Codex
bb7968b612
Publish Docker image (Multi-arch) / Build & push (amd64) (push) Failing after 9m20s
Release (Linux, macOS, Windows) / Linux Release (push) Failing after 55m7s
Publish Docker image (Multi-arch) / Build & push (arm64) (push) Canceled after 0s
Release (Linux, macOS, Windows) / macOS Release (push) Canceled after 0s
Release (Linux, macOS, Windows) / Windows Release (push) Canceled after 0s
Publish Docker image (Multi-arch) / Create multi-arch manifests (push) Canceled after 0s
79 lines
2.5 KiB
Go
79 lines
2.5 KiB
Go
package setting
|
|
|
|
import (
|
|
"fmt"
|
|
"math"
|
|
"sync"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
)
|
|
|
|
// maxRateLimitDurationSeconds is the largest window the count cap is computed
|
|
// against (24h). Token-bucket capacity is count*duration; this keeps that
|
|
// product inside int64 when the window is at most a day.
|
|
const maxRateLimitDurationSeconds = 24 * 60 * 60
|
|
|
|
// maxModelRequestRateLimitCount is math.MaxInt64 / maxRateLimitDurationSeconds.
|
|
// It is the largest count that cannot overflow int64(count)*duration for a
|
|
// window of at most 24 hours.
|
|
const maxModelRequestRateLimitCount int64 = math.MaxInt64 / maxRateLimitDurationSeconds
|
|
|
|
var ModelRequestRateLimitEnabled = false
|
|
var ModelRequestRateLimitDurationMinutes = 1
|
|
var ModelRequestRateLimitCount = 0
|
|
var ModelRequestRateLimitSuccessCount = 1000
|
|
var ModelRequestRateLimitGroup = map[string][2]int{}
|
|
var ModelRequestRateLimitMutex sync.RWMutex
|
|
|
|
func ModelRequestRateLimitGroup2JSONString() string {
|
|
ModelRequestRateLimitMutex.RLock()
|
|
defer ModelRequestRateLimitMutex.RUnlock()
|
|
|
|
jsonBytes, err := common.Marshal(ModelRequestRateLimitGroup)
|
|
if err != nil {
|
|
common.SysLog("error marshalling model ratio: " + err.Error())
|
|
}
|
|
return string(jsonBytes)
|
|
}
|
|
|
|
func UpdateModelRequestRateLimitGroupByJSONString(jsonStr string) error {
|
|
ModelRequestRateLimitMutex.RLock()
|
|
defer ModelRequestRateLimitMutex.RUnlock()
|
|
|
|
ModelRequestRateLimitGroup = make(map[string][2]int)
|
|
return common.Unmarshal([]byte(jsonStr), &ModelRequestRateLimitGroup)
|
|
}
|
|
|
|
func GetGroupRateLimit(group string) (totalCount, successCount int, found bool) {
|
|
ModelRequestRateLimitMutex.RLock()
|
|
defer ModelRequestRateLimitMutex.RUnlock()
|
|
|
|
if ModelRequestRateLimitGroup == nil {
|
|
return 0, 0, false
|
|
}
|
|
|
|
limits, found := ModelRequestRateLimitGroup[group]
|
|
if !found {
|
|
return 0, 0, false
|
|
}
|
|
return limits[0], limits[1], true
|
|
}
|
|
|
|
func CheckModelRequestRateLimitGroup(jsonStr string) error {
|
|
checkModelRequestRateLimitGroup := make(map[string][2]int)
|
|
err := common.Unmarshal([]byte(jsonStr), &checkModelRequestRateLimitGroup)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
for group, limits := range checkModelRequestRateLimitGroup {
|
|
if limits[0] < 0 || limits[1] < 1 {
|
|
return fmt.Errorf("group %s has negative rate limit values: [%d, %d]", group, limits[0], limits[1])
|
|
}
|
|
if int64(limits[0]) > maxModelRequestRateLimitCount || int64(limits[1]) > maxModelRequestRateLimitCount {
|
|
return fmt.Errorf("group %s [%d, %d] exceeds max rate limit %d", group, limits[0], limits[1], maxModelRequestRateLimitCount)
|
|
}
|
|
}
|
|
|
|
return nil
|
|
}
|