Files
llama-swap/proxy/config/peer.go
T
Benson Wong 22e098ac8b Add Peer Model Support (#438)
This PR allows a single llama-swap to be the central proxy for models served by other inference servers. The peer servers can be another llama-swap or any API that supports the /v1/* inference endpoint.

Updates: #433, #299
Closes: #296
2025-12-27 20:18:06 -08:00

48 lines
1010 B
Go

package config
import (
"fmt"
"net/url"
)
type PeerDictionaryConfig map[string]PeerConfig
type PeerConfig struct {
Proxy string `yaml:"proxy"`
ProxyURL *url.URL `yaml:"-"`
ApiKey string `yaml:"apiKey"`
Models []string `yaml:"models"`
}
func (c *PeerConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
type rawPeerConfig PeerConfig
defaults := rawPeerConfig{
Proxy: "",
ApiKey: "",
Models: []string{},
}
if err := unmarshal(&defaults); err != nil {
return err
}
// Validate proxy is not empty
if defaults.Proxy == "" {
return fmt.Errorf("proxy is required")
}
// Validate proxy is a valid URL and store the parsed value
parsedURL, err := url.Parse(defaults.Proxy)
if err != nil {
return fmt.Errorf("invalid peer proxy URL (%s): %w", defaults.Proxy, err)
}
defaults.ProxyURL = parsedURL
// Validate models is not empty
if len(defaults.Models) == 0 {
return fmt.Errorf("peer models can not be empty")
}
*c = PeerConfig(defaults)
return nil
}