mirror of
https://github.com/hanzoai/redis.git
synced 2026-10-30 18:25:12 +00:00
YaacovHazan
0e0dabb8cb
git-subtree-dir: modules/vector-sets git-subtree-mainline:c8d677e087git-subtree-split:2de9527bc1
31 lines
880 B
Plaintext
31 lines
880 B
Plaintext
This example maps long form movies plots to movies titles.
|
|
It will create fp32 and binary vectors (the two extremes).
|
|
|
|
1. Install ollama, and install the embedding model "mxbai-embed-large"
|
|
2. Download mpst_full_data.csv from https://www.kaggle.com/datasets/cryptexcode/mpst-movie-plot-synopses-with-tags
|
|
3. python insert.py
|
|
|
|
127.0.0.1:6379> VSIM many_movies_mxbai-embed-large_NOQUANT ELE "The Matrix"
|
|
1) "The Matrix"
|
|
2) "The Matrix Reloaded"
|
|
3) "The Matrix Revolutions"
|
|
4) "Commando"
|
|
5) "Avatar"
|
|
6) "Forbidden Planet"
|
|
7) "Terminator Salvation"
|
|
8) "Mandroid"
|
|
9) "The Omega Code"
|
|
10) "Coherence"
|
|
|
|
127.0.0.1:6379> VSIM many_movies_mxbai-embed-large_BIN ELE "The Matrix"
|
|
1) "The Matrix"
|
|
2) "The Matrix Reloaded"
|
|
3) "The Matrix Revolutions"
|
|
4) "The Omega Code"
|
|
5) "Forbidden Planet"
|
|
6) "Avatar"
|
|
7) "John Carter"
|
|
8) "System Shock 2"
|
|
9) "Coherence"
|
|
10) "Tomorrowland"
|