Merge remote-tracking branch 'upstream/main'

This commit is contained in:
ckt1031 2023-09-04 14:57:40 +08:00
commit cd3d1b9f1b
21 changed files with 731 additions and 127 deletions

View File

@ -129,7 +129,7 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型,开箱即用
数据将会保存在宿主机的 `/home/ubuntu/data/one-api` 目录,请确保该目录存在且具有写入权限,或者更改为合适的目录。
如果启动失败,请添加 `--privileged=true`,具体参考 #482
如果启动失败,请添加 `--privileged=true`,具体参考 https://github.com/songquanpeng/one-api/issues/482
如果上面的镜像无法拉取,可以尝试使用 GitHub 的 Docker 镜像,将上面的 `justsong/one-api` 替换为 `ghcr.io/songquanpeng/one-api` 即可。
@ -326,6 +326,14 @@ graph LR
+ 例子:`CHANNEL_TEST_FREQUENCY=1440`
9. `POLLING_INTERVAL`:批量更新渠道余额以及测试可用性时的请求间隔,单位为秒,默认无间隔。
+ 例子:`POLLING_INTERVAL=5`
10. `BATCH_UPDATE_ENABLED`:启用数据库批量更新聚合,会导致用户额度的更新存在一定的延迟可选值为 `true``false`,未设置则默认为 `false`
+ 例子:`BATCH_UPDATE_ENABLED=true`
+ 如果你遇到了数据库连接数过多的问题,可以尝试启用该选项。
11. `BATCH_UPDATE_INTERVAL=5`:批量更新聚合的时间间隔,单位为秒,默认为 `5`
+ 例子:`BATCH_UPDATE_INTERVAL=5`
12. 请求频率限制:
+ `GLOBAL_API_RATE_LIMIT`:全局 API 速率限制(除中继请求外),单 ip 三分钟内的最大请求数,默认为 `180`
+ `GLOBAL_WEB_RATE_LIMIT`:全局 Web 速率限制,单 ip 三分钟内的最大请求数,默认为 `60`
### 命令行参数
1. `--port <port_number>`: 指定服务器监听的端口号,默认为 `3000`

View File

@ -103,6 +103,9 @@ var RequestInterval = time.Duration(requestInterval) * time.Second
var SyncFrequency = 10 * 60 // unit is second, will be overwritten by SYNC_FREQUENCY
var BatchUpdateEnabled = false
var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)
const (
RoleGuestUser = 0
RoleCommonUser = 1
@ -120,10 +123,10 @@ var (
// All duration's unit is seconds
// Shouldn't larger then RateLimitKeyExpirationDuration
var (
GlobalApiRateLimitNum = 180
GlobalApiRateLimitNum = GetOrDefault("GLOBAL_API_RATE_LIMIT", 180)
GlobalApiRateLimitDuration int64 = 3 * 60
GlobalWebRateLimitNum = 60
GlobalWebRateLimitNum = GetOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
GlobalWebRateLimitDuration int64 = 3 * 60
UploadRateLimitNum = 10
@ -194,6 +197,8 @@ const (
ChannelTypeXunfei = 18
ChannelType360 = 19
ChannelTypeOpenRouter = 20
ChannelTypeAIProxyLibrary = 21
ChannelTypeFastGPT = 22
)
var ChannelBaseURLs = []string{
@ -218,4 +223,6 @@ var ChannelBaseURLs = []string{
"", // 18
"https://ai.360.cn", // 19
"https://openrouter.ai/api", // 20
"https://api.aiproxy.io", // 21
"https://fastgpt.run/api/openapi", // 22
}

View File

@ -50,9 +50,10 @@ var ModelRatio = map[string]float64{
"chatglm_pro": 0.7143, // ¥0.01 / 1k tokens
"chatglm_std": 0.3572, // ¥0.005 / 1k tokens
"chatglm_lite": 0.1429, // ¥0.002 / 1k tokens
"qwen-v1": 0.8572, // TBD: https://help.aliyun.com/document_detail/2399482.html?spm=a2c4g.2399482.0.0.1ad347feilAgag
"qwen-plus-v1": 0.5715, // Same as above
"SparkDesk": 0.8572, // TBD
"qwen-v1": 0.8572, // ¥0.012 / 1k tokens
"qwen-plus-v1": 1, // ¥0.014 / 1k tokens
"text-embedding-v1": 0.05, // ¥0.0007 / 1k tokens
"SparkDesk": 1.2858, // ¥0.018 / 1k tokens
"360GPT_S2_V9": 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

View File

@ -18,7 +18,7 @@ import (
"github.com/gin-gonic/gin"
)
func testChannel(channel *model.Channel, request ChatRequest) (error, *OpenAIError) {
func testChannel(channel *model.Channel, request ChatRequest) (err error, openaiErr *OpenAIError) {
switch channel.Type {
case common.ChannelTypePaLM:
fallthrough
@ -36,6 +36,11 @@ func testChannel(channel *model.Channel, request ChatRequest) (error, *OpenAIErr
return errors.New("该渠道类型当前版本不支持测试,请手动测试"), nil
case common.ChannelTypeAzure:
request.Model = "gpt-35-turbo"
defer func() {
if err != nil {
err = errors.New("请确保已在 Azure 上创建了 gpt-35-turbo 模型,并且 apiVersion 已正确填写!")
}
}()
default:
request.Model = "gpt-3.5-turbo"
}

View File

@ -360,6 +360,15 @@ func init() {
Root: "qwen-plus-v1",
Parent: nil,
},
{
Id: "text-embedding-v1",
Object: "model",
Created: 1677649963,
OwnedBy: "ali",
Permission: permission,
Root: "text-embedding-v1",
Parent: nil,
},
{
Id: "SparkDesk",
Object: "model",

220
controller/relay-aiproxy.go Normal file
View File

@ -0,0 +1,220 @@
package controller
import (
"bufio"
"encoding/json"
"fmt"
"github.com/gin-gonic/gin"
"io"
"net/http"
"one-api/common"
"strconv"
"strings"
)
// https://docs.aiproxy.io/dev/library#使用已经定制好的知识库进行对话问答
type AIProxyLibraryRequest struct {
Model string `json:"model"`
Query string `json:"query"`
LibraryId string `json:"libraryId"`
Stream bool `json:"stream"`
}
type AIProxyLibraryError struct {
ErrCode int `json:"errCode"`
Message string `json:"message"`
}
type AIProxyLibraryDocument struct {
Title string `json:"title"`
URL string `json:"url"`
}
type AIProxyLibraryResponse struct {
Success bool `json:"success"`
Answer string `json:"answer"`
Documents []AIProxyLibraryDocument `json:"documents"`
AIProxyLibraryError
}
type AIProxyLibraryStreamResponse struct {
Content string `json:"content"`
Finish bool `json:"finish"`
Model string `json:"model"`
Documents []AIProxyLibraryDocument `json:"documents"`
}
func requestOpenAI2AIProxyLibrary(request GeneralOpenAIRequest) *AIProxyLibraryRequest {
query := ""
if len(request.Messages) != 0 {
query = request.Messages[len(request.Messages)-1].Content
}
return &AIProxyLibraryRequest{
Model: request.Model,
Stream: request.Stream,
Query: query,
}
}
func aiProxyDocuments2Markdown(documents []AIProxyLibraryDocument) string {
if len(documents) == 0 {
return ""
}
content := "\n\n参考文档\n"
for i, document := range documents {
content += fmt.Sprintf("%d. [%s](%s)\n", i+1, document.Title, document.URL)
}
return content
}
func responseAIProxyLibrary2OpenAI(response *AIProxyLibraryResponse) *OpenAITextResponse {
content := response.Answer + aiProxyDocuments2Markdown(response.Documents)
choice := OpenAITextResponseChoice{
Index: 0,
Message: Message{
Role: "assistant",
Content: content,
},
FinishReason: "stop",
}
fullTextResponse := OpenAITextResponse{
Id: common.GetUUID(),
Object: "chat.completion",
Created: common.GetTimestamp(),
Choices: []OpenAITextResponseChoice{choice},
}
return &fullTextResponse
}
func documentsAIProxyLibrary(documents []AIProxyLibraryDocument) *ChatCompletionsStreamResponse {
var choice ChatCompletionsStreamResponseChoice
choice.Delta.Content = aiProxyDocuments2Markdown(documents)
choice.FinishReason = &stopFinishReason
return &ChatCompletionsStreamResponse{
Id: common.GetUUID(),
Object: "chat.completion.chunk",
Created: common.GetTimestamp(),
Model: "",
Choices: []ChatCompletionsStreamResponseChoice{choice},
}
}
func streamResponseAIProxyLibrary2OpenAI(response *AIProxyLibraryStreamResponse) *ChatCompletionsStreamResponse {
var choice ChatCompletionsStreamResponseChoice
choice.Delta.Content = response.Content
return &ChatCompletionsStreamResponse{
Id: common.GetUUID(),
Object: "chat.completion.chunk",
Created: common.GetTimestamp(),
Model: response.Model,
Choices: []ChatCompletionsStreamResponseChoice{choice},
}
}
func aiProxyLibraryStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
var usage Usage
scanner := bufio.NewScanner(resp.Body)
scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
if atEOF && len(data) == 0 {
return 0, nil, nil
}
if i := strings.Index(string(data), "\n"); i >= 0 {
return i + 1, data[0:i], nil
}
if atEOF {
return len(data), data, nil
}
return 0, nil, nil
})
dataChan := make(chan string)
stopChan := make(chan bool)
go func() {
for scanner.Scan() {
data := scanner.Text()
if len(data) < 5 { // ignore blank line or wrong format
continue
}
if data[:5] != "data:" {
continue
}
data = data[5:]
dataChan <- data
}
stopChan <- true
}()
setEventStreamHeaders(c)
var documents []AIProxyLibraryDocument
c.Stream(func(w io.Writer) bool {
select {
case data := <-dataChan:
var AIProxyLibraryResponse AIProxyLibraryStreamResponse
err := json.Unmarshal([]byte(data), &AIProxyLibraryResponse)
if err != nil {
common.SysError("error unmarshalling stream response: " + err.Error())
return true
}
if len(AIProxyLibraryResponse.Documents) != 0 {
documents = AIProxyLibraryResponse.Documents
}
response := streamResponseAIProxyLibrary2OpenAI(&AIProxyLibraryResponse)
jsonResponse, err := json.Marshal(response)
if err != nil {
common.SysError("error marshalling stream response: " + err.Error())
return true
}
c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
return true
case <-stopChan:
response := documentsAIProxyLibrary(documents)
jsonResponse, err := json.Marshal(response)
if err != nil {
common.SysError("error marshalling stream response: " + err.Error())
return true
}
c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
return false
}
})
err := resp.Body.Close()
if err != nil {
return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
}
return nil, &usage
}
func aiProxyLibraryHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
var AIProxyLibraryResponse AIProxyLibraryResponse
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
}
err = resp.Body.Close()
if err != nil {
return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
}
err = json.Unmarshal(responseBody, &AIProxyLibraryResponse)
if err != nil {
return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
}
if AIProxyLibraryResponse.ErrCode != 0 {
return &OpenAIErrorWithStatusCode{
OpenAIError: OpenAIError{
Message: AIProxyLibraryResponse.Message,
Type: strconv.Itoa(AIProxyLibraryResponse.ErrCode),
Code: AIProxyLibraryResponse.ErrCode,
},
StatusCode: resp.StatusCode,
}, nil
}
fullTextResponse := responseAIProxyLibrary2OpenAI(&AIProxyLibraryResponse)
jsonResponse, err := json.Marshal(fullTextResponse)
if err != nil {
return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
}
c.Writer.Header().Set("Content-Type", "application/json")
c.Writer.WriteHeader(resp.StatusCode)
_, err = c.Writer.Write(jsonResponse)
return nil, &fullTextResponse.Usage
}

View File

@ -35,6 +35,29 @@ type AliChatRequest struct {
Parameters AliParameters `json:"parameters,omitempty"`
}
type AliEmbeddingRequest struct {
Model string `json:"model"`
Input struct {
Texts []string `json:"texts"`
} `json:"input"`
Parameters *struct {
TextType string `json:"text_type,omitempty"`
} `json:"parameters,omitempty"`
}
type AliEmbedding struct {
Embedding []float64 `json:"embedding"`
TextIndex int `json:"text_index"`
}
type AliEmbeddingResponse struct {
Output struct {
Embeddings []AliEmbedding `json:"embeddings"`
} `json:"output"`
Usage AliUsage `json:"usage"`
AliError
}
type AliError struct {
Code string `json:"code"`
Message string `json:"message"`
@ -44,6 +67,7 @@ type AliError struct {
type AliUsage struct {
InputTokens int `json:"input_tokens"`
OutputTokens int `json:"output_tokens"`
TotalTokens int `json:"total_tokens"`
}
type AliOutput struct {
@ -95,6 +119,70 @@ func requestOpenAI2Ali(request GeneralOpenAIRequest) *AliChatRequest {
}
}
func embeddingRequestOpenAI2Ali(request GeneralOpenAIRequest) *AliEmbeddingRequest {
return &AliEmbeddingRequest{
Model: "text-embedding-v1",
Input: struct {
Texts []string `json:"texts"`
}{
Texts: request.ParseInput(),
},
}
}
func aliEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
var aliResponse AliEmbeddingResponse
err := json.NewDecoder(resp.Body).Decode(&aliResponse)
if err != nil {
return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
}
err = resp.Body.Close()
if err != nil {
return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
}
if aliResponse.Code != "" {
return &OpenAIErrorWithStatusCode{
OpenAIError: OpenAIError{
Message: aliResponse.Message,
Type: aliResponse.Code,
Param: aliResponse.RequestId,
Code: aliResponse.Code,
},
StatusCode: resp.StatusCode,
}, nil
}
fullTextResponse := embeddingResponseAli2OpenAI(&aliResponse)
jsonResponse, err := json.Marshal(fullTextResponse)
if err != nil {
return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
}
c.Writer.Header().Set("Content-Type", "application/json")
c.Writer.WriteHeader(resp.StatusCode)
_, err = c.Writer.Write(jsonResponse)
return nil, &fullTextResponse.Usage
}
func embeddingResponseAli2OpenAI(response *AliEmbeddingResponse) *OpenAIEmbeddingResponse {
openAIEmbeddingResponse := OpenAIEmbeddingResponse{
Object: "list",
Data: make([]OpenAIEmbeddingResponseItem, 0, len(response.Output.Embeddings)),
Model: "text-embedding-v1",
Usage: Usage{TotalTokens: response.Usage.TotalTokens},
}
for _, item := range response.Output.Embeddings {
openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, OpenAIEmbeddingResponseItem{
Object: `embedding`,
Index: item.TextIndex,
Embedding: item.Embedding,
})
}
return &openAIEmbeddingResponse
}
func responseAli2OpenAI(response *AliChatResponse) *OpenAITextResponse {
choice := OpenAITextResponseChoice{
Index: 0,

View File

@ -144,20 +144,9 @@ func streamResponseBaidu2OpenAI(baiduResponse *BaiduChatStreamResponse) *ChatCom
}
func embeddingRequestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduEmbeddingRequest {
baiduEmbeddingRequest := BaiduEmbeddingRequest{
Input: nil,
return &BaiduEmbeddingRequest{
Input: request.ParseInput(),
}
switch request.Input.(type) {
case string:
baiduEmbeddingRequest.Input = []string{request.Input.(string)}
case []any:
for _, item := range request.Input.([]any) {
if str, ok := item.(string); ok {
baiduEmbeddingRequest.Input = append(baiduEmbeddingRequest.Input, str)
}
}
}
return &baiduEmbeddingRequest
}
func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *OpenAIEmbeddingResponse {

View File

@ -22,6 +22,7 @@ const (
APITypeZhipu
APITypeAli
APITypeXunfei
APITypeAIProxyLibrary
)
var httpClient *http.Client
@ -104,6 +105,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
apiType = APITypeAli
case common.ChannelTypeXunfei:
apiType = APITypeXunfei
case common.ChannelTypeAIProxyLibrary:
apiType = APITypeAIProxyLibrary
}
baseURL := common.ChannelBaseURLs[channelType]
requestURL := c.Request.URL.String()
@ -171,6 +174,11 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
fullRequestURL = fmt.Sprintf("https://open.bigmodel.cn/api/paas/v3/model-api/%s/%s", textRequest.Model, method)
case APITypeAli:
fullRequestURL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation"
if relayMode == RelayModeEmbeddings {
fullRequestURL = "https://dashscope.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding"
}
case APITypeAIProxyLibrary:
fullRequestURL = fmt.Sprintf("%s/api/library/ask", baseURL)
}
var promptTokens int
var completionTokens int
@ -257,8 +265,24 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
}
requestBody = bytes.NewBuffer(jsonStr)
case APITypeAli:
var jsonStr []byte
var err error
switch relayMode {
case RelayModeEmbeddings:
aliEmbeddingRequest := embeddingRequestOpenAI2Ali(textRequest)
jsonStr, err = json.Marshal(aliEmbeddingRequest)
default:
aliRequest := requestOpenAI2Ali(textRequest)
jsonStr, err := json.Marshal(aliRequest)
jsonStr, err = json.Marshal(aliRequest)
}
if err != nil {
return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
}
requestBody = bytes.NewBuffer(jsonStr)
case APITypeAIProxyLibrary:
aiProxyLibraryRequest := requestOpenAI2AIProxyLibrary(textRequest)
aiProxyLibraryRequest.LibraryId = c.GetString("library_id")
jsonStr, err := json.Marshal(aiProxyLibraryRequest)
if err != nil {
return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
}
@ -302,6 +326,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
if textRequest.Stream {
req.Header.Set("X-DashScope-SSE", "enable")
}
default:
req.Header.Set("Authorization", "Bearer "+apiKey)
}
req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
req.Header.Set("Accept", c.Request.Header.Get("Accept"))
@ -381,7 +407,6 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
logContent := fmt.Sprintf("模型倍率 %.2f,分组倍率 %.2f", modelRatio, groupRatio)
model.RecordConsumeLog(userId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
model.UpdateChannelUsedQuota(channelId, quota)
}
}
@ -507,7 +532,14 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
}
return nil
} else {
err, usage := aliHandler(c, resp)
var err *OpenAIErrorWithStatusCode
var usage *Usage
switch relayMode {
case RelayModeEmbeddings:
err, usage = aliEmbeddingHandler(c, resp)
default:
err, usage = aliHandler(c, resp)
}
if err != nil {
return err
}
@ -535,6 +567,26 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
} else {
return errorWrapper(errors.New("xunfei api does not support non-stream mode"), "invalid_api_type", http.StatusBadRequest)
}
case APITypeAIProxyLibrary:
if isStream {
err, usage := aiProxyLibraryStreamHandler(c, resp)
if err != nil {
return err
}
if usage != nil {
textResponse.Usage = *usage
}
return nil
} else {
err, usage := aiProxyLibraryHandler(c, resp)
if err != nil {
return err
}
if usage != nil {
textResponse.Usage = *usage
}
return nil
}
default:
return errorWrapper(errors.New("unknown api type"), "unknown_api_type", http.StatusInternalServerError)
}

View File

@ -44,6 +44,25 @@ type GeneralOpenAIRequest struct {
Functions any `json:"functions,omitempty"`
}
func (r GeneralOpenAIRequest) ParseInput() []string {
if r.Input == nil {
return nil
}
var input []string
switch r.Input.(type) {
case string:
input = []string{r.Input.(string)}
case []any:
input = make([]string, 0, len(r.Input.([]any)))
for _, item := range r.Input.([]any) {
if str, ok := item.(string); ok {
input = append(input, str)
}
}
}
return input
}
type ChatRequest struct {
Model string `json:"model"`
Messages []Message `json:"messages"`

View File

@ -610,10 +610,11 @@
"警告": "Warning",
"确定": "Confirm",
"。": ".",
"点击查看": "click to view",
"使用明细(总消耗额度:" : "Usage Details (Total Consumption Quota: ",
"": ")",
"360 智脑": "360 AI",
"模型版本": "Model version",
"请输入星火大模型版本注意是接口地址中的版本号例如v2.1": "Please enter the version of the Starfire model, note that it is the version number in the interface address, for example: v2.1"
"请输入星火大模型版本注意是接口地址中的版本号例如v2.1": "Please enter the version of the Starfire model, note that it is the version number in the interface address, for example: v2.1",
"点击查看": "click to view",
"请确保已在 Azure 上创建了 gpt-35-turbo 模型,并且 apiVersion 已正确填写!": "Please make sure that the gpt-35-turbo model has been created on Azure, and the apiVersion has been filled in correctly!"
}

View File

@ -98,6 +98,11 @@ func main() {
}
go controller.AutomaticallyTestChannels(frequency)
}
if os.Getenv("BATCH_UPDATE_ENABLED") == "true" {
common.BatchUpdateEnabled = true
common.SysLog("batch update enabled with interval " + strconv.Itoa(common.BatchUpdateInterval) + "s")
model.InitBatchUpdater()
}
// controller.InitTokenEncoders()
// Initialize HTTP server

View File

@ -100,7 +100,18 @@ func TokenAuth() func(c *gin.Context) {
c.Abort()
return
}
if !model.CacheIsUserEnabled(token.UserId) {
userEnabled, err := model.IsUserEnabled(token.UserId)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{
"error": gin.H{
"message": err.Error(),
"type": "one_api_error",
},
})
c.Abort()
return
}
if !userEnabled {
c.JSON(http.StatusForbidden, gin.H{
"error": gin.H{
"message": "用户已被封禁",

View File

@ -116,8 +116,13 @@ func Distribute() func(c *gin.Context) {
c.Set("model_mapping", channel.ModelMapping)
c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
c.Set("base_url", channel.BaseURL)
if channel.Type == common.ChannelTypeAzure || channel.Type == common.ChannelTypeXunfei {
switch channel.Type {
case common.ChannelTypeAzure:
c.Set("api_version", channel.Other)
case common.ChannelTypeXunfei:
c.Set("api_version", channel.Other)
case common.ChannelTypeAIProxyLibrary:
c.Set("library_id", channel.Other)
}
c.Next()
}

View File

@ -109,23 +109,28 @@ func CacheDecreaseUserQuota(id int, quota int) error {
return err
}
func CacheIsUserEnabled(userId int) bool {
func CacheIsUserEnabled(userId int) (bool, error) {
if !common.RedisEnabled {
return IsUserEnabled(userId)
}
enabled, err := common.RedisGet(fmt.Sprintf("user_enabled:%d", userId))
if err != nil {
status := common.UserStatusDisabled
if IsUserEnabled(userId) {
status = common.UserStatusEnabled
if err == nil {
return enabled == "1", nil
}
userEnabled, err := IsUserEnabled(userId)
if err != nil {
return false, err
}
enabled = "0"
if userEnabled {
enabled = "1"
}
enabled = fmt.Sprintf("%d", status)
err = common.RedisSet(fmt.Sprintf("user_enabled:%d", userId), enabled, time.Duration(UserId2StatusCacheSeconds)*time.Second)
if err != nil {
common.SysError("Redis set user enabled error: " + err.Error())
}
}
return enabled == "1"
return userEnabled, err
}
var group2model2channels map[string]map[string][]*Channel

View File

@ -152,6 +152,14 @@ func UpdateChannelStatusById(id int, status int) {
}
func UpdateChannelUsedQuota(id int, quota int) {
if common.BatchUpdateEnabled {
addNewRecord(BatchUpdateTypeChannelUsedQuota, id, quota)
return
}
updateChannelUsedQuota(id, quota)
}
func updateChannelUsedQuota(id int, quota int) {
err := DB.Model(&Channel{}).Where("id = ?", id).Update("used_quota", gorm.Expr("used_quota + ?", quota)).Error
if err != nil {
common.SysError("failed to update channel used quota: " + err.Error())

View File

@ -39,32 +39,35 @@ func ValidateUserToken(key string) (token *Token, err error) {
}
token, err = CacheGetTokenByKey(key)
if err == nil {
if token.Status == common.TokenStatusExhausted {
return nil, errors.New("该令牌额度已用尽")
} else if token.Status == common.TokenStatusExpired {
return nil, errors.New("该令牌已过期")
}
if token.Status != common.TokenStatusEnabled {
return nil, errors.New("该令牌状态不可用")
}
if token.ExpiredTime != -1 && token.ExpiredTime < common.GetTimestamp() {
if !common.RedisEnabled {
token.Status = common.TokenStatusExpired
err := token.SelectUpdate()
if err != nil {
common.SysError("failed to update token status" + err.Error())
}
}
return nil, errors.New("该令牌已过期")
}
if !token.UnlimitedQuota && token.RemainQuota <= 0 {
if !common.RedisEnabled {
// in this case, we can make sure the token is exhausted
token.Status = common.TokenStatusExhausted
err := token.SelectUpdate()
if err != nil {
common.SysError("failed to update token status" + err.Error())
}
}
return nil, errors.New("该令牌额度已用尽")
}
go func() {
token.AccessedTime = common.GetTimestamp()
err := token.SelectUpdate()
if err != nil {
common.SysError("failed to update token" + err.Error())
}
}()
return token, nil
}
return nil, errors.New("无效的令牌")
@ -131,10 +134,19 @@ func IncreaseTokenQuota(id int, quota int) (err error) {
if quota < 0 {
return errors.New("quota 不能为负数!")
}
if common.BatchUpdateEnabled {
addNewRecord(BatchUpdateTypeTokenQuota, id, quota)
return nil
}
return increaseTokenQuota(id, quota)
}
func increaseTokenQuota(id int, quota int) (err error) {
err = DB.Model(&Token{}).Where("id = ?", id).Updates(
map[string]interface{}{
"remain_quota": gorm.Expr("remain_quota + ?", quota),
"used_quota": gorm.Expr("used_quota - ?", quota),
"accessed_time": common.GetTimestamp(),
},
).Error
return err
@ -144,10 +156,19 @@ func DecreaseTokenQuota(id int, quota int) (err error) {
if quota < 0 {
return errors.New("quota 不能为负数!")
}
if common.BatchUpdateEnabled {
addNewRecord(BatchUpdateTypeTokenQuota, id, -quota)
return nil
}
return decreaseTokenQuota(id, quota)
}
func decreaseTokenQuota(id int, quota int) (err error) {
err = DB.Model(&Token{}).Where("id = ?", id).Updates(
map[string]interface{}{
"remain_quota": gorm.Expr("remain_quota - ?", quota),
"used_quota": gorm.Expr("used_quota + ?", quota),
"accessed_time": common.GetTimestamp(),
},
).Error
return err

View File

@ -253,17 +253,16 @@ func IsAdmin(userId int) bool {
return user.Role >= common.RoleAdminUser
}
func IsUserEnabled(userId int) bool {
func IsUserEnabled(userId int) (bool, error) {
if userId == 0 {
return false
return false, errors.New("user id is empty")
}
var user User
err := DB.Where("id = ?", userId).Select("status").Find(&user).Error
if err != nil {
common.SysError("no such user " + err.Error())
return false
return false, err
}
return user.Status == common.UserStatusEnabled
return user.Status == common.UserStatusEnabled, nil
}
func ValidateAccessToken(token string) (user *User) {
@ -308,6 +307,14 @@ func IncreaseUserQuota(id int, quota int) (err error) {
if quota < 0 {
return errors.New("quota 不能为负数!")
}
if common.BatchUpdateEnabled {
addNewRecord(BatchUpdateTypeUserQuota, id, quota)
return nil
}
return increaseUserQuota(id, quota)
}
func increaseUserQuota(id int, quota int) (err error) {
err = DB.Model(&User{}).Where("id = ?", id).Update("quota", gorm.Expr("quota + ?", quota)).Error
return err
}
@ -316,6 +323,14 @@ func DecreaseUserQuota(id int, quota int) (err error) {
if quota < 0 {
return errors.New("quota 不能为负数!")
}
if common.BatchUpdateEnabled {
addNewRecord(BatchUpdateTypeUserQuota, id, -quota)
return nil
}
return decreaseUserQuota(id, quota)
}
func decreaseUserQuota(id int, quota int) (err error) {
err = DB.Model(&User{}).Where("id = ?", id).Update("quota", gorm.Expr("quota - ?", quota)).Error
return err
}
@ -326,10 +341,18 @@ func GetRootUserEmail() (email string) {
}
func UpdateUserUsedQuotaAndRequestCount(id int, quota int) {
if common.BatchUpdateEnabled {
addNewRecord(BatchUpdateTypeUsedQuotaAndRequestCount, id, quota)
return
}
updateUserUsedQuotaAndRequestCount(id, quota, 1)
}
func updateUserUsedQuotaAndRequestCount(id int, quota int, count int) {
err := DB.Model(&User{}).Where("id = ?", id).Updates(
map[string]interface{}{
"used_quota": gorm.Expr("used_quota + ?", quota),
"request_count": gorm.Expr("request_count + ?", 1),
"request_count": gorm.Expr("request_count + ?", count),
},
).Error
if err != nil {

75
model/utils.go Normal file
View File

@ -0,0 +1,75 @@
package model
import (
"one-api/common"
"sync"
"time"
)
const BatchUpdateTypeCount = 4 // if you add a new type, you need to add a new map and a new lock
const (
BatchUpdateTypeUserQuota = iota
BatchUpdateTypeTokenQuota
BatchUpdateTypeUsedQuotaAndRequestCount
BatchUpdateTypeChannelUsedQuota
)
var batchUpdateStores []map[int]int
var batchUpdateLocks []sync.Mutex
func init() {
for i := 0; i < BatchUpdateTypeCount; i++ {
batchUpdateStores = append(batchUpdateStores, make(map[int]int))
batchUpdateLocks = append(batchUpdateLocks, sync.Mutex{})
}
}
func InitBatchUpdater() {
go func() {
for {
time.Sleep(time.Duration(common.BatchUpdateInterval) * time.Second)
batchUpdate()
}
}()
}
func addNewRecord(type_ int, id int, value int) {
batchUpdateLocks[type_].Lock()
defer batchUpdateLocks[type_].Unlock()
if _, ok := batchUpdateStores[type_][id]; !ok {
batchUpdateStores[type_][id] = value
} else {
batchUpdateStores[type_][id] += value
}
}
func batchUpdate() {
common.SysLog("batch update started")
for i := 0; i < BatchUpdateTypeCount; i++ {
batchUpdateLocks[i].Lock()
store := batchUpdateStores[i]
batchUpdateStores[i] = make(map[int]int)
batchUpdateLocks[i].Unlock()
for key, value := range store {
switch i {
case BatchUpdateTypeUserQuota:
err := increaseUserQuota(key, value)
if err != nil {
common.SysError("failed to batch update user quota: " + err.Error())
}
case BatchUpdateTypeTokenQuota:
err := increaseTokenQuota(key, value)
if err != nil {
common.SysError("failed to batch update token quota: " + err.Error())
}
case BatchUpdateTypeUsedQuotaAndRequestCount:
updateUserUsedQuotaAndRequestCount(key, value, 1) // TODO: count is incorrect
case BatchUpdateTypeChannelUsedQuota:
updateChannelUsedQuota(key, value)
}
}
}
common.SysLog("batch update finished")
}

View File

@ -9,6 +9,8 @@ export const CHANNEL_OPTIONS = [
{ key: 16, text: '智谱 ChatGLM', value: 16, color: 'violet' },
{ key: 19, text: '360 智脑', value: 19, color: 'blue' },
{ key: 8, text: '自定义渠道', value: 8, color: 'pink' },
{ key: 22, text: '知识库FastGPT', value: 22, color: 'blue' },
{ key: 21, text: '知识库AI Proxy', value: 21, color: 'purple' },
{ key: 20, text: '代理OpenRouter', value: 20, color: 'black' },
{ key: 2, text: '代理API2D', value: 2, color: 'blue' },
{ key: 5, text: '代理OpenAI-SB', value: 5, color: 'brown' },

View File

@ -10,6 +10,20 @@ const MODEL_MAPPING_EXAMPLE = {
'gpt-4-32k-0314': 'gpt-4-32k'
};
function type2secretPrompt(type) {
// inputs.type === 15 ? '按照如下格式输入APIKey|SecretKey' : (inputs.type === 18 ? '按照如下格式输入APPID|APISecret|APIKey' : '请输入渠道对应的鉴权密钥')
switch (type) {
case 15:
return '按照如下格式输入APIKey|SecretKey';
case 18:
return '按照如下格式输入APPID|APISecret|APIKey';
case 22:
return '按照如下格式输入APIKey-AppId例如fastgpt-0sp2gtvfdgyi4k30jwlgwf1i-64f335d84283f05518e9e041';
default:
return '请输入渠道对应的鉴权密钥';
}
}
const EditChannel = () => {
const params = useParams();
const navigate = useNavigate();
@ -55,7 +69,7 @@ const EditChannel = () => {
localModels = ['ERNIE-Bot', 'ERNIE-Bot-turbo', 'Embedding-V1'];
break;
case 17:
localModels = ['qwen-v1', 'qwen-plus-v1'];
localModels = ['qwen-v1', 'qwen-plus-v1', 'text-embedding-v1'];
break;
case 16:
localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
@ -203,6 +217,24 @@ const EditChannel = () => {
}
};
const addCustomModel = () => {
if (customModel.trim() === '') return;
if (inputs.models.includes(customModel)) return;
let localModels = [...inputs.models];
localModels.push(customModel);
let localModelOptions = [];
localModelOptions.push({
key: customModel,
text: customModel,
value: customModel
});
setModelOptions(modelOptions => {
return [...modelOptions, ...localModelOptions];
});
setCustomModel('');
handleInputChange(null, { name: 'models', value: localModels });
};
return (
<>
<Segment loading={loading}>
@ -305,6 +337,20 @@ const EditChannel = () => {
</Form.Field>
)
}
{
inputs.type === 21 && (
<Form.Field>
<Form.Input
label='知识库 ID'
name='other'
placeholder={'请输入知识库 ID例如123456'}
onChange={handleInputChange}
value={inputs.other}
autoComplete='new-password'
/>
</Form.Field>
)
}
<Form.Field>
<Form.Dropdown
label='模型'
@ -332,29 +378,19 @@ const EditChannel = () => {
}}>清除所有模型</Button>
<Input
action={
<Button type={'button'} onClick={() => {
if (customModel.trim() === '') return;
if (inputs.models.includes(customModel)) return;
let localModels = [...inputs.models];
localModels.push(customModel);
let localModelOptions = [];
localModelOptions.push({
key: customModel,
text: customModel,
value: customModel
});
setModelOptions(modelOptions => {
return [...modelOptions, ...localModelOptions];
});
setCustomModel('');
handleInputChange(null, { name: 'models', value: localModels });
}}>填入</Button>
<Button type={'button'} onClick={addCustomModel}>填入</Button>
}
placeholder='输入自定义模型名称'
value={customModel}
onChange={(e, { value }) => {
setCustomModel(value);
}}
onKeyDown={(e) => {
if (e.key === 'Enter') {
addCustomModel();
e.preventDefault();
}
}}
/>
</div>
<Form.Field>
@ -405,7 +441,7 @@ const EditChannel = () => {
label='密钥'
name='key'
required
placeholder={inputs.type === 15 ? '按照如下格式输入APIKey|SecretKey' : (inputs.type === 18 ? '按照如下格式输入APPID|APISecret|APIKey' : '请输入渠道对应的鉴权密钥')}
placeholder={type2secretPrompt(inputs.type)}
onChange={handleInputChange}
value={inputs.key}
autoComplete='new-password'
@ -423,7 +459,7 @@ const EditChannel = () => {
)
}
{
inputs.type !== 3 && inputs.type !== 8 && (
inputs.type !== 3 && inputs.type !== 8 && inputs.type !== 22 && (
<Form.Field>
<Form.Input
label='代理'
@ -436,6 +472,20 @@ const EditChannel = () => {
</Form.Field>
)
}
{
inputs.type === 22 && (
<Form.Field>
<Form.Input
label='私有部署地址'
name='base_url'
placeholder={'请输入私有部署地址格式为https://fastgpt.run/api/openapi'}
onChange={handleInputChange}
value={inputs.base_url}
autoComplete='new-password'
/>
</Form.Field>
)
}
<Button onClick={handleCancel}>取消</Button>
<Button type={isEdit ? 'button' : 'submit'} positive onClick={submit}>提交</Button>
</Form>