Details
-
Improvement
-
Resolution: Duplicate
-
Major
-
None
-
0.1, 0.2, 0.2.1
-
None
-
Unknown
-
Description
Improve the token management for the LLM models with proper tokenizer.
Attachments
Issue Links
- duplicates
-
LLMAI-173 Chunking is character-based and ignores the embedding model's maximum input length, so chunk tails are silently never embedded
-
- Open
-