oadmin/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into main

Browse Source
This commit is contained in:
kuwork
2025-02-04 22:52:37 +08:00
committed by GitHub
parent 7588c42b42 a0fe527047
commit 89d48a6618
42 changed files with 385 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
relay/channel/api_request.go
View File

@@ -39,7 +39,7 @@ func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
if err != nil {
return nil, fmt.Errorf("setup request header failed: %w", err)
}
resp, err := doRequest(c, req)
resp, err := doRequest(c, req, info)
if err != nil {
return nil, fmt.Errorf("do request failed: %w", err)
}
@@ -62,7 +62,7 @@ func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBod
if err != nil {
return nil, fmt.Errorf("setup request header failed: %w", err)
}
resp, err := doRequest(c, req)
resp, err := doRequest(c, req, info)
if err != nil {
return nil, fmt.Errorf("do request failed: %w", err)
}
@@ -90,8 +90,18 @@ func DoWssRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
return targetConn, nil
}
func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
resp, err := service.GetHttpClient().Do(req)
func doRequest(c *gin.Context, req *http.Request, info *common.RelayInfo) (*http.Response, error) {
var client *http.Client
var err error
if proxyURL, ok := info.ChannelSetting["proxy"]; ok {
client, err = service.NewProxyHttpClient(proxyURL.(string))
if err != nil {
return nil, fmt.Errorf("new proxy http client failed: %w", err)
}
} else {
client = service.GetHttpClient()
}
resp, err := client.Do(req)
if err != nil {
return nil, err
}
@@ -120,7 +130,7 @@ func DoTaskApiRequest(a TaskAdaptor, c *gin.Context, info *common.TaskRelayInfo,
if err != nil {
return nil, fmt.Errorf("setup request header failed: %w", err)
}
resp, err := doRequest(c, req)
resp, err := doRequest(c, req, info.ToRelayInfo())
if err != nil {
return nil, fmt.Errorf("do request failed: %w", err)
}

2
relay/channel/aws/dto.go
View File

@@ -10,7 +10,7 @@ type AwsClaudeRequest struct {
System string `json:"system,omitempty"`
Messages []claude.ClaudeMessage `json:"messages"`
MaxTokens uint `json:"max_tokens,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
TopP float64 `json:"top_p,omitempty"`
TopK int `json:"top_k,omitempty"`
StopSequences []string `json:"stop_sequences,omitempty"`

2
relay/channel/baidu/dto.go
View File

@@ -12,7 +12,7 @@ type BaiduMessage struct {
type BaiduChatRequest struct {
Messages []BaiduMessage `json:"messages"`
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
TopP float64 `json:"top_p,omitempty"`
PenaltyScore float64 `json:"penalty_score,omitempty"`
Stream bool `json:"stream,omitempty"`

2
relay/channel/claude/dto.go
View File

@@ -50,7 +50,7 @@ type ClaudeRequest struct {
MaxTokens uint `json:"max_tokens,omitempty"`
MaxTokensToSample uint `json:"max_tokens_to_sample,omitempty"`
StopSequences []string `json:"stop_sequences,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
TopP float64 `json:"top_p,omitempty"`
TopK int `json:"top_k,omitempty"`
//ClaudeMetadata `json:"metadata,omitempty"`

2
relay/channel/cloudflare/dto.go
View File

@@ -9,7 +9,7 @@ type CfRequest struct {
Prompt string `json:"prompt,omitempty"`
Raw bool `json:"raw,omitempty"`
Stream bool `json:"stream,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
}
type CfAudioResponse struct {

2
relay/channel/gemini/dto.go
View File

@@ -71,7 +71,7 @@ type GeminiChatTool struct {
}
type GeminiChatGenerationConfig struct {
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
TopP float64 `json:"topP,omitempty"`
TopK float64 `json:"topK,omitempty"`
MaxOutputTokens uint `json:"maxOutputTokens,omitempty"`

18
relay/channel/ollama/dto.go
View File

@@ -6,7 +6,7 @@ type OllamaRequest struct {
Model string `json:"model,omitempty"`
Messages []dto.Message `json:"messages,omitempty"`
Stream bool `json:"stream,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
Seed float64 `json:"seed,omitempty"`
Topp float64 `json:"top_p,omitempty"`
TopK int `json:"top_k,omitempty"`
@@ -18,14 +18,14 @@ type OllamaRequest struct {
}
type Options struct {
Seed int `json:"seed,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
TopK int `json:"top_k,omitempty"`
TopP float64 `json:"top_p,omitempty"`
FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
PresencePenalty float64 `json:"presence_penalty,omitempty"`
NumPredict int `json:"num_predict,omitempty"`
NumCtx int `json:"num_ctx,omitempty"`
Seed int `json:"seed,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
TopK int `json:"top_k,omitempty"`
TopP float64 `json:"top_p,omitempty"`
FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
PresencePenalty float64 `json:"presence_penalty,omitempty"`
NumPredict int `json:"num_predict,omitempty"`
NumCtx int `json:"num_ctx,omitempty"`
}
type OllamaEmbeddingRequest struct {

28
relay/channel/openai/adaptor.go
View File

@@ -10,6 +10,7 @@ import (
"mime/multipart"
"net/http"
"one-api/common"
constant2 "one-api/constant"
"one-api/dto"
"one-api/relay/channel"
"one-api/relay/channel/ai360"
@@ -44,16 +45,20 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
}
switch info.ChannelType {
case common.ChannelTypeAzure:
apiVersion := info.ApiVersion
if apiVersion == "" {
apiVersion = constant2.AzureDefaultAPIVersion
}
// 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)
requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, apiVersion)
task := strings.TrimPrefix(requestURL, "/v1/")
model_ := info.UpstreamModelName
model_ = strings.Replace(model_, ".", "", -1)
// https://github.com/songquanpeng/one-api/issues/67
requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
if info.RelayMode == constant.RelayModeRealtime {
requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, info.ApiVersion)
requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, apiVersion)
}
return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
case common.ChannelTypeMiniMax:
@@ -109,13 +114,28 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
if info.ChannelType != common.ChannelTypeOpenAI && info.ChannelType != common.ChannelTypeAzure {
request.StreamOptions = nil
}
if strings.HasPrefix(request.Model, "o1") {
if strings.HasPrefix(request.Model, "o1") || strings.HasPrefix(request.Model, "o3") {
if request.MaxCompletionTokens == 0 && request.MaxTokens != 0 {
request.MaxCompletionTokens = request.MaxTokens
request.MaxTokens = 0
}
if strings.HasPrefix(request.Model, "o3") {
request.Temperature = nil
}
if strings.HasSuffix(request.Model, "-high") {
request.ReasoningEffort = "high"
request.Model = strings.TrimSuffix(request.Model, "-high")
} else if strings.HasSuffix(request.Model, "-low") {
request.ReasoningEffort = "low"
request.Model = strings.TrimSuffix(request.Model, "-low")
} else if strings.HasSuffix(request.Model, "-medium") {
request.ReasoningEffort = "medium"
request.Model = strings.TrimSuffix(request.Model, "-medium")
}
info.ReasoningEffort = request.ReasoningEffort
info.UpstreamModelName = request.Model
}
if request.Model == "o1" || request.Model == "o1-2024-12-17" {
if request.Model == "o1" || request.Model == "o1-2024-12-17" || strings.HasPrefix(request.Model, "o3") {
//修改第一个Message的内容，将system改为developer
if len(request.Messages) > 0 && request.Messages[0].Role == "system" {
request.Messages[0].Role = "developer"

4
relay/channel/openai/constant.go
View File

@@ -13,6 +13,10 @@ var ModelList = []string{
"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
"o1-preview", "o1-preview-2024-09-12",
"o1-mini", "o1-mini-2024-09-12",
"o3-mini", "o3-mini-2025-01-31",
"o3-mini-high", "o3-mini-2025-01-31-high",
"o3-mini-low", "o3-mini-2025-01-31-low",
"o3-mini-medium", "o3-mini-2025-01-31-medium",
"o1", "o1-2024-12-17",
"gpt-4o-audio-preview", "gpt-4o-audio-preview-2024-10-01",
"gpt-4o-realtime-preview", "gpt-4o-realtime-preview-2024-10-01", "gpt-4o-realtime-preview-2024-12-17",

2
relay/channel/palm/dto.go
View File

@@ -18,7 +18,7 @@ type PaLMPrompt struct {
type PaLMChatRequest struct {
Prompt PaLMPrompt `json:"prompt"`
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
CandidateCount int `json:"candidateCount,omitempty"`
TopP float64 `json:"topP,omitempty"`
TopK uint `json:"topK,omitempty"`

4
relay/channel/tencent/relay-tencent.go
View File

@@ -39,9 +39,7 @@ func requestOpenAI2Tencent(a *Adaptor, request dto.GeneralOpenAIRequest) *Tencen
if request.TopP != 0 {
req.TopP = &request.TopP
}
if request.Temperature != 0 {
req.Temperature = &request.Temperature
}
req.Temperature = request.Temperature
return &req
}

2
relay/channel/vertex/dto.go
View File

@@ -9,7 +9,7 @@ type VertexAIClaudeRequest struct {
MaxTokens int `json:"max_tokens,omitempty"`
StopSequences []string `json:"stop_sequences,omitempty"`
Stream bool `json:"stream,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
TopP float64 `json:"top_p,omitempty"`
TopK int `json:"top_k,omitempty"`
Tools []claude.Tool `json:"tools,omitempty"`

10
relay/channel/xunfei/dto.go
View File

@@ -13,11 +13,11 @@ type XunfeiChatRequest struct {
} `json:"header"`
Parameter struct {
Chat struct {
Domain string `json:"domain,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
TopK int `json:"top_k,omitempty"`
MaxTokens uint `json:"max_tokens,omitempty"`
Auditing bool `json:"auditing,omitempty"`
Domain string `json:"domain,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
TopK int `json:"top_k,omitempty"`
MaxTokens uint `json:"max_tokens,omitempty"`
Auditing bool `json:"auditing,omitempty"`
} `json:"chat"`
} `json:"parameter"`
Payload struct {

2
relay/channel/zhipu/dto.go
View File

@@ -12,7 +12,7 @@ type ZhipuMessage struct {
type ZhipuRequest struct {
Prompt []ZhipuMessage `json:"prompt"`
Temperature float64 `json:"temperature,omitempty"`
Temperature *float64 `json:"temperature,omitempty"`
TopP float64 `json:"top_p,omitempty"`
RequestId string `json:"request_id,omitempty"`
Incremental bool `json:"incremental,omitempty"`

3
relay/common/relay_info.go
View File

@@ -30,6 +30,7 @@ type RelayInfo struct {
RelayMode int
UpstreamModelName string
OriginModelName string
RecodeModelName string
RequestURLPath string
ApiVersion string
PromptTokens int
@@ -45,6 +46,7 @@ type RelayInfo struct {
RealtimeTools []dto.RealTimeTool
IsFirstRequest bool
AudioUsage bool
ReasoningEffort string
ChannelSetting map[string]interface{}
}
@@ -87,6 +89,7 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
FirstResponseTime: startTime.Add(-time.Second),
OriginModelName: c.GetString("original_model"),
UpstreamModelName: c.GetString("original_model"),
RecodeModelName: c.GetString("recode_model"),
ApiType: apiType,
ApiVersion: c.GetString("api_version"),
ApiKey: strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),

5
relay/relay-text.go
View File

@@ -93,6 +93,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
}
}
relayInfo.UpstreamModelName = textRequest.Model
relayInfo.RecodeModelName = textRequest.Model
modelPrice, getModelPriceSuccess := common.GetModelPrice(textRequest.Model, false)
groupRatio := setting.GetGroupRatio(relayInfo.Group)
@@ -218,10 +219,10 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
return openaiErr
}
if strings.HasPrefix(relayInfo.UpstreamModelName, "gpt-4o-audio") {
if strings.HasPrefix(relayInfo.RecodeModelName, "gpt-4o-audio") {
service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
} else {
postConsumeQuota(c, relayInfo, textRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
postConsumeQuota(c, relayInfo, relayInfo.RecodeModelName, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
}
return nil
}