mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-04-14 11:07:27 +00:00
Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
cb73889353 | ||
|
|
804aad3f37 | ||
|
|
3af62a3efa |
@@ -42,6 +42,10 @@ var defaultModelRatio = map[string]float64{
|
||||
"gpt-4o": 2.5, // $0.01 / 1K tokens
|
||||
"gpt-4o-2024-05-13": 2.5, // $0.01 / 1K tokens
|
||||
"gpt-4o-2024-08-06": 1.25, // $0.01 / 1K tokens
|
||||
"o1-preview": 7.5,
|
||||
"o1-preview-2024-09-12": 7.5,
|
||||
"o1-mini": 1.5,
|
||||
"o1-mini-2024-09-12": 1.5,
|
||||
"gpt-4o-mini": 0.075,
|
||||
"gpt-4o-mini-2024-07-18": 0.075,
|
||||
"gpt-4-turbo": 5, // $0.01 / 1K tokens
|
||||
@@ -331,17 +335,6 @@ func GetCompletionRatio(name string) float64 {
|
||||
if strings.HasPrefix(name, "gpt-4o-gizmo") {
|
||||
name = "gpt-4o-gizmo-*"
|
||||
}
|
||||
if strings.HasPrefix(name, "gpt-3.5") {
|
||||
if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
|
||||
// https://openai.com/blog/new-embedding-models-and-api-updates
|
||||
// Updated GPT-3.5 Turbo model and lower pricing
|
||||
return 3
|
||||
}
|
||||
if strings.HasSuffix(name, "1106") {
|
||||
return 2
|
||||
}
|
||||
return 4.0 / 3.0
|
||||
}
|
||||
if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
|
||||
if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") {
|
||||
return 3
|
||||
@@ -354,6 +347,9 @@ func GetCompletionRatio(name string) float64 {
|
||||
}
|
||||
return 2
|
||||
}
|
||||
if strings.HasPrefix(name, "o1-") {
|
||||
return 4
|
||||
}
|
||||
if name == "chatgpt-4o-latest" {
|
||||
return 3
|
||||
}
|
||||
@@ -364,6 +360,17 @@ func GetCompletionRatio(name string) float64 {
|
||||
} else if strings.Contains(name, "claude-3") {
|
||||
return 5
|
||||
}
|
||||
if strings.HasPrefix(name, "gpt-3.5") {
|
||||
if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
|
||||
// https://openai.com/blog/new-embedding-models-and-api-updates
|
||||
// Updated GPT-3.5 Turbo model and lower pricing
|
||||
return 3
|
||||
}
|
||||
if strings.HasSuffix(name, "1106") {
|
||||
return 2
|
||||
}
|
||||
return 4.0 / 3.0
|
||||
}
|
||||
if strings.HasPrefix(name, "mistral-") {
|
||||
return 3
|
||||
}
|
||||
|
||||
@@ -20,6 +20,7 @@ import (
|
||||
"one-api/relay/constant"
|
||||
"one-api/service"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
@@ -81,8 +82,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
|
||||
return fmt.Errorf("invalid api type: %d, adaptor is nil", apiType), nil
|
||||
}
|
||||
|
||||
request := buildTestRequest()
|
||||
request.Model = testModel
|
||||
request := buildTestRequest(testModel)
|
||||
meta.UpstreamModelName = testModel
|
||||
common.SysLog(fmt.Sprintf("testing channel %d with model %s", channel.Id, testModel))
|
||||
|
||||
@@ -141,17 +141,22 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func buildTestRequest() *dto.GeneralOpenAIRequest {
|
||||
func buildTestRequest(model string) *dto.GeneralOpenAIRequest {
|
||||
testRequest := &dto.GeneralOpenAIRequest{
|
||||
Model: "", // this will be set later
|
||||
MaxTokens: 1,
|
||||
Stream: false,
|
||||
Model: "", // this will be set later
|
||||
Stream: false,
|
||||
}
|
||||
if strings.HasPrefix(model, "o1-") {
|
||||
testRequest.MaxCompletionTokens = 1
|
||||
} else {
|
||||
testRequest.MaxTokens = 1
|
||||
}
|
||||
content, _ := json.Marshal("hi")
|
||||
testMessage := dto.Message{
|
||||
Role: "user",
|
||||
Content: content,
|
||||
}
|
||||
testRequest.Model = model
|
||||
testRequest.Messages = append(testRequest.Messages, testMessage)
|
||||
return testRequest
|
||||
}
|
||||
@@ -226,26 +231,22 @@ func testAllChannels(notify bool) error {
|
||||
tok := time.Now()
|
||||
milliseconds := tok.Sub(tik).Milliseconds()
|
||||
|
||||
ban := false
|
||||
if milliseconds > disableThreshold {
|
||||
err = errors.New(fmt.Sprintf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0))
|
||||
ban = true
|
||||
}
|
||||
shouldBanChannel := false
|
||||
|
||||
// request error disables the channel
|
||||
if openaiWithStatusErr != nil {
|
||||
oaiErr := openaiWithStatusErr.Error
|
||||
err = errors.New(fmt.Sprintf("type %s, httpCode %d, code %v, message %s", oaiErr.Type, openaiWithStatusErr.StatusCode, oaiErr.Code, oaiErr.Message))
|
||||
ban = service.ShouldDisableChannel(channel.Type, openaiWithStatusErr)
|
||||
shouldBanChannel = service.ShouldDisableChannel(channel.Type, openaiWithStatusErr)
|
||||
}
|
||||
|
||||
// parse *int to bool
|
||||
if !channel.GetAutoBan() {
|
||||
ban = false
|
||||
if milliseconds > disableThreshold {
|
||||
err = errors.New(fmt.Sprintf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0))
|
||||
shouldBanChannel = true
|
||||
}
|
||||
|
||||
// disable channel
|
||||
if ban && isChannelEnabled {
|
||||
if isChannelEnabled && shouldBanChannel && channel.GetAutoBan() {
|
||||
service.DisableChannel(channel.Id, channel.Name, err.Error())
|
||||
}
|
||||
|
||||
|
||||
@@ -7,31 +7,32 @@ type ResponseFormat struct {
|
||||
}
|
||||
|
||||
type GeneralOpenAIRequest struct {
|
||||
Model string `json:"model,omitempty"`
|
||||
Messages []Message `json:"messages,omitempty"`
|
||||
Prompt any `json:"prompt,omitempty"`
|
||||
Stream bool `json:"stream,omitempty"`
|
||||
StreamOptions *StreamOptions `json:"stream_options,omitempty"`
|
||||
MaxTokens uint `json:"max_tokens,omitempty"`
|
||||
Temperature float64 `json:"temperature,omitempty"`
|
||||
TopP float64 `json:"top_p,omitempty"`
|
||||
TopK int `json:"top_k,omitempty"`
|
||||
Stop any `json:"stop,omitempty"`
|
||||
N int `json:"n,omitempty"`
|
||||
Input any `json:"input,omitempty"`
|
||||
Instruction string `json:"instruction,omitempty"`
|
||||
Size string `json:"size,omitempty"`
|
||||
Functions any `json:"functions,omitempty"`
|
||||
FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
|
||||
PresencePenalty float64 `json:"presence_penalty,omitempty"`
|
||||
ResponseFormat any `json:"response_format,omitempty"`
|
||||
Seed float64 `json:"seed,omitempty"`
|
||||
Tools []ToolCall `json:"tools,omitempty"`
|
||||
ToolChoice any `json:"tool_choice,omitempty"`
|
||||
User string `json:"user,omitempty"`
|
||||
LogProbs bool `json:"logprobs,omitempty"`
|
||||
TopLogProbs int `json:"top_logprobs,omitempty"`
|
||||
Dimensions int `json:"dimensions,omitempty"`
|
||||
Model string `json:"model,omitempty"`
|
||||
Messages []Message `json:"messages,omitempty"`
|
||||
Prompt any `json:"prompt,omitempty"`
|
||||
Stream bool `json:"stream,omitempty"`
|
||||
StreamOptions *StreamOptions `json:"stream_options,omitempty"`
|
||||
MaxTokens uint `json:"max_tokens,omitempty"`
|
||||
MaxCompletionTokens uint `json:"max_completion_tokens,omitempty"`
|
||||
Temperature float64 `json:"temperature,omitempty"`
|
||||
TopP float64 `json:"top_p,omitempty"`
|
||||
TopK int `json:"top_k,omitempty"`
|
||||
Stop any `json:"stop,omitempty"`
|
||||
N int `json:"n,omitempty"`
|
||||
Input any `json:"input,omitempty"`
|
||||
Instruction string `json:"instruction,omitempty"`
|
||||
Size string `json:"size,omitempty"`
|
||||
Functions any `json:"functions,omitempty"`
|
||||
FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
|
||||
PresencePenalty float64 `json:"presence_penalty,omitempty"`
|
||||
ResponseFormat any `json:"response_format,omitempty"`
|
||||
Seed float64 `json:"seed,omitempty"`
|
||||
Tools []ToolCall `json:"tools,omitempty"`
|
||||
ToolChoice any `json:"tool_choice,omitempty"`
|
||||
User string `json:"user,omitempty"`
|
||||
LogProbs bool `json:"logprobs,omitempty"`
|
||||
TopLogProbs int `json:"top_logprobs,omitempty"`
|
||||
Dimensions int `json:"dimensions,omitempty"`
|
||||
}
|
||||
|
||||
type OpenAITools struct {
|
||||
|
||||
@@ -11,6 +11,8 @@ var ModelList = []string{
|
||||
"chatgpt-4o-latest",
|
||||
"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06",
|
||||
"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
|
||||
"o1-preview", "o1-preview-2024-09-12",
|
||||
"o1-mini", "o1-mini-2024-09-12",
|
||||
"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
|
||||
"text-curie-001", "text-babbage-001", "text-ada-001",
|
||||
"text-moderation-latest", "text-moderation-stable",
|
||||
|
||||
Reference in New Issue
Block a user