Corentin Meyer
Corentin Meyer
Any update ? Facing the same issue with Zscaler, it's terrible
Note: As a 1st step: we now have working Sparse embedder in Haystack through FastEmbed integration https://github.com/deepset-ai/haystack-core-integrations/pull/579
Btw it would be cool to have a general BM25 Embedder in core haystack repo instead of relying only on Splade Embedder from FastEmbed :) As you already have a...
Note: As a 2nd step: Qdrant integration could now support Sparse vector and be compatible with the FastEmbed sparse embedder from above 👀 https://github.com/deepset-ai/haystack-core-integrations/pull/578
Sorry, it went out of my mind I will do it :)
I know why I stopped, because I had issue setting up the env (on windows). Now that all is set, I can see there was test failling (on top of...
Should be good now. I had to change the test a bit because as I explained I suggested to only validate latest message (and include only latest message for validation)...
Eventually I did it by hand with ```python def indices_low_conf(model, test_X, test_Y, margin=0.55): """Return the indices of the images where the confidence of the model is lower than the margin."""...
Meh you're right, I'm just blind ! Sorry for this issue, have a good one ! :)
Any update on merging this ? Using python 3.9 code I had this specific issue: ```python-traceback --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) /home/meyer/code-project/HistoQuant/zc_Unet.ipynb Cell 16' in () 63 print('Number...