mirror of
https://github.com/prosolis/gogobee.git
synced 2026-09-14 02:41:09 +00:00
prosolis
583616f9d0
Replaces the per-plugin Ollama HTTP calls with internal/llm, which picks a backend from the environment (vLLM or Ollama) behind one Chat interface, plus internal/plugin/llm_client.go as the plugin-facing wrapper. Startup now logs llm_backend/llm_endpoint/llm_model instead of the two OLLAMA_* vars, which no longer describe where inference actually goes. These files were already running in prod from the vLLM migration but had never been committed; this is that live state, byte-for-byte.
30 lines
649 B
Go
30 lines
649 B
Go
package llm
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"time"
|
|
)
|
|
|
|
// pingTimeout keeps a liveness probe short — /botinfo renders synchronously and
|
|
// a hung endpoint must not hold the reply.
|
|
const pingTimeout = 5 * time.Second
|
|
|
|
func getJSON(ctx context.Context, url string, out any) error {
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
resp, err := http.DefaultClient.Do(req)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK {
|
|
return fmt.Errorf("HTTP %d", resp.StatusCode)
|
|
}
|
|
return json.NewDecoder(resp.Body).Decode(out)
|
|
}
|