27 comments

[ 11.4 ms ] story [ 46.2 ms ] thread
Oh to have had a delete account/comments option.
Am I misunderstanding what a parquet file is, or are all of the HN posts along with the embedding metadata a total of 55GB?
I know it's unrelated but does anyone knows a good paper comparing vector searches vs "normal" full text search? Sometimes I ask myself of the squeeze worth the juice
I think it would be useful to add a right-click menu option to HN content, like "similar sentences", which displays a list of links to them. I wonder if it would tell me that this suggestion has been made before.
Finetune LLM to post_score -> high quality slop generator
I don't remember licensing my HN comments for 3rd party processing.
Maybe I’m reading this wrong, but commercial use of comments is prohibited by the HN Privacy and data Policy. So is creating derivative works (so technically a vector representation)
I wonder if it'd be okay to do an AirDropped coin based on them? Does one exist? Maybe as a YC startup idea?
I don't know how to feel about this. Is the only purpose of the comments here is to train some commercial model? I have a feeling that, this might affect my involvement here going forward.
Don't use all-MiniLM-L6-v2 for new vector embeddings datasets.

Yes, it's the open-weights embedding model used in all the tutorials and it was the most pragmatic model to use in sentence-transformers when vector stores were in their infancy, but it's old and does not implement the newest advances in architectures and data training pipelines, and it has a low context length of 512 when embedding models can do 2k+ with even more efficient tokenizers.

For open-weights, I would recommend EmbeddingGemma (https://huggingface.co/google/embeddinggemma-300m) instead which has incredible benchmarks and a 2k context window: although it's larger/slower to encode, the payoff is worth it. For a compromise, bge-base-en-v1.5 (https://huggingface.co/BAAI/bge-base-en-v1.5) or nomic-embed-text-v1.5 (https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) are also good.

I am trying sentence-transformers/multi-qa-MiniLM-L6-cos-v1 for deploying a light weight transformer on CPU machine -its output dimension is 384. I want to keep the dimension low as possible. nomic-embed-text offers lower dimensions upto 64. I will need to test my dataset. Will comeback with the results.
Why all-MiniLM-L6-v2? This is so old and terribly behind the new models...
Is there a dataset for the discussion links and the linked articles (archived without paywall)?
The most smug AI ever will be trained on this
why is this not on huggingface as a dataset yet? is anyone poutine this on hugginggface?
Fun project. I'm sure it will get a lot of interest here.

For those into vector storage in general, one thing that has interested me lately is the idea of storing vectors as GGUF files and bring the familiar llama.cpp style quants to it (i.e. Q4_K, MXFP4 etc). An example of this is below.

https://gist.github.com/davidmezzetti/ca31dff155d2450ea1b516...

Can I submit a request somewhere to have my data removed?
Is there an affordable service for doing something like this?
I can't help but feel a bit violated by this.
So... asking for a friend, if I comment here, it becomes a vector?