The community member is using a list index but needs to speed up the processing time. Their use case does not allow them to risk missing important information, so a list index is required. They are wondering if there is a way to use trees to summarize and send out multiple API calls at once to speed up the process.
The comments suggest that using a tree index instead of a list index could be faster to query, but a bit slower to build. The community members discuss different approaches, such as using async, increasing chunk size, and using a composable index. They also discuss the trade-offs between a tree index and a list index, with the key concern being that the community member cannot miss any information.
There is no explicitly marked answer in the comments, but the community members provide various suggestions and discuss the pros and cons of different approaches.
Hi, im using a list index but u need to speed up the processing time. My use case doesn’t allow for me to risk missing important information so a list index is required there a way to case doesn’t allow for me to risk missing important information so a list index is required. Is there a way to maybe with trees summarize send out multiple API calls at once?
Great ! The key part is that I can’t miss any information so that limits me to a high k similarity on vector or list/tree. Does a tree miss any information?
