39 lines
1.1 KiB
YAML
39 lines
1.1 KiB
YAML
|
apiVersion: v1
|
||
|
|
kind: ConfigMap
|
||
|
|
metadata:
|
||
|
|
name: api-gateway-config
|
||
|
|
namespace: api
|
||
|
|
labels:
|
||
|
|
app: api-gateway
|
||
|
|
data:
|
||
|
|
config.yaml: |
|
||
|
|
# Gateway configuration - loaded at startup, never compiled in
|
||
|
|
# See REQUIREMENTS.md for full specification
|
||
|
|
|
||
|
|
# Routes: standard HTTP proxy routes (not LLM-specific)
|
||
|
|
# These are for non-LLM services (agent-pod/console, etc.)
|
||
|
|
routes: []
|
||
|
|
|
||
|
|
# Models: LLM model registry for body-based dispatch
|
||
|
|
# POST /v1/chat/completions routes based on the "model" field in request JSON
|
||
|
|
models:
|
||
|
|
- name: "reasoning"
|
||
|
|
address: "reasoning-predictor.llm-serving:80"
|
||
|
|
path: "/v1/chat/completions"
|
||
|
|
|
||
|
|
- name: "ornith:35b"
|
||
|
|
address: "ornith-predictor.llm-serving:80"
|
||
|
|
path: "/v1/chat/completions"
|
||
|
|
|
||
|
|
- name: "qwen2.5:3b-instruct"
|
||
|
|
address: "ornith-predictor.llm-serving:80"
|
||
|
|
path: "/v1/chat/completions"
|
||
|
|
|
||
|
|
- name: "nomic-ai/nomic-embed-text-v2-moe"
|
||
|
|
address: "embeddings-predictor.llm-serving:80"
|
||
|
|
path: "/v1/embeddings"
|
||
|
|
|
||
|
|
- name: "BAAI/bge-reranker-base"
|
||
|
|
address: "reranker-predictor.llm-serving:80"
|
||
|
|
path: "/v1/rerank"
|