mirror of
https://github.com/songquanpeng/one-api.git
synced 2025-10-24 02:13:42 +08:00
Compare commits
4 Commits
v0.4.1
...
v0.4.2-alp
Author | SHA1 | Date | |
---|---|---|---|
|
9d0bec83df | ||
|
f97a9ce597 | ||
|
4339f45f74 | ||
|
e398e0756b |
11
README.md
11
README.md
@@ -68,16 +68,17 @@ _✨ All in one 的 OpenAI 接口,整合各种 API 访问方式,开箱即用
|
||||
7. 支持**通道管理**,批量创建通道。
|
||||
8. 支持**用户分组**以及**渠道分组**。
|
||||
9. 支持渠道**设置模型列表**。
|
||||
10. 支持发布公告,设置充值链接,设置新用户初始额度。
|
||||
11. 支持丰富的**自定义**设置,
|
||||
10. 支持**查看额度明细**。
|
||||
11. 支持发布公告,设置充值链接,设置新用户初始额度。
|
||||
12. 支持丰富的**自定义**设置,
|
||||
1. 支持自定义系统名称,logo 以及页脚。
|
||||
2. 支持自定义首页和关于页面,可以选择使用 HTML & Markdown 代码进行自定义,或者使用一个单独的网页通过 iframe 嵌入。
|
||||
12. 支持通过系统访问令牌访问管理 API。
|
||||
13. 支持用户管理,支持**多种用户登录注册方式**:
|
||||
13. 支持通过系统访问令牌访问管理 API。
|
||||
14. 支持用户管理,支持**多种用户登录注册方式**:
|
||||
+ 邮箱登录注册以及通过邮箱进行密码重置。
|
||||
+ [GitHub 开放授权](https://github.com/settings/applications/new)。
|
||||
+ 微信公众号授权(需要额外部署 [WeChat Server](https://github.com/songquanpeng/wechat-server))。
|
||||
14. 未来其他大模型开放 API 后,将第一时间支持,并将其封装成同样的 API 访问方式。
|
||||
15. 未来其他大模型开放 API 后,将第一时间支持,并将其封装成同样的 API 访问方式。
|
||||
|
||||
## 部署
|
||||
### 基于 Docker 进行部署
|
||||
|
@@ -26,8 +26,8 @@ var ModelRatio = map[string]float64{
|
||||
"ada": 10,
|
||||
"text-embedding-ada-002": 0.2,
|
||||
"text-search-ada-doc-001": 10,
|
||||
"text-moderation-stable": 10,
|
||||
"text-moderation-latest": 10,
|
||||
"text-moderation-stable": 0.1,
|
||||
"text-moderation-latest": 0.1,
|
||||
}
|
||||
|
||||
func ModelRatio2JSONString() string {
|
||||
|
@@ -59,7 +59,7 @@ func testChannel(channel *model.Channel, request *ChatRequest) error {
|
||||
return err
|
||||
}
|
||||
if response.Usage.CompletionTokens == 0 {
|
||||
return errors.New(fmt.Sprintf("type %s, code %s, message %s", response.Error.Type, response.Error.Code, response.Error.Message))
|
||||
return errors.New(fmt.Sprintf("type %s, code %v, message %s", response.Error.Type, response.Error.Code, response.Error.Message))
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
@@ -161,6 +161,24 @@ func init() {
|
||||
Root: "text-ada-001",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "text-moderation-latest",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "openai",
|
||||
Permission: permission,
|
||||
Root: "text-moderation-latest",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "text-moderation-stable",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "openai",
|
||||
Permission: permission,
|
||||
Root: "text-moderation-stable",
|
||||
Parent: nil,
|
||||
},
|
||||
}
|
||||
openAIModelsMap = make(map[string]OpenAIModels)
|
||||
for _, model := range openAIModels {
|
||||
|
@@ -24,6 +24,7 @@ const (
|
||||
RelayModeChatCompletions
|
||||
RelayModeCompletions
|
||||
RelayModeEmbeddings
|
||||
RelayModeModeration
|
||||
)
|
||||
|
||||
// https://platform.openai.com/docs/api-reference/chat
|
||||
@@ -37,6 +38,7 @@ type GeneralOpenAIRequest struct {
|
||||
Temperature float64 `json:"temperature"`
|
||||
TopP float64 `json:"top_p"`
|
||||
N int `json:"n"`
|
||||
Input string `json:"input"`
|
||||
}
|
||||
|
||||
type ChatRequest struct {
|
||||
@@ -63,7 +65,7 @@ type OpenAIError struct {
|
||||
Message string `json:"message"`
|
||||
Type string `json:"type"`
|
||||
Param string `json:"param"`
|
||||
Code string `json:"code"`
|
||||
Code any `json:"code"`
|
||||
}
|
||||
|
||||
type OpenAIErrorWithStatusCode struct {
|
||||
@@ -100,11 +102,13 @@ func Relay(c *gin.Context) {
|
||||
relayMode = RelayModeCompletions
|
||||
} else if strings.HasPrefix(c.Request.URL.Path, "/v1/embeddings") {
|
||||
relayMode = RelayModeEmbeddings
|
||||
} else if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
|
||||
relayMode = RelayModeModeration
|
||||
}
|
||||
err := relayHelper(c, relayMode)
|
||||
if err != nil {
|
||||
if err.StatusCode == http.StatusTooManyRequests {
|
||||
err.OpenAIError.Message = "负载已满,请稍后再试,或升级账户以提升服务质量。"
|
||||
err.OpenAIError.Message = "当前分组负载已饱和,请稍后再试,或升级账户以提升服务质量。"
|
||||
}
|
||||
c.JSON(err.StatusCode, gin.H{
|
||||
"error": err.OpenAIError,
|
||||
@@ -143,6 +147,9 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
|
||||
}
|
||||
}
|
||||
if relayMode == RelayModeModeration && textRequest.Model == "" {
|
||||
textRequest.Model = "text-moderation-latest"
|
||||
}
|
||||
baseURL := common.ChannelBaseURLs[channelType]
|
||||
requestURL := c.Request.URL.String()
|
||||
if channelType == common.ChannelTypeCustom {
|
||||
@@ -180,6 +187,8 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
promptTokens = countTokenMessages(textRequest.Messages, textRequest.Model)
|
||||
case RelayModeCompletions:
|
||||
promptTokens = countTokenText(textRequest.Prompt, textRequest.Model)
|
||||
case RelayModeModeration:
|
||||
promptTokens = countTokenText(textRequest.Input, textRequest.Model)
|
||||
}
|
||||
preConsumedTokens := common.PreConsumedQuota
|
||||
if textRequest.MaxTokens != 0 {
|
||||
@@ -239,6 +248,9 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
quota = textResponse.Usage.PromptTokens + textResponse.Usage.CompletionTokens*completionRatio
|
||||
}
|
||||
quota = int(float64(quota) * ratio)
|
||||
if ratio != 0 && quota <= 0 {
|
||||
quota = 1
|
||||
}
|
||||
quotaDelta := quota - preConsumedQuota
|
||||
err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
|
||||
if err != nil {
|
||||
|
@@ -7,6 +7,7 @@ import (
|
||||
"one-api/common"
|
||||
"one-api/model"
|
||||
"strconv"
|
||||
"strings"
|
||||
)
|
||||
|
||||
type ModelRequest struct {
|
||||
@@ -64,6 +65,11 @@ func Distribute() func(c *gin.Context) {
|
||||
c.Abort()
|
||||
return
|
||||
}
|
||||
if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
|
||||
if modelRequest.Model == "" {
|
||||
modelRequest.Model = "text-moderation-stable"
|
||||
}
|
||||
}
|
||||
userId := c.GetInt("id")
|
||||
userGroup, _ := model.GetUserGroup(userId)
|
||||
channel, err = model.GetRandomSatisfiedChannel(userGroup, modelRequest.Model)
|
||||
|
@@ -37,6 +37,6 @@ func SetRelayRouter(router *gin.Engine) {
|
||||
relayV1Router.POST("/fine-tunes/:id/cancel", controller.RelayNotImplemented)
|
||||
relayV1Router.GET("/fine-tunes/:id/events", controller.RelayNotImplemented)
|
||||
relayV1Router.DELETE("/models/:model", controller.RelayNotImplemented)
|
||||
relayV1Router.POST("/moderations", controller.RelayNotImplemented)
|
||||
relayV1Router.POST("/moderations", controller.Relay)
|
||||
}
|
||||
}
|
||||
|
Reference in New Issue
Block a user