-
-
Notifications
You must be signed in to change notification settings - Fork 5.4k
Closed
Labels
Integration RequestRequest for support of a new LLM, Embedder, or Vector databaseRequest for support of a new LLM, Embedder, or Vector databasepossible bugBug was reported but is not confirmed or is unable to be replicated.Bug was reported but is not confirmed or is unable to be replicated.
Description
| this.embeddingChunkLimit = 1_000; |
Why is this not configurable using EMBEDDING_MODEL_CHUNK_SIZE or something? Because some embedding models need lower chunk sizes.
For example, sentence-transformers/all-MiniLM-L6-v2 has a default of 256 "word pieces".
Metadata
Metadata
Assignees
Labels
Integration RequestRequest for support of a new LLM, Embedder, or Vector databaseRequest for support of a new LLM, Embedder, or Vector databasepossible bugBug was reported but is not confirmed or is unable to be replicated.Bug was reported but is not confirmed or is unable to be replicated.