C. George Williams

Yeah, getting the docker environment can be tricky. When I get a chance I'll look at it this week asap. On Mon, Mar 27, 2023 at 5:53 PM gary88christie ***@***.***>...

"gary88christie" I'm not sure how to add you to the pull request, but please check this out and let me know if it resolves your issue. https://github.com/harsha-simhadri/big-ann-benchmarks/pull/101 As I mentioned...

Thanks @gary88christie. It appears to be ok as far as I can tell. Can you submit a pull request and I'll try it out?

A successful test of sparse faiss/random-filter-s on Mac M1 (plot below.) Note I had to link against libfaiss.so instead of libfaiss_avs.so because the Docker QEMU x86 does not emulate AVX:...

A successful test of sparse linscan/sparse-small on Mac M1 (plot below.) 

Hi @scott01272001. I'll check out your repo at some point soon...but I'm wondering if you've tried 1) pass by reference and 2) BytePointer/ByteBuffer instead byte arrays. I'll move this conversation...

Great. I'll try to get to it this week...but I will do it as soon as i can. Thanks for your response. On Mon, Oct 31, 2016 at 2:25 PM,...

@andersonbcdefg Can I try your dataset?

Great, @andersonbcdefg I downloaded [this data file ](https://huggingface.co/datasets/teknium/OpenHermes-2.5/blob/main/openhermes2_5.json). What model/service did you use to vectorize the text? Can you share your vectorization technique/code? That way i can try to reproduce...

> @sourcesync I didn't do anything crazy just compute dense embeddings with an open-source model like BGE-small over the "conversations" field converted to text by unrolling the conversation with "user:"...