Jerry Liu

this is a great idea

should be handled with #215!

see our customization tutorial here (specifically the part about customizing LLMs): https://docs.llamaindex.ai/en/latest/getting_started/customization.html also llms: https://docs.llamaindex.ai/en/latest/module_guides/models/llms.html

i'm working on an upgrade to rags that should address your second point :)

> @jerryjliu we can add an option for that, but that really only makes sense for objects you cam define on the fly (I.e. a query engine tool). This wouldn't...

thanks @mariusnita, sorry about the issue. i'll take a look soon. Is this only with the tree index? Does it work for simple vector index?

> BTW, I just noticed the vector index is 20x cheaper and faster to create, and seems to have much better question-answering performance than the tree index. (Although I was...

@mariusnita do you have sample data to help me repro by any chance? Feel free to DM me in the Discord

Thanks @stanakaj. Yeah given the max input size this should be something gpt index handles under the hood, i'd be curious to see what the data is

thanks @mariusnita, taking a look now