martin/meeting-lab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: configure 32k context for protocol generation

Browse Source
This commit is contained in:
admin
2026-08-25 15:29:40 +02:00
parent d77bfedb6e
commit df89a38829
5 changed files with 16 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/diarization.md
+3 -3
View File
@@ -48,9 +48,9 @@ derived representation sent to prompt construction.
Before contacting Ollama, Meeting Lab conservatively estimates prompt tokens
from UTF-8 byte count without adding a model tokenizer dependency. The default safe
budget is 16,200 estimated tokens, below the observed 16,386-token effective
boundary even when a larger `num_ctx` was requested. The estimate is calibrated
against the currently validated German BPD input and is configurable through
budget is 29,000 estimated tokens within the explicitly configured 32,768-token
Ollama context. The estimate is calibrated against the currently validated
German BPD input and is configurable through
`MvpMeetingConfig.protocol_safe_input_token_budget` or
`--protocol-safe-input-token-budget`.