go-openai VS gollum

Unfortunately, you're using sashabaranov/go-openai, which has different api behavior than the official langchain python package [0].

I was hoping this would be a drop in replacement for langchain (so DS ppl can code in python and gophers can port it to production).

[0] - https://github.com/sashabaranov/go-openai#why-dont-we-get-th...

what do you offer that https://github.com/sashabaranov/go-openai does not ?

We will use this great library to connect to the openAPI API https://github.com/sashabaranov/go-openai

This was built using an AWS Lambda function built in GO with the https://github.com/sashabaranov/go-openai module

I did a similar optimization via https://github.com/viterin/vek as the SIMD version. Some somewhat unscientific calculations showed a 10x improvement staying in float32: https://github.com/stillmatic/gollum/blob/07a9aa35d2517af8cf...

TBH my takeaway was that it was more useful to use smaller vectors as a representation

I like Go a lot for working with OpenAI etc, it's 'just' API calls and Go is great at that. I've opensourced some bits here: https://github.com/stillmatic/gollum -- in particular, function dispatch (given a prompt, return an arbitrary Go struct) is really nice, as is a very fast in-memory KNN index.

I've written a version of this in Golang: https://github.com/stillmatic/gollum/blob/main/dispatch.go

```go

I have gotten 10x speedups with SIMD on modern hardware. Goroutines make this actually fairly tricky, as you essentially have to process all the events and then sort the entire array, which is usually the bottleneck. The heap adds a small amount of complexity but is significantly more efficient, feels like good ROI.

https://github.com/stillmatic/gollum/blob/main/vectorstore.g...