ryan 9629bfcef4 Fix embedding tokenizer mismatch with custom embedding server ...

Disable tiktoken pre-encoding for custom embedding servers. LangChain
was encoding text into OpenAI token IDs then sending them to llama-server
which has a different vocabulary, causing "invalid tokens" errors.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-05-11 23:42:23 -04:00

..

__init__.py

Replace ChromaDB with pgvector for vector storage

2026-04-24 08:43:52 -04:00

fetchers.py

ynab update

2026-01-31 22:47:43 -05:00

logic.py

Fix embedding tokenizer mismatch with custom embedding server

2026-05-11 23:42:23 -04:00

models.py

reorganization

2026-01-31 17:13:27 -05:00