diff --git a/doc/examples/sample-config.yaml b/doc/examples/sample-config.yaml index 49ad389..72dd0ff 100644 --- a/doc/examples/sample-config.yaml +++ b/doc/examples/sample-config.yaml @@ -1,7 +1,7 @@ # config.yaml -# Ollama endpoints +# Ollama endpoints local + remote endpoints: - - http://192.168.0.50:11434 + - http://localhost:11434 - http://192.168.0.51:11434 - http://192.168.0.52:11434 # External OpenAI-compatible endpoints (will NOT be queried for /api/ps /api/ps_details) @@ -12,7 +12,7 @@ endpoints: # and included in the model selection pool for inference routing llama_server_endpoints: - http://localhost:8080/v1 - - http://localhost:8081/v1 + - http://192.168.0.33:8081/v1 # Maximum concurrent connections *per endpoint‑model pair* (equals to OLLAMA_NUM_PARALLEL) max_concurrent_connections: 2 @@ -28,5 +28,5 @@ api_keys: "http://192.168.0.51:11434": "ollama" "http://192.168.0.52:11434": "ollama" "https://api.openai.com/v1": "${OPENAI_KEY}" - "http://localhost:8080/v1": "llama-server" # Optional API key for llama-server - "http://localhost:8081/v1": "llama-server" \ No newline at end of file + "http://localhost:8080/v1": "llama-server" # Optional API key for llama-server - depends on llama_server config + "http://192.168.0.33:8081/v1": "llama-server" \ No newline at end of file