mirror of
https://github.com/songquanpeng/one-api.git
synced 2025-10-23 01:43:42 +08:00
Compare commits
6 Commits
v0.4.3-alp
...
v0.4.3-alp
Author | SHA1 | Date | |
---|---|---|---|
|
38668e7331 | ||
|
323f3d263a | ||
|
0c34ed4c61 | ||
|
7c7eb6b7ec | ||
|
8b2ef666ef | ||
|
955d5f8707 |
@@ -117,6 +117,8 @@ sudo certbot --nginx
|
||||
sudo service nginx restart
|
||||
```
|
||||
|
||||
初始账号用户名为 `root`,密码为 `123456`。
|
||||
|
||||
### 手动部署
|
||||
1. 从 [GitHub Releases](https://github.com/songquanpeng/one-api/releases/latest) 下载可执行文件或者从源码编译:
|
||||
```shell
|
||||
|
@@ -17,6 +17,7 @@ func GroupRatio2JSONString() string {
|
||||
}
|
||||
|
||||
func UpdateGroupRatioByJSONString(jsonStr string) error {
|
||||
GroupRatio = make(map[string]float64)
|
||||
return json.Unmarshal([]byte(jsonStr), &GroupRatio)
|
||||
}
|
||||
|
||||
|
@@ -2,16 +2,23 @@ package common
|
||||
|
||||
import "encoding/json"
|
||||
|
||||
// ModelRatio
|
||||
// https://platform.openai.com/docs/models/model-endpoint-compatibility
|
||||
// https://openai.com/pricing
|
||||
// TODO: when a new api is enabled, check the pricing here
|
||||
// 1 === $0.002 / 1K tokens
|
||||
var ModelRatio = map[string]float64{
|
||||
"gpt-4": 15,
|
||||
"gpt-4-0314": 15,
|
||||
"gpt-4-0613": 15,
|
||||
"gpt-4-32k": 30,
|
||||
"gpt-4-32k-0314": 30,
|
||||
"gpt-3.5-turbo": 1, // $0.002 / 1K tokens
|
||||
"gpt-3.5-turbo-0301": 1,
|
||||
"gpt-4-32k-0613": 30,
|
||||
"gpt-3.5-turbo": 0.75, // $0.0015 / 1K tokens
|
||||
"gpt-3.5-turbo-0301": 0.75,
|
||||
"gpt-3.5-turbo-0613": 0.75,
|
||||
"gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens
|
||||
"gpt-3.5-turbo-16k-0613": 1.5,
|
||||
"text-ada-001": 0.2,
|
||||
"text-babbage-001": 0.25,
|
||||
"text-curie-001": 1,
|
||||
@@ -39,6 +46,7 @@ func ModelRatio2JSONString() string {
|
||||
}
|
||||
|
||||
func UpdateModelRatioByJSONString(jsonStr string) error {
|
||||
ModelRatio = make(map[string]float64)
|
||||
return json.Unmarshal([]byte(jsonStr), &ModelRatio)
|
||||
}
|
||||
|
||||
|
@@ -71,6 +71,33 @@ func init() {
|
||||
Root: "gpt-3.5-turbo-0301",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "gpt-3.5-turbo-0613",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "openai",
|
||||
Permission: permission,
|
||||
Root: "gpt-3.5-turbo-0613",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "gpt-3.5-turbo-16k",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "openai",
|
||||
Permission: permission,
|
||||
Root: "gpt-3.5-turbo-16k",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "gpt-3.5-turbo-16k-0613",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "openai",
|
||||
Permission: permission,
|
||||
Root: "gpt-3.5-turbo-16k-0613",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "gpt-4",
|
||||
Object: "model",
|
||||
@@ -89,6 +116,15 @@ func init() {
|
||||
Root: "gpt-4-0314",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "gpt-4-0613",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "openai",
|
||||
Permission: permission,
|
||||
Root: "gpt-4-0613",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "gpt-4-32k",
|
||||
Object: "model",
|
||||
@@ -107,6 +143,15 @@ func init() {
|
||||
Root: "gpt-4-32k-0314",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "gpt-4-32k-0613",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "openai",
|
||||
Permission: permission,
|
||||
Root: "gpt-4-32k-0613",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "text-embedding-ada-002",
|
||||
Object: "model",
|
||||
|
@@ -58,6 +58,20 @@ func countTokenMessages(messages []Message, model string) int {
|
||||
return tokenNum
|
||||
}
|
||||
|
||||
func countTokenInput(input any, model string) int {
|
||||
switch input.(type) {
|
||||
case string:
|
||||
return countTokenText(input.(string), model)
|
||||
case []string:
|
||||
text := ""
|
||||
for _, s := range input.([]string) {
|
||||
text += s
|
||||
}
|
||||
return countTokenText(text, model)
|
||||
}
|
||||
return 0
|
||||
}
|
||||
|
||||
func countTokenText(text string, model string) int {
|
||||
tokenEncoder := getTokenEncoder(model)
|
||||
token := tokenEncoder.Encode(text, nil, nil)
|
||||
|
@@ -38,7 +38,7 @@ type GeneralOpenAIRequest struct {
|
||||
Temperature float64 `json:"temperature"`
|
||||
TopP float64 `json:"top_p"`
|
||||
N int `json:"n"`
|
||||
Input string `json:"input"`
|
||||
Input any `json:"input"`
|
||||
}
|
||||
|
||||
type ChatRequest struct {
|
||||
@@ -189,7 +189,7 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
case RelayModeCompletions:
|
||||
promptTokens = countTokenText(textRequest.Prompt, textRequest.Model)
|
||||
case RelayModeModeration:
|
||||
promptTokens = countTokenText(textRequest.Input, textRequest.Model)
|
||||
promptTokens = countTokenInput(textRequest.Input, textRequest.Model)
|
||||
}
|
||||
preConsumedTokens := common.PreConsumedQuota
|
||||
if textRequest.MaxTokens != 0 {
|
||||
@@ -239,16 +239,15 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
defer func() {
|
||||
if consumeQuota {
|
||||
quota := 0
|
||||
usingGPT4 := strings.HasPrefix(textRequest.Model, "gpt-4")
|
||||
completionRatio := 1
|
||||
if usingGPT4 {
|
||||
completionRatio := 1.34 // default for gpt-3
|
||||
if strings.HasPrefix(textRequest.Model, "gpt-4") {
|
||||
completionRatio = 2
|
||||
}
|
||||
if isStream {
|
||||
responseTokens := countTokenText(streamResponseText, textRequest.Model)
|
||||
quota = promptTokens + responseTokens*completionRatio
|
||||
quota = promptTokens + int(float64(responseTokens)*completionRatio)
|
||||
} else {
|
||||
quota = textResponse.Usage.PromptTokens + textResponse.Usage.CompletionTokens*completionRatio
|
||||
quota = textResponse.Usage.PromptTokens + int(float64(textResponse.Usage.CompletionTokens)*completionRatio)
|
||||
}
|
||||
quota = int(float64(quota) * ratio)
|
||||
if ratio != 0 && quota <= 0 {
|
||||
@@ -260,7 +259,7 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
common.SysError("Error consuming token remain quota: " + err.Error())
|
||||
}
|
||||
userId := c.GetInt("id")
|
||||
model.RecordLog(userId, model.LogTypeConsume, fmt.Sprintf("使用模型 %s 消耗 %d 点额度(模型倍率 %.2f,分组倍率 %.2f)", textRequest.Model, quota, modelRatio, groupRatio))
|
||||
model.RecordLog(userId, model.LogTypeConsume, fmt.Sprintf("使用模型 %s 消耗 %d 点额度(模型倍率 %.2f,分组倍率 %.2f,补全倍率 %.2f)", textRequest.Model, quota, modelRatio, groupRatio, completionRatio))
|
||||
}
|
||||
}()
|
||||
|
||||
|
@@ -29,7 +29,7 @@ function renderType(type) {
|
||||
|
||||
function renderBalance(type, balance) {
|
||||
if (type === 5) {
|
||||
return <span>{balance.toFixed(2)}</span>
|
||||
return <span>¥{(balance / 10000).toFixed(2)}</span>
|
||||
}
|
||||
return <span>${balance.toFixed(2)}</span>
|
||||
}
|
||||
|
Reference in New Issue
Block a user