so it'll be easier to handoff to another cs agent. We tried pure OpenAI calls but we are hitting the token limit even if we use gpt-3.5-16k. I was thinking we can use llama_index for this use case. Have you guys tried this before? Any patterns which we can use?

Would really appreciate to point me to the right direction. TIA!

i am getting this answer when I am using llm=ChatOpenAI . Even I indexed my entire data set, it seems it is not added in the context. Any ideas how I can let it answer more accurately?

Answer:The context provided is about ... Therefore, the original answer remains the same.

Hi, does GPTSimpleVectorIndex support changing of the LLM predictor? I checked my usage and it is still falling back to text-davinci-03. here's the gist of the code.

# define LLM llm_predictor = LLMPredictor(llm=OpenAI(temperature=0, model_name="gpt-3.5-turbo", max_tokens=512)) service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper) index = GPTSimpleVectorIndex.from_documents( documents, service_context=service_context )

hi, is there a way to limit the OpenAI API tokens generated in llamaindex? just wanted to control cost since I am exploring using my own funds. 😄