Vector database
1 like3,852 views
The document explains vector databases, which facilitate advanced search capabilities like visual and semantic search for applications such as e-commerce and customer service. It discusses the importance of vector embeddings for representing data and mentions various tools and approaches used for vector similarity search. Additionally, it provides examples of how to retrieve similar products based on image data using Redis database functionalities.
![{
"name": "MY Blue shirt"
"images": [
[0.2, 0.4, 0.3, 0.5…],
[0.1, 0.5, 0.3, 0.2…],
],
"price": 19.90,
"location": "32.05, 34.680"
}
Example
Catalog](https://image.slidesharecdn.com/vectordatabase-220125150057/85/Vector-database-16-320.jpg)
![FT.SEARCH products
"*=>[TOP_K 10 @images $BLOB]"
Example
Find me the Top 10 products most similar to given image
{
"name": "MY Blue shirt"
"images": [
[0.2, 0.4, 0.3, 0.5…],
[0.1, 0.5, 0.3, 0.2…],
],
"price": 19.90,
"location": "32.05, 34.680"
}](https://image.slidesharecdn.com/vectordatabase-220125150057/85/Vector-database-17-320.jpg)
![Example cont.
Find me the Top 10 products most similar to given image
that cost $10-$20
FT.SEARCH my_index
"@price[10 20] => [TOP_K 10 @images $BLOB]"
{
"name": "MY Blue shirt"
"images": [
[0.2, 0.4, 0.3, 0.5…],
[0.1, 0.5, 0.3, 0.2…],
],
"price": 19.90,
"location": "32.05, 34.680"
}](https://image.slidesharecdn.com/vectordatabase-220125150057/85/Vector-database-18-320.jpg)
![Example cont.
Find me the Top 10 products most similar to given image
that cost $10-$20
and the store located 10 KM from TLV
FT.SEARCH my_index
"@price[10 15] @location:[32.082, 34.780 10 km]
=> [TOP_K 10 @images $BLOB]"
{
"name": "MY Blue shirt"
"images": [
[0.2, 0.4, 0.3, 0.5…],
[0.1, 0.5, 0.3, 0.2…],
],
"price": 19.90,
"location": "32.05, 34.680"
}](https://image.slidesharecdn.com/vectordatabase-220125150057/85/Vector-database-19-320.jpg)
![Example cont.
Find me the Top 10 products most similar to given image
that cost $10-$20
and the store located 10 KM from TLV sort by Price
FT.SEARCH my_index
"@price[10 15] @location:[32.082, 34.780 10 km]
=> [TOP_K 10 @images $BLOB]"
SORTBY @price ASC
{
"name": "MY Blue shirt"
"images": [
[0.2, 0.4, 0.3, 0.5…],
[0.1, 0.5, 0.3, 0.2…],
],
"price": 19.90,
"location": "32.05, 34.680"
}](https://image.slidesharecdn.com/vectordatabase-220125150057/85/Vector-database-20-320.jpg)
![Graph?
MATCH
(:Product{image:$BLOB})<-[:in]-(:Cart)-[:in]->(p2:Product)
RETURN p2](https://image.slidesharecdn.com/vectordatabase-220125150057/85/Vector-database-21-320.jpg)
Vector database
- 1. Vector Similarity Search or What is Vector Database? Guy Korland, PhD. CTO of Incubation, Redis
- 2. • What? • Why? • How? Vector Database?
- 3. What is Vector Database?
- 4. It’s a new database vertical Vector Database
- 5. Why do we need it? Visual Search E-Commerce: Recommenders Natural Language Search Customer Service: semantic search, Q&A, content recommendation, Jobs Recommend: Similar products, brands, properties Image Recognition: face recognition, similar products
- 6. How?
- 8. Vector representation of words + similarity (word2vec) https://medium.com/@hari4om/word-embedding-d816f643140
- 11. Works in the space https://github.com/facebookresearch/faiss/wiki
- 12. Benchmarks http://ann-benchmarks.com/ • FAISS - Facebook • ScaNN - Google • SPTAG - Microsoft • NGT - Yahoo! • ANNOY - Spotify
- 13. Hashes Bitmaps Strings Bit Field Streams Hyperloglog Sorted Sets Sets Geospatial Search Graph TimeSeries AI JSON Data-Structures Modules BloomFilter Redis beyond cache Lists Redis Enterprise core Linear scalability HA Geo-distribution Durability Backup & restore Tiered-memory access Security Multi-tenant Gears
- 14. Hashes Bitmaps Strings Bit Field Streams Hyperloglog Sorted Sets Sets Geospatial Search Graph TimeSeries AI JSON Data-Structures Modules BloomFilter Redis beyond cache Lists Redis Enterprise core Linear scalability HA Geo-distribution Durability Backup & restore Tiered-memory access Security Multi-tenant Gears
- 15. Redis 15 Images embeddings Texts embeddings Videos embeddings Stored Indexed Redis as a database RedisJSON RedisGraph Hashes Redis as a database with Similarity Search RedisJSON RedisGraph Hashes
- 16. { "name": "MY Blue shirt" "images": [ [0.2, 0.4, 0.3, 0.5…], [0.1, 0.5, 0.3, 0.2…], ], "price": 19.90, "location": "32.05, 34.680" } Example Catalog
- 17. FT.SEARCH products "*=>[TOP_K 10 @images $BLOB]" Example Find me the Top 10 products most similar to given image { "name": "MY Blue shirt" "images": [ [0.2, 0.4, 0.3, 0.5…], [0.1, 0.5, 0.3, 0.2…], ], "price": 19.90, "location": "32.05, 34.680" }
- 18. Example cont. Find me the Top 10 products most similar to given image that cost $10-$20 FT.SEARCH my_index "@price[10 20] => [TOP_K 10 @images $BLOB]" { "name": "MY Blue shirt" "images": [ [0.2, 0.4, 0.3, 0.5…], [0.1, 0.5, 0.3, 0.2…], ], "price": 19.90, "location": "32.05, 34.680" }
- 19. Example cont. Find me the Top 10 products most similar to given image that cost $10-$20 and the store located 10 KM from TLV FT.SEARCH my_index "@price[10 15] @location:[32.082, 34.780 10 km] => [TOP_K 10 @images $BLOB]" { "name": "MY Blue shirt" "images": [ [0.2, 0.4, 0.3, 0.5…], [0.1, 0.5, 0.3, 0.2…], ], "price": 19.90, "location": "32.05, 34.680" }
- 20. Example cont. Find me the Top 10 products most similar to given image that cost $10-$20 and the store located 10 KM from TLV sort by Price FT.SEARCH my_index "@price[10 15] @location:[32.082, 34.780 10 km] => [TOP_K 10 @images $BLOB]" SORTBY @price ASC { "name": "MY Blue shirt" "images": [ [0.2, 0.4, 0.3, 0.5…], [0.1, 0.5, 0.3, 0.2…], ], "price": 19.90, "location": "32.05, 34.680" }
- 22. • https://redisearch.io - https://github.com/RediSearch/redisearch • https://redisai.io - https://github.com/RedisAI/VectorSimilarity - https://redis.com/blog/build-intelligent-apps-redis-vector-similarity-search/ Where to read more? (Preview)