🎹 Searching for similar musics 🎻🎸 David Pilato | @dadoonet
Slide 1
Slide 2
Elasticsearch You Know, for Search
Slide 3
Slide 4
Slide 5
These are not the droids you are looking for.
Slide 6
GET /_analyze { “char_filter”: [ “html_strip” ], “tokenizer”: “standard”, “filter”: [ “lowercase”, “stop”, “snowball” ], “text”: “These are <em>not</em> the droids you are looking for.” }
Slide 7
These are <em>not</em> the droids you are looking for. { “tokens”: [{ “token”: “droid”, “start_offset”: 27, “end_offset”: 33, “type”: “<ALPHANUM>”, “position”: 4 },{ “token”: “you”, “start_offset”: 34, “end_offset”: 37, “type”: “<ALPHANUM>”, “position”: 5 }, { “token”: “look”, “start_offset”: 42, “end_offset”: 49, “type”: “<ALPHANUM>”, “position”: 7 }]}
Slide 8
Semantic search ≠ Literal matches
Slide 9
Elasticsearch You Know, for Search
Slide 10
Elasticsearch You Know, for Vector Search
Slide 11
Example: 1-dimensional vector Character Vector [ 1 ] ] Realistic
[ Embeddings represent your data Cartoon 1
Slide 12
represent different data aspects Human Character Vector [ 1, 1 Realistic Cartoon ] ] Machine
[ Multiple dimensions 1, 0
Slide 13
is grouped together Human Character Vector [ 1.0, 1.0 1.0, 0.0 Realistic Cartoon [ 1.0, 0.8 1.0, 1.0 [ 1.0, 1.0 ] ] ] ] ]
Machine
[ [ Similar data
Slide 14
Vector search ranks objects by similarity (~relevance) to the query Human Rank Query 1 Realistic Cartoon 2 3 4 5 Machine Result
Slide 15
How do you index vectors ?
Slide 16
Architecture of Vector Search
Slide 17
dense_vector field type PUT ecommerce { “mappings”: { “properties”: { “description”: { “type”: “text” } “desc_embedding”: { “type”: “dense_vector” } } } }
Slide 18
Data Ingestion and Embedding Generation POST ecommerce/_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 /ecommerce/_doc
Slide 19
How do you search vectors ?
Slide 20
Architecture of Vector Search
Slide 21
knn query GET ecommerce/_search { “query” : { “bool”: { “must”: [{ “knn”: { “field”: “desc_embbeding”, “num_candidates”: 50, “query_vector”: [0.123, 0.244,…] } }], “filter”: { “term”: { “department”: “women” } } } } }, “size”: 10
Slide 22
Architecture of Vector Search
Slide 23
But how does it really work?
Slide 24
Similarity Human q cos(θ) = d1 d2 Realistic θ q⃗ × d ⃗ | q⃗ | × | d |⃗ _score = 1 + cos(θ) 2
Slide 25
Similarity θ Similar vectors θ close to 0 cos(θ) close to 1 1+1 _score = =1 2 θ Orthogonal vectors θ close to 90° cos(θ) close to 0 1+0 _score = = 0.5 2 θ Opposite vectors θ close to 180° cos(θ) close to -1 1−1 _score = =0 2
Slide 26
https://djdadoo.pilato.fr/
Slide 27
https://github.com/dadoonet/music-search/
Slide 28
🎹 Searching for similar musics 🎻🎸 David Pilato | @dadoonet
