How does this work? I thought it was probably powered by embeddings and maybe some more traditional search code, but I checked out the linked github repo and I didn't see any model/inference code. The public code is a wrapper that communicates with your commercial API?
Some searches work like magic and others seem to veer off target a lot. For example, "sculpture" and "watercolor" worked just about how I'd expect. "Lamb" showed lambs and sheep. But "otter" showed a random selection of animals.
This is neat, not sure how to report queries that are working poorly as you have mentioned. But when I search "Waltz" I am presented with Kitchen Utensils and only one piece of dancing folks. Presumably this is due to the Artist's name being 'Walton'.
Ketika kode dan kanvas bertemu — sebuah pencarian tak sekadar kata, tapi rasa. Di antara lukisan dan batang piksel, mesin mencoba memahami jawaban yang tak terucap.
I recently learned that semantic search embeddings mostly represent topics and concepts, but they don’t handle negation or emotion very well.
For example, if you search for “paintings of winter landscapes but without sun and trees,” you’ll still get results with trees. That’s because embeddings capture the presence of concepts like “tree” or “landscape,” but not logical relationships like “without” or “not.”
Similarly, embeddings aren’t great at capturing how something feels. They can tell that “sad poem” and “happy poem” are different mainly because of the words used, not because they truly understand emotional tone.
This happens because most embedding models (like OpenAI’s or sentence-transformers) are trained to group things by semantic similarity, not logical meaning or sentiment. Negation, polarity, and affect aren’t explicitly represented in the vector space.
Might be common knowledge to some, but it was a cool TIL moment for me, realizing that embeddings are great at what something is about, but not how it feels or what it excludes.
It always gives me exactly 16 (or less) images. So this cannot be very reliable because there are more results. Proof: Add a space anwhere to your search string in the form and hit enter again, then some new results are mixed in.
18 comments
[ 2.9 ms ] story [ 43.2 ms ] threadSome searches work like magic and others seem to veer off target a lot. For example, "sculpture" and "watercolor" worked just about how I'd expect. "Lamb" showed lambs and sheep. But "otter" showed a random selection of animals.
Colnomic and nvidia models are great for embedding images and MUVERA can transform those to 1D vectors.
"Images of german shepherds" never fails to provide some humor.
Would be interesting to know how relevant that approach is now.
For example, if you search for “paintings of winter landscapes but without sun and trees,” you’ll still get results with trees. That’s because embeddings capture the presence of concepts like “tree” or “landscape,” but not logical relationships like “without” or “not.”
Similarly, embeddings aren’t great at capturing how something feels. They can tell that “sad poem” and “happy poem” are different mainly because of the words used, not because they truly understand emotional tone.
This happens because most embedding models (like OpenAI’s or sentence-transformers) are trained to group things by semantic similarity, not logical meaning or sentiment. Negation, polarity, and affect aren’t explicitly represented in the vector space.
Might be common knowledge to some, but it was a cool TIL moment for me, realizing that embeddings are great at what something is about, but not how it feels or what it excludes.