discourse-ai/lib/embeddings/vector_representations
Roman Rizzi 534b0df391
REFACTOR: Separation of concerns for embedding generation. (#1027)
In a previous refactor, we moved the responsibility of querying and storing embeddings into the `Schema` class. Now, it's time for embedding generation.

The motivation behind these changes is to isolate vector characteristics in simple objects to later replace them with a DB-backed version, similar to what we did with LLM configs.
2024-12-16 09:55:39 -03:00
..
all_mpnet_base_v2.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00
base.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00
bge_large_en.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00
bge_m3.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00
gemini.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00
multilingual_e5_large.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00
text_embedding_3_large.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00
text_embedding_3_small.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00
text_embedding_ada_002.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00