scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-11 03:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 84

docs(auto_routing): fix dimension weights and tier boundaries to match config.py defaults

Browse source
This commit is contained in:
Ishaan Jaffer 2026-02-21 12:20:07 -08:00
parent 93688aea8d
commit 4755c8f5b8
1 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
docs/my-website/docs/proxy/auto_routing.md
View file

@ -357,9 +357,9 @@ complexity_router_config:
COMPLEX: claude-sonnet
REASONING: o1-preview
tier_boundaries:
simple_medium: 0.25 # Below 0.25 → SIMPLE
medium_complex: 0.50 # 0.25-0.50 → MEDIUM
complex_reasoning: 0.75 # 0.50-0.75 → COMPLEX, above → REASONING
simple_medium: 0.15 # Below 0.15 → SIMPLE
medium_complex: 0.35 # 0.15-0.35 → MEDIUM
complex_reasoning: 0.60 # 0.35-0.60 → COMPLEX, above → REASONING
```
#### Token Thresholds
@ -381,12 +381,12 @@ Customize how much each signal contributes to the complexity score:
complexity_router_config:
dimension_weights:
tokenCount: 0.10 # Prompt length
codePresence: 0.25 # Code-related keywords
codePresence: 0.30 # Code-related keywords
reasoningMarkers: 0.25 # "step by step", "think through", etc.
technicalTerms: 0.20 # Domain-specific complexity
simpleIndicators: 0.10 # "what is", "define", greetings
multiStepPatterns: 0.05 # "first...then", numbered steps
questionComplexity: 0.05 # Multiple questions
technicalTerms: 0.25 # Domain-specific complexity
simpleIndicators: 0.05 # "what is", "define", greetings
multiStepPatterns: 0.03 # "first...then", numbered steps
questionComplexity: 0.02 # Multiple questions
```
### How Complexity Routing Works