plano/demos/use_cases/preference_based_routing/arch_config.yaml
2025-05-08 14:07:23 -07:00

33 lines
662 B
YAML

version: "0.1-beta"
endpoints:
gcp_hosted_outer_llm:
endpoint: 34.46.85.85:8000
http_host: 34.46.85.85
# endpoint: host.docker.internal:11223
listeners:
egress_traffic:
address: 0.0.0.0
port: 12000
message_format: openai
timeout: 30s
llm_providers:
- name: gpt-4o
provider_interface: openai
access_key: $OPENAI_API_KEY
model: gpt-4o
usage: |
complex reasoning problem, require multi step answer
- name: o4-mini
provider_interface: openai
access_key: $OPENAI_API_KEY
model: o4-mini
usage: |
simple requests, basic fact retrieval, easy to answer
tracing:
random_sampling: 100