xinyin025/new-api
1
0
Fork 0
mirror of https://github.com/linux-do/new-api.git synced 2025-09-18 00:16:37 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'Calcium-Ion:main' into new512

Browse Source
This commit is contained in:
iszcz 2024-05-17 12:53:23 +08:00 committed by GitHub
commit f956e4489f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
23 changed files with 221 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
common/constants.go
View File

@ -208,6 +208,7 @@ const (
ChannelTypeLingYiWanWu = 31
ChannelTypeAws = 33
ChannelTypeCohere = 34
ChannelTypeMiniMax = 35
ChannelTypeDummy // this one is only for count, do not add any channel after this
)

26
common/model-ratio.go
View File

@ -69,9 +69,17 @@ var DefaultModelRatio = map[string]float64{
"claude-3-haiku-20240307": 0.125, // $0.25 / 1M tokens
"claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens
"claude-3-opus-20240229": 7.5, // $15 / 1M tokens
"ERNIE-Bot": 0.8572, // ￥0.012 / 1k tokens
"ERNIE-Bot-turbo": 0.5715, // ￥0.008 / 1k tokens
"ERNIE-Bot-4": 8.572, // ￥0.12 / 1k tokens
"ERNIE-Bot": 0.8572, // ￥0.012 / 1k tokens //renamed to ERNIE-3.5-8K
"ERNIE-Bot-turbo": 0.5715, // ￥0.008 / 1k tokens //renamed to ERNIE-Lite-8K
"ERNIE-Bot-4": 8.572, // ￥0.12 / 1k tokens //renamed to ERNIE-4.0-8K
"ERNIE-4.0-8K": 8.572, // ￥0.12 / 1k tokens
"ERNIE-3.5-8K": 0.8572, // ￥0.012 / 1k tokens
"ERNIE-Speed-8K": 0.2858, // ￥0.004 / 1k tokens
"ERNIE-Speed-128K": 0.2858, // ￥0.004 / 1k tokens
"ERNIE-Lite-8K": 0.2143, // ￥0.003 / 1k tokens
"ERNIE-Tiny-8K": 0.0715, // ￥0.001 / 1k tokens
"ERNIE-Character-8K": 0.2858, // ￥0.004 / 1k tokens
"ERNIE-Functions-8K": 0.2858, // ￥0.004 / 1k tokens
"Embedding-V1": 0.1429, // ￥0.002 / 1k tokens
"PaLM-2": 1,
"gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
@ -98,6 +106,9 @@ var DefaultModelRatio = map[string]float64{
"SparkDesk-v3.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.5": 1.2858, // ￥0.018 / 1k tokens
"360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
"360gpt-turbo": 0.0858, // ¥0.0012 / 1k tokens
"360gpt-turbo-responsibility-8k": 0.8572, // ¥0.012 / 1k tokens
"360gpt-pro": 0.8572, // ¥0.012 / 1k tokens
"embedding-bert-512-v1": 0.0715, // ¥0.001 / 1k tokens
"embedding_s1_v1": 0.0715, // ¥0.001 / 1k tokens
"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
@ -289,6 +300,15 @@ func GetCompletionRatio(name string) float64 {
if strings.HasPrefix(name, "deepseek") {
return 2
}
if strings.HasPrefix(name, "ERNIE-Speed-") {
return 2
} else if strings.HasPrefix(name, "ERNIE-Lite-") {
return 2
} else if strings.HasPrefix(name, "ERNIE-Character") {
return 2
} else if strings.HasPrefix(name, "ERNIE-Functions") {
return 2
}
switch name {
case "llama2-70b-4096":
return 0.8 / 0.64

9
common/utils.go
View File

@ -258,3 +258,12 @@ func MapToJsonStrFloat(m map[string]float64) string {
}
return string(bytes)
}
func StrToMap(str string) map[string]interface{} {
m := make(map[string]interface{})
err := json.Unmarshal([]byte(str), &m)
if err != nil {
return nil
}
return m
}

14
controller/channel-test.go
View File

@ -64,7 +64,21 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
} else {
testModel = adaptor.GetModelList()[0]
}
} else {
modelMapping := *channel.ModelMapping
if modelMapping != "" && modelMapping != "{}" {
modelMap := make(map[string]string)
err := json.Unmarshal([]byte(modelMapping), &modelMap)
if err != nil {
openaiErr := service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError).Error
return err, &openaiErr
}
if modelMap[testModel] != "" {
testModel = modelMap[testModel]
}
}
}
request := buildTestRequest()
request.Model = testModel
meta.UpstreamModelName = testModel

16
controller/model.go
View File

@ -11,6 +11,7 @@ import (
"one-api/relay"
"one-api/relay/channel/ai360"
"one-api/relay/channel/lingyiwanwu"
"one-api/relay/channel/minimax"
"one-api/relay/channel/moonshot"
relaycommon "one-api/relay/common"
relayconstant "one-api/relay/constant"
@ -79,7 +80,7 @@ func init() {
Id: modelName,
Object: "model",
Created: 1626777600,
OwnedBy: "moonshot",
OwnedBy: moonshot.ChannelName,
Permission: permission,
Root: modelName,
Parent: nil,
@ -90,7 +91,18 @@ func init() {
Id: modelName,
Object: "model",
Created: 1626777600,
OwnedBy: "lingyiwanwu",
OwnedBy: lingyiwanwu.ChannelName,
Permission: permission,
Root: modelName,
Parent: nil,
})
}
for _, modelName := range minimax.ModelList {
openAIModels = append(openAIModels, dto.OpenAIModels{
Id: modelName,
Object: "model",
Created: 1626777600,
OwnedBy: minimax.ChannelName,
Permission: permission,
Root: modelName,
Parent: nil,

7
controller/relay.go
View File

@ -43,7 +43,7 @@ func Relay(c *gin.Context) {
group := c.GetString("group")
originalModel := c.GetString("original_model")
openaiErr := relayHandler(c, relayMode)
useChannel := []int{channelId}
c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
if openaiErr != nil {
go processChannelError(c, channelId, openaiErr)
} else {
@ -56,7 +56,9 @@ func Relay(c *gin.Context) {
break
}
channelId = channel.Id
useChannel = append(useChannel, channelId)
useChannel := c.GetStringSlice("use_channel")
useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
c.Set("use_channel", useChannel)
common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
middleware.SetupContextForSelectedChannel(c, channel, originalModel)
@ -67,6 +69,7 @@ func Relay(c *gin.Context) {
go processChannelError(c, channelId, openaiErr)
}
}
useChannel := c.GetStringSlice("use_channel")
if len(useChannel) > 1 {
retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
common.LogInfo(c.Request.Context(), retryLogStr)

9
model/log.go
View File

@ -142,6 +142,15 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
tx = tx.Where("created_at <= ?", endTimestamp)
}
err = tx.Order("id desc").Limit(num).Offset(startIdx).Omit("id").Find(&logs).Error
for i := range logs {
var otherMap map[string]interface{}
otherMap = common.StrToMap(logs[i].Other)
if otherMap != nil {
// delete admin
delete(otherMap, "admin_info")
}
logs[i].Other = common.MapToJsonStr(otherMap)
}
return logs, err
}

12
model/main.go
View File

@ -93,12 +93,12 @@ func InitDB() (err error) {
if !common.IsMasterNode {
return nil
}
if common.UsingMySQL {
_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;") // TODO: delete this line when most users have upgraded
_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);") // TODO: delete this line when most users have upgraded
_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);") // TODO: delete this line when most users have upgraded
}
//if common.UsingMySQL {
// _, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;") // TODO: delete this line when most users have upgraded
// _, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);") // TODO: delete this line when most users have upgraded
// _, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
// _, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);") // TODO: delete this line when most users have upgraded
//}
common.SysLog("database migration started")
err = db.AutoMigrate(&Channel{})
if err != nil {

2
model/token.go
View File

@ -11,7 +11,7 @@ import (
type Token struct {
Id int `json:"id"`
UserId int `json:"user_id"`
UserId int `json:"user_id" gorm:"index"`
Key string `json:"key" gorm:"type:char(48);uniqueIndex"`
Status int `json:"status" gorm:"default:1"`
Name string `json:"name" gorm:"index" `

3
relay/channel/ai360/constants.go
View File

@ -1,6 +1,9 @@
package ai360
var ModelList = []string{
"360gpt-turbo",
"360gpt-turbo-responsibility-8k",
"360gpt-pro",
"360GPT_S2_V9",
"embedding-bert-512-v1",
"embedding_s1_v1",

17
relay/channel/baidu/adaptor.go
View File

@ -9,6 +9,7 @@ import (
"one-api/relay/channel"
relaycommon "one-api/relay/common"
"one-api/relay/constant"
"strings"
)
type Adaptor struct {
@ -33,8 +34,24 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
case "BLOOMZ-7B":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
case "ERNIE-4.0-8K":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
case "ERNIE-3.5-8K":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
case "ERNIE-Speed-8K":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed"
case "ERNIE-Character-8K":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-char-8k"
case "ERNIE-Functions-8K":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-func-8k"
case "ERNIE-Lite-8K-0922":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
case "Yi-34B-Chat":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/yi_34b_chat"
case "Embedding-V1":
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
default:
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/" + strings.ToLower(info.UpstreamModelName)
}
var accessToken string
var err error

18
relay/channel/baidu/constants.go
View File

@ -1,11 +1,19 @@
package baidu
var ModelList = []string{
"ERNIE-Bot-4",
"ERNIE-Bot-8K",
"ERNIE-Bot",
"ERNIE-Speed",
"ERNIE-Bot-turbo",
"ERNIE-3.5-8K",
"ERNIE-4.0-8K",
"ERNIE-Speed-8K",
"ERNIE-Speed-128K",
"ERNIE-Lite-8K",
"ERNIE-Tiny-8K",
"ERNIE-Character-8K",
"ERNIE-Functions-8K",
//"ERNIE-Bot-4",
//"ERNIE-Bot-8K",
//"ERNIE-Bot",
//"ERNIE-Speed",
//"ERNIE-Bot-turbo",
"Embedding-V1",
}

2
relay/channel/lingyiwanwu/constrants.go
View File

@ -7,3 +7,5 @@ var ModelList = []string{
"yi-34b-chat-200k",
"yi-vl-plus",
}
var ChannelName = "lingyiwanwu"

13
relay/channel/minimax/constants.go Normal file
View File

@ -0,0 +1,13 @@
package minimax
// https://www.minimaxi.com/document/guides/chat-model/V2?id=65e0736ab2845de20908e2dd
var ModelList = []string{
"abab6.5-chat",
"abab6.5s-chat",
"abab6-chat",
"abab5.5-chat",
"abab5.5s-chat",
}
var ChannelName = "minimax"

10
relay/channel/minimax/relay-minimax.go Normal file
View File

@ -0,0 +1,10 @@
package minimax
import (
"fmt"
relaycommon "one-api/relay/common"
)
func GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
return fmt.Sprintf("%s/v1/text/chatcompletion_v2", info.BaseUrl), nil
}

2
relay/channel/moonshot/constants.go
View File

@ -5,3 +5,5 @@ var ModelList = []string{
"moonshot-v1-32k",
"moonshot-v1-128k",
}
var ChannelName = "moonshot"

26
relay/channel/openai/adaptor.go
View File

@ -11,6 +11,7 @@ import (
"one-api/relay/channel"
"one-api/relay/channel/ai360"
"one-api/relay/channel/lingyiwanwu"
"one-api/relay/channel/minimax"
"one-api/relay/channel/moonshot"
relaycommon "one-api/relay/common"
"one-api/service"
@ -26,7 +27,8 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIReq
}
func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
if info.ChannelType == common.ChannelTypeAzure {
switch info.ChannelType {
case common.ChannelTypeAzure:
// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
requestURL := strings.Split(info.RequestURLPath, "?")[0]
requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, info.ApiVersion)
@ -37,9 +39,16 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
}
case common.ChannelTypeMiniMax:
return minimax.GetRequestURL(info)
//case common.ChannelTypeCustom:
// url := info.BaseUrl
// url = strings.Replace(url, "{model}", info.UpstreamModelName, -1)
// return url, nil
default:
return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
}
}
func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
channel.SetupApiRequestHeader(info, c, req)
@ -90,11 +99,24 @@ func (a *Adaptor) GetModelList() []string {
return moonshot.ModelList
case common.ChannelTypeLingYiWanWu:
return lingyiwanwu.ModelList
case common.ChannelTypeMiniMax:
return minimax.ModelList
default:
return ModelList
}
}
func (a *Adaptor) GetChannelName() string {
switch a.ChannelType {
case common.ChannelType360:
return ai360.ChannelName
case common.ChannelTypeMoonshot:
return moonshot.ChannelName
case common.ChannelTypeLingYiWanWu:
return lingyiwanwu.ChannelName
case common.ChannelTypeMiniMax:
return minimax.ChannelName
default:
return ChannelName
}
}

4
relay/constant/api_type.go
View File

@ -15,7 +15,7 @@ const (
APITypeAIProxyLibrary
APITypeTencent
APITypeGemini
APITypeZhipu_v4
APITypeZhipuV4
APITypeOllama
APITypePerplexity
APITypeAws
@ -48,7 +48,7 @@ func ChannelType2APIType(channelType int) (int, bool) {
case common.ChannelTypeGemini:
apiType = APITypeGemini
case common.ChannelTypeZhipu_v4:
apiType = APITypeZhipu_v4
apiType = APITypeZhipuV4
case common.ChannelTypeOllama:
apiType = APITypeOllama
case common.ChannelTypePerplexity:

3
relay/relay-text.go
View File

@ -320,6 +320,9 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRe
other["group_ratio"] = groupRatio
other["completion_ratio"] = completionRatio
other["model_price"] = modelPrice
adminInfo := make(map[string]interface{})
adminInfo["use_channel"] = ctx.GetStringSlice("use_channel")
other["admin_info"] = adminInfo
model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, promptTokens, completionTokens, logModel, tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream, other)
//if quota != 0 {

2
relay/relay_adaptor.go
View File

@ -41,7 +41,7 @@ func GetAdaptor(apiType int) channel.Adaptor {
return &xunfei.Adaptor{}
case constant.APITypeZhipu:
return &zhipu.Adaptor{}
case constant.APITypeZhipu_v4:
case constant.APITypeZhipuV4:
return &zhipu_4v.Adaptor{}
case constant.APITypeOllama:
return &ollama.Adaptor{}

7
web/src/components/ChannelsTable.js
View File

@ -6,6 +6,7 @@ import {
showError,
showInfo,
showSuccess,
showWarning,
timestamp2string,
} from '../helpers';
@ -309,6 +310,12 @@ const ChannelsTable = () => {
const setChannelFormat = (channels) => {
for (let i = 0; i < channels.length; i++) {
if (channels[i].type === 8) {
showWarning(
'检测到您使用了“自定义渠道”类型，请更换为“OpenAI”渠道类型！',
);
showWarning('下个版本将不再支持“自定义渠道”类型！');
}
channels[i].key = '' + channels[i].id;
let test_models = [];
channels[i].models.split(',').forEach((item, index) => {

24
web/src/components/LogsTable.js
View File

@ -294,6 +294,30 @@ const LogsTable = () => {
);
},
},
{
title: '重试',
dataIndex: 'retry',
className: isAdmin() ? 'tableShow' : 'tableHiddle',
render: (text, record, index) => {
let content = '渠道：' + record.channel;
if (record.other !== '') {
let other = JSON.parse(record.other);
if (other.admin_info !== undefined) {
if (
other.admin_info.use_channel !== null &&
other.admin_info.use_channel !== undefined &&
other.admin_info.use_channel !== ''
) {
// channel id array
let useChannel = other.admin_info.use_channel;
let useChannelStr = useChannel.join('->');
content = `渠道：${useChannelStr}`;
}
}
}
return isAdminUser ? <div>{content}</div> : <></>;
},
},
{
title: '详情',
dataIndex: 'content',

15
web/src/constants/channel.constants.js
View File

@ -36,13 +36,6 @@ export const CHANNEL_OPTIONS = [
color: 'teal',
label: 'Azure OpenAI',
},
{
key: 11,
text: 'Google PaLM2',
value: 11,
color: 'orange',
label: 'Google PaLM2',
},
{
key: 24,
text: 'Google Gemini',
@ -92,10 +85,18 @@ export const CHANNEL_OPTIONS = [
color: 'purple',
label: '智谱 GLM-4V',
},
{
key: 11,
text: 'Google PaLM2',
value: 11,
color: 'orange',
label: 'Google PaLM2',
},
{ key: 25, text: 'Moonshot', value: 25, color: 'green', label: 'Moonshot' },
{ key: 19, text: '360 智脑', value: 19, color: 'blue', label: '360 智脑' },
{ key: 23, text: '腾讯混元', value: 23, color: 'teal', label: '腾讯混元' },
{ key: 31, text: '零一万物', value: 31, color: 'green', label: '零一万物' },
{ key: 35, text: 'MiniMax', value: 35, color: 'green', label: 'MiniMax' },
{ key: 8, text: '自定义渠道', value: 8, color: 'pink', label: '自定义渠道' },
{
key: 22,