mirror of
https://github.com/khoj-ai/khoj.git
synced 2024-11-27 17:35:07 +01:00
c28755ccd2
Extract performance into separate sectin into shoving it under search Create page for web interface
19 lines
795 B
Markdown
19 lines
795 B
Markdown
## Performance
|
|
|
|
### Search performance
|
|
|
|
- Semantic search using the bi-encoder is fairly fast at \<100 ms across all content types
|
|
- Reranking using the cross-encoder is slower at \<2s on 15 results. Tweak `top_k` to tradeoff speed for accuracy of results
|
|
- Filters in query (e.g by file, word or date) usually add \<20ms to query latency
|
|
|
|
### Indexing performance
|
|
|
|
- Indexing is more strongly impacted by the size of the source data
|
|
- Indexing 100K+ line corpus of notes takes about 10 minutes
|
|
- Indexing 4000+ images takes about 15 minutes and more than 8Gb of RAM
|
|
- Note: *It should only take this long on the first run* as the index is incrementally updated
|
|
|
|
### Miscellaneous
|
|
|
|
- Testing done on a Mac M1 and a \>100K line corpus of notes
|
|
- Search, indexing on a GPU has not been tested yet
|