discourse-ai/lib/embeddings/vector_representations
Sam b2b01185f2
FEATURE: add support for new OpenAI embedding models (#445)
* FEATURE: add support for new OpenAI embedding models

This adds support for just released text_embedding_3_small and large

Note, we have not yet implemented truncation support which is a
new API feature. (triggered using dimensions)

* Tiny side fix, recalc bots when ai is enabled or disabled

* FIX: downsample to 2000 items per vector which is a pgvector limitation
2024-01-29 13:24:30 -03:00
..
all_mpnet_base_v2.rb FEATURE: Support for SRV records for Discourse services (#414) 2024-01-10 19:23:07 -03:00
base.rb FEATURE: add support for new OpenAI embedding models (#445) 2024-01-29 13:24:30 -03:00
bge_large_en.rb FEATURE: Support for SRV records for Discourse services (#414) 2024-01-10 19:23:07 -03:00
gemini.rb FEATURE: Support for Gemini Embeddings (#382) 2023-12-28 10:28:01 -03:00
multilingual_e5_large.rb FEATURE: Support for SRV records for Discourse services (#414) 2024-01-10 19:23:07 -03:00
text_embedding_3_large.rb FEATURE: add support for new OpenAI embedding models (#445) 2024-01-29 13:24:30 -03:00
text_embedding_3_small.rb FEATURE: add support for new OpenAI embedding models (#445) 2024-01-29 13:24:30 -03:00
text_embedding_ada_002.rb FEATURE: add support for new OpenAI embedding models (#445) 2024-01-29 13:24:30 -03:00