How has everyone dealt with speed issues

have you tried our async support?

index.query(..., response_mode="tree_summarize", use_async=True)

(looking into making some of this default behavior)

@jerryjliu0 I have not, does that create asynchronous calls and once the network responds deals with it w/ a callback? (similar to promises in JS)

With the above command it’s still called from a synchronous wrapper

We do have a native async call in ‘aquery’ too

hey @jerryjliu0!

My partner @Tenzin | Tali AI and I have been using Llama index for a few weeks now. We have been incredibly impressed with the library and it has been instrumental in helping us process in our development process..

We are currently building a project called Minutescribe that started out as a meeting transcription application, but now includes a LLM that is plugged into many data sources, acting as a personal assistant. The project is still in the development phase and is changing rapidly.

We believe that Llama index will be an integral part of our project, and we are committed to building our project on top of it. We would love to discuss how we can collaborate and work together to further develop both of our projects. Specifically we are interested in learning how we can support you and llama.

In general we are trying to build relationships on the space.

Would you be open to jumping on a quick call to discuss?

@Ali | Tali AI sure! Feel free to DM me on discord