mikemccand commented on issue #13519: URL: https://github.com/apache/lucene/issues/13519#issuecomment-2206145047
Could someone summarize what is actually wrong with Lucene here? From my `luceneutil` tests it looks like `int8` with `DOT_PRODUCT` is buggy / does not work (.006 recall on `cohere-768-IP` where `float32` gets 0.957). E.g. `int8` quantization only works if your vectors are unsigned, or `int8` quantization only works with `VectorSimilarityFunction.EUCLIDEAN` or so? I know we are discussing how to make the conflated quantization and distance metric combinations math work out (i.e. how to fix the issue), but I'm just trying to get the big picture of what the issue even is. How would we explain the buggy behavior to users? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
