Document workload-oriented LLM profile deployment

This commit is contained in:
2026-08-03 17:21:42 +00:00
parent 5cd7f8e737
commit 394278e1f2
16 changed files with 230 additions and 87 deletions

View File

@@ -1,4 +1,6 @@
version: 4
promptkit:
profile_file: ./examples/profiles/dnd-extraction.yml
concurrency:
total_llm: 2
stage_workers:
@@ -16,6 +18,7 @@ debug:
directory: ./notarius-debug
pipelines:
dnd-session:
llm_profile: dnd-extraction
input: seriatim
# Stable campaign context is shared by every module that accepts these slots.
references:
@@ -54,7 +57,6 @@ pipelines:
merge: appendorder
normalize:
module: dnd/npcs
llm_profile: gemini-2-flash
retries: 2
scene-descriptions:
extract:

View File

@@ -1,6 +1,7 @@
version: 4
pipelines:
dnd-session:
llm_profile: dnd-extraction
input: seriatim
artifacts:
spells:

View File

@@ -0,0 +1,5 @@
id: dnd-extraction
backend: openrouter
model: openai/gpt-5.6-luna
timeout_seconds: 240
service_tier: flex