plano/demos/llm_routing/session_affinity_redis/config.yaml

36 lines
766 B
YAML

version: v0.4.0
listeners:
- type: model
name: model_listener
port: 12000
model_providers:
- model: openai/gpt-4o-mini
access_key: $OPENAI_API_KEY
default: true
- model: openai/gpt-5.2
access_key: $OPENAI_API_KEY
routing_preferences:
- name: fast_responses
description: short factual questions, quick lookups, simple summarization, or greetings
models:
- openai/gpt-4o-mini
- name: deep_reasoning
description: multi-step reasoning, complex analysis, code review, or detailed explanations
models:
- openai/gpt-5.2
- openai/gpt-4o-mini
routing:
session_ttl_seconds: 300
session_cache:
type: redis
url: redis://localhost:6379
tracing:
random_sampling: 100
trace_arch_internal: true