dima/supabase
1
0 Fork 0
mirror of https://github.com/supabase/supabase.git synced 2026-10-19 16:19:10 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat: add link to wikipedia dataset

Browse Source
This commit is contained in:
Greg Richardson authored and GitHub committed 2023-08-02 17:06:52 -05:00
1 parent b6c8211248
commit 092e8939db
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
apps/www/_blog/2023-08-03-fewer-dimensions-are-better-pgvector.mdx
+1 -1
View File
@@ -89,7 +89,7 @@ We compared the performance of `text-embedding-ada-002` from OpenAI (1536 dimens
- **Database size:** with 2vCPU (ARM) and 8GB RAM - `large` add-on for Supabase project.
- **Version:** Postgres v15 and pgvector v0.4.0
- **Dataset:** 224,482 embeddings from Wikipedia articles.
- **Dataset:** 224,482 embeddings from [Wikipedia articles](https://www.kaggle.com/datasets/stephanst/wikipedia-simple-openai-embeddings).
- **Index:** The index was generated for `inner-product` (dot product) distance function with `lists=1000`.
- **Process:** We followed [our optimization guide and tips](https://supabase.com/docs/guides/ai/going-to-prod#performance-tips-when-using-indexes).