🎹🎻🎸 Et si nous cherchions des morceaux de musique 🎼🎶 ?
A presentation at Montreal JUG in in Montreal, QC, Canada by David Pilato
Searching for similar music tracks 🎹🎻🎸 David Pilato | @dadoonet
Elasticsearch You Know, for Vector Search
Example: 1-dimensional vector Character Vector [ 1 ] ] Realistic
[ Embeddings represent your data Cartoon 1
represent different data aspects Human Character Vector [ 1, 1 Realistic Cartoon ] ] Machine
[ Multiple dimensions 1, 0
is grouped together Human Character Vector [ 1.0, 1.0 Realistic Cartoon 1.0, 0.0 [ 1.0, 0.8 ] ] ]
Machine
[ Similar data
Vector search ranks objects by similarity (~relevance) to the query Human Rank Query 1 Realistic Cartoon 2 3 4 5 Machine Result
Similarity: cosine (cosine) Human q cos(θ) = d1 d2 Realistic θ q⃗ × d ⃗ | q⃗ | × | d |⃗ _score = 1 + cos(θ) 2
Similarity: cosine (cosine) 1+1 _score = =1 2 1+0 _score = = 0.5 2 1−1 _score = =0 2
Similarity: Dot Product (dot_product) q⃗ × d ⃗ = | q⃗ | × cos(θ) × | d |⃗ q d θ | q⃗ | × co s (θ ) 1 + dot_ product(q, d) scorefloat = 2 0.5 + dot product(q, d) _scorebyte = 32768 × dims
Similarity: Euclidean distance (l2_norm) y 2 n i (x ∑ 1 i= − y i) q l2_normq,d = y1 d x1 y2 x2 n ∑ i=1 (xi − yi) 1 _score = 1 + (l2_normq,d )2 x 2
How do you index vectors ?
Data Ingestion and Embedding Generation POST /_doc { “_id”:”product-1234”, “product_name”:”Summer Dress”, “description”:”Our best-selling…”, “Price”: 118, “color”:”blue”, “fabric”:”cotton”, “fabric”:”cotton” } “desc_embedding”:[0.452,0.3242,…], “desc_embedding”:[0.452,0.3242,…] } “img_embedding”:[0.012,0.0,…] } Source data POST /_doc
How do you search vectors ?
Vector Query GET product-catalog/_search { “knn”: { “field”: “desc_embbeding”, “k”: 5, “num_candidates”: 50, “query_vector”: [0.123, 0.244,…], “filter”: { “term”: { “department”: “women” } } } }, “size”: 10
https://djdadoo.pilato.fr/
https://github.com/dadoonet/music-search/
Searching for similar music tracks 🎹🎻🎸 David Pilato | @dadoonet
Pendant cette session, nous allons utiliser les principes de la recherche vectorielle pour trouver des morceaux de musique ressemblant (peut-être) à d’autres. Pour cela, nous ferons un rappel des principes de la génération d’embeddings pour représenter n’importe quel type de données, qu’elles soient textuelles ou binaires.
Resources
The following resources were mentioned during the presentation or are useful additional information.
Buzz and feedback
Here’s what was said about this presentation on social media.
