forked from QuantumNous/new-api
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathpricing.go
More file actions
433 lines (397 loc) · 14 KB
/
Copy pathpricing.go
File metadata and controls
433 lines (397 loc) · 14 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
package model
import (
"fmt"
"strings"
"sync"
"time"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/constant"
"github.com/QuantumNous/new-api/relaykit/dto"
"github.com/QuantumNous/new-api/setting/billing_setting"
"github.com/QuantumNous/new-api/setting/ratio_setting"
"github.com/QuantumNous/new-api/types"
)
type Pricing struct {
ModelName string `json:"model_name"`
Description string `json:"description,omitempty"`
Icon string `json:"icon,omitempty"`
Tags string `json:"tags,omitempty"`
VendorID int `json:"vendor_id,omitempty"`
QuotaType int `json:"quota_type"`
ModelRatio float64 `json:"model_ratio"`
ModelPrice float64 `json:"model_price"`
OwnerBy string `json:"owner_by"`
CompletionRatio float64 `json:"completion_ratio"`
CacheRatio *float64 `json:"cache_ratio,omitempty"`
CreateCacheRatio *float64 `json:"create_cache_ratio,omitempty"`
ImageRatio *float64 `json:"image_ratio,omitempty"`
AudioRatio *float64 `json:"audio_ratio,omitempty"`
AudioCompletionRatio *float64 `json:"audio_completion_ratio,omitempty"`
EnableGroup []string `json:"enable_groups"`
SupportedEndpointTypes []constant.EndpointType `json:"supported_endpoint_types"`
BillingMode string `json:"billing_mode,omitempty"`
BillingExpr string `json:"billing_expr,omitempty"`
PricingVersion string `json:"pricing_version,omitempty"`
}
type PricingVendor struct {
ID int `json:"id"`
Name string `json:"name"`
Description string `json:"description,omitempty"`
Icon string `json:"icon,omitempty"`
}
var (
pricingMap []Pricing
vendorsList []PricingVendor
supportedEndpointMap map[string]common.EndpointInfo
lastGetPricingTime time.Time
updatePricingLock sync.Mutex
// 缓存映射:模型名 -> 启用分组 / 计费类型
modelEnableGroups = make(map[string][]string)
modelQuotaTypeMap = make(map[string]int)
modelEnableGroupsLock = sync.RWMutex{}
)
var (
modelSupportEndpointTypes = make(map[string][]constant.EndpointType)
modelSupportEndpointsLock = sync.RWMutex{}
)
func GetPricing() []Pricing {
if time.Since(lastGetPricingTime) > time.Minute*1 || len(pricingMap) == 0 {
updatePricingLock.Lock()
defer updatePricingLock.Unlock()
// Double check after acquiring the lock
if time.Since(lastGetPricingTime) > time.Minute*1 || len(pricingMap) == 0 {
modelSupportEndpointsLock.Lock()
defer modelSupportEndpointsLock.Unlock()
updatePricing()
}
}
return pricingMap
}
func InvalidatePricingCache() {
updatePricingLock.Lock()
defer updatePricingLock.Unlock()
pricingMap = nil
vendorsList = nil
lastGetPricingTime = time.Time{}
}
// GetVendors 返回当前定价接口使用到的供应商信息
func GetVendors() []PricingVendor {
if time.Since(lastGetPricingTime) > time.Minute*1 || len(pricingMap) == 0 {
// 保证先刷新一次
GetPricing()
}
return vendorsList
}
func GetModelSupportEndpointTypes(model string) []constant.EndpointType {
if model == "" {
return make([]constant.EndpointType, 0)
}
modelSupportEndpointsLock.RLock()
defer modelSupportEndpointsLock.RUnlock()
if endpoints, ok := modelSupportEndpointTypes[model]; ok {
return endpoints
}
return make([]constant.EndpointType, 0)
}
func getPricingEndpointTypesForAbility(ability AbilityWithChannel, advancedCustomConfigs map[int]*dto.AdvancedCustomConfig) []constant.EndpointType {
if ability.ChannelType != constant.ChannelTypeAdvancedCustom {
return common.GetEndpointTypesByChannelType(ability.ChannelType, ability.Model)
}
if config := advancedCustomConfigs[ability.ChannelId]; config != nil {
return config.SupportedEndpointTypesForModel(ability.Model)
}
return common.GetEndpointTypesByChannelType(ability.ChannelType, ability.Model)
}
// loadPricingAdvancedCustomConfigs runs inside updatePricing while
// updatePricingLock is held, and nests channelSyncLock.RLock. This defines the
// global lock order updatePricingLock -> channelSyncLock: any code path holding
// channelSyncLock must release it before touching the pricing cache (see
// InitChannelCache / CacheUpdateChannel), otherwise it deadlocks.
// The returned configs are pointers shared with the channel cache; they are
// replaced wholesale on update and never mutated in place, so reading them after
// RUnlock is safe.
func loadPricingAdvancedCustomConfigs(enableAbilities []AbilityWithChannel) map[int]*dto.AdvancedCustomConfig {
channelIDs := make([]int, 0)
seen := make(map[int]struct{})
for _, ability := range enableAbilities {
if ability.ChannelType != constant.ChannelTypeAdvancedCustom {
continue
}
if _, exists := seen[ability.ChannelId]; exists {
continue
}
seen[ability.ChannelId] = struct{}{}
channelIDs = append(channelIDs, ability.ChannelId)
}
if len(channelIDs) == 0 {
return nil
}
configs := make(map[int]*dto.AdvancedCustomConfig, len(channelIDs))
if common.MemoryCacheEnabled {
channelSyncLock.RLock()
defer channelSyncLock.RUnlock()
for _, channelID := range channelIDs {
if config := channel2advancedCustomConfig[channelID]; config != nil {
configs[channelID] = config
}
}
return configs
}
for _, channelID := range channelIDs {
channel, err := CacheGetChannel(channelID)
if err != nil {
common.SysLog(fmt.Sprintf("load advanced custom channel settings error: channel_id=%d, error=%v", channelID, err))
continue
}
if channel.Type != constant.ChannelTypeAdvancedCustom {
continue
}
if config := channel.GetOtherSettings().AdvancedCustom; config != nil {
configs[channelID] = config
}
}
return configs
}
func appendPricingEndpoint(endpoints []string, endpoint string) []string {
if endpoint == "" || common.StringsContains(endpoints, endpoint) {
return endpoints
}
return append(endpoints, endpoint)
}
func updatePricing() {
//modelRatios := common.GetModelRatios()
enableAbilities, err := GetAllEnableAbilityWithChannels()
if err != nil {
common.SysLog(fmt.Sprintf("GetAllEnableAbilityWithChannels error: %v", err))
return
}
// 预加载模型元数据与供应商一次,避免循环查询
var allMeta []Model
_ = DB.Find(&allMeta).Error
metaMap := make(map[string]*Model)
prefixList := make([]*Model, 0)
suffixList := make([]*Model, 0)
containsList := make([]*Model, 0)
for i := range allMeta {
m := &allMeta[i]
if m.NameRule == NameRuleExact {
metaMap[m.ModelName] = m
} else {
switch m.NameRule {
case NameRulePrefix:
prefixList = append(prefixList, m)
case NameRuleSuffix:
suffixList = append(suffixList, m)
case NameRuleContains:
containsList = append(containsList, m)
}
}
}
// 将非精确规则模型匹配到 metaMap
for _, m := range prefixList {
for _, pricingModel := range enableAbilities {
if strings.HasPrefix(pricingModel.Model, m.ModelName) {
if _, exists := metaMap[pricingModel.Model]; !exists {
metaMap[pricingModel.Model] = m
}
}
}
}
for _, m := range suffixList {
for _, pricingModel := range enableAbilities {
if strings.HasSuffix(pricingModel.Model, m.ModelName) {
if _, exists := metaMap[pricingModel.Model]; !exists {
metaMap[pricingModel.Model] = m
}
}
}
}
for _, m := range containsList {
for _, pricingModel := range enableAbilities {
if strings.Contains(pricingModel.Model, m.ModelName) {
if _, exists := metaMap[pricingModel.Model]; !exists {
metaMap[pricingModel.Model] = m
}
}
}
}
// 预加载供应商
var vendors []Vendor
_ = DB.Find(&vendors).Error
vendorMap := make(map[int]*Vendor)
for i := range vendors {
vendorMap[vendors[i].Id] = &vendors[i]
}
// 初始化默认供应商映射
initDefaultVendorMapping(metaMap, vendorMap, enableAbilities)
// 构建对前端友好的供应商列表
vendorsList = make([]PricingVendor, 0, len(vendorMap))
for _, v := range vendorMap {
vendorsList = append(vendorsList, PricingVendor{
ID: v.Id,
Name: v.Name,
Description: v.Description,
Icon: v.Icon,
})
}
modelGroupsMap := make(map[string]*types.Set[string])
for _, ability := range enableAbilities {
groups, ok := modelGroupsMap[ability.Model]
if !ok {
groups = types.NewSet[string]()
modelGroupsMap[ability.Model] = groups
}
groups.Add(ability.Group)
}
//这里使用切片而不是Set,因为一个模型可能支持多个端点类型,并且第一个端点是优先使用端点
modelSupportEndpointsStr := make(map[string][]string)
advancedCustomConfigs := loadPricingAdvancedCustomConfigs(enableAbilities)
// 先根据已有能力填充原生端点
for _, ability := range enableAbilities {
endpoints := modelSupportEndpointsStr[ability.Model]
channelTypes := getPricingEndpointTypesForAbility(ability, advancedCustomConfigs)
for _, channelType := range channelTypes {
if !common.StringsContains(endpoints, string(channelType)) {
endpoints = append(endpoints, string(channelType))
}
}
modelSupportEndpointsStr[ability.Model] = endpoints
}
// 再补充模型自定义端点:若配置有效则追加到已有推断,不再裁剪渠道真实能力
for modelName, meta := range metaMap {
if strings.TrimSpace(meta.Endpoints) == "" {
continue
}
var raw map[string]interface{}
if err := common.Unmarshal([]byte(meta.Endpoints), &raw); err == nil {
endpoints := modelSupportEndpointsStr[modelName]
for k, v := range raw {
switch v.(type) {
case string, map[string]interface{}:
endpoints = appendPricingEndpoint(endpoints, k)
}
}
if len(endpoints) > 0 {
modelSupportEndpointsStr[modelName] = endpoints
}
}
}
modelSupportEndpointTypes = make(map[string][]constant.EndpointType)
for model, endpoints := range modelSupportEndpointsStr {
supportedEndpoints := make([]constant.EndpointType, 0)
for _, endpointStr := range endpoints {
endpointType := constant.EndpointType(endpointStr)
supportedEndpoints = append(supportedEndpoints, endpointType)
}
modelSupportEndpointTypes[model] = supportedEndpoints
}
// 构建全局 supportedEndpointMap(默认 + 自定义覆盖)
supportedEndpointMap = make(map[string]common.EndpointInfo)
// 1. 默认端点
for _, endpoints := range modelSupportEndpointTypes {
for _, et := range endpoints {
if info, ok := common.GetDefaultEndpointInfo(et); ok {
if _, exists := supportedEndpointMap[string(et)]; !exists {
supportedEndpointMap[string(et)] = info
}
}
}
}
// 2. 自定义端点(models 表)覆盖默认
for _, meta := range metaMap {
if strings.TrimSpace(meta.Endpoints) == "" {
continue
}
var raw map[string]interface{}
if err := common.Unmarshal([]byte(meta.Endpoints), &raw); err == nil {
for k, v := range raw {
switch val := v.(type) {
case string:
supportedEndpointMap[k] = common.EndpointInfo{Path: val, Method: "POST"}
case map[string]interface{}:
ep := common.EndpointInfo{Method: "POST"}
if p, ok := val["path"].(string); ok {
ep.Path = p
}
if m, ok := val["method"].(string); ok {
ep.Method = strings.ToUpper(m)
}
supportedEndpointMap[k] = ep
default:
// ignore unsupported types
}
}
}
}
pricingMap = make([]Pricing, 0)
for model, groups := range modelGroupsMap {
pricing := Pricing{
ModelName: model,
EnableGroup: groups.Items(),
SupportedEndpointTypes: modelSupportEndpointTypes[model],
}
// 补充模型元数据(描述、标签、供应商、状态)
if meta, ok := metaMap[model]; ok {
// 若模型被禁用(status!=1),则直接跳过,不返回给前端
if meta.Status != 1 {
continue
}
pricing.Description = meta.Description
pricing.Icon = meta.Icon
pricing.Tags = meta.Tags
pricing.VendorID = meta.VendorID
}
modelPrice, findPrice := ratio_setting.GetModelPrice(model, false)
if findPrice {
pricing.ModelPrice = modelPrice
pricing.QuotaType = 1
} else {
modelRatio, _, _ := ratio_setting.GetModelRatio(model)
pricing.ModelRatio = modelRatio
pricing.CompletionRatio = ratio_setting.GetCompletionRatio(model)
pricing.QuotaType = 0
}
if cacheRatio, ok := ratio_setting.GetCacheRatio(model); ok {
pricing.CacheRatio = &cacheRatio
}
if createCacheRatio, ok := ratio_setting.GetCreateCacheRatio(model); ok {
pricing.CreateCacheRatio = &createCacheRatio
}
if imageRatio, ok := ratio_setting.GetImageRatio(model); ok {
pricing.ImageRatio = &imageRatio
}
if ratio_setting.ContainsAudioRatio(model) {
audioRatio := ratio_setting.GetAudioRatio(model)
pricing.AudioRatio = &audioRatio
}
if ratio_setting.ContainsAudioCompletionRatio(model) {
audioCompletionRatio := ratio_setting.GetAudioCompletionRatio(model)
pricing.AudioCompletionRatio = &audioCompletionRatio
}
if billingMode := billing_setting.GetBillingMode(model); billingMode == "tiered_expr" {
if expr, ok := billing_setting.GetBillingExpr(model); ok && strings.TrimSpace(expr) != "" {
pricing.BillingMode = billingMode
pricing.BillingExpr = expr
}
}
pricingMap = append(pricingMap, pricing)
}
// 防止大更新后数据不通用
if len(pricingMap) > 0 {
pricingMap[0].PricingVersion = "5a90f2b86c08bd983a9a2e6d66c255f4eaef9c4bc934386d2b6ae84ef0ff1f1f"
}
// 刷新缓存映射,供高并发快速查询
modelEnableGroupsLock.Lock()
modelEnableGroups = make(map[string][]string)
modelQuotaTypeMap = make(map[string]int)
for _, p := range pricingMap {
modelEnableGroups[p.ModelName] = p.EnableGroup
modelQuotaTypeMap[p.ModelName] = p.QuotaType
}
modelEnableGroupsLock.Unlock()
lastGetPricingTime = time.Now()
}
// GetSupportedEndpointMap 返回全局端点到路径的映射
func GetSupportedEndpointMap() map[string]common.EndpointInfo {
return supportedEndpointMap
}