mirror of
https://github.com/songquanpeng/one-api.git
synced 2025-11-21 15:36:49 +08:00
Merge branch 'songquanpeng:main' into v1-models-response
This commit is contained in:
@@ -23,6 +23,8 @@ func testChannel(channel *model.Channel, request ChatRequest) (error, *OpenAIErr
|
||||
case common.ChannelTypeBaidu:
|
||||
fallthrough
|
||||
case common.ChannelTypeZhipu:
|
||||
fallthrough
|
||||
case common.ChannelTypeXunfei:
|
||||
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"
|
||||
|
||||
@@ -3,10 +3,12 @@ package controller
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"github.com/gin-gonic/gin"
|
||||
"net/http"
|
||||
"one-api/common"
|
||||
"one-api/model"
|
||||
"strings"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
)
|
||||
|
||||
func GetStatus(c *gin.Context) {
|
||||
@@ -78,6 +80,22 @@ func SendEmailVerification(c *gin.Context) {
|
||||
})
|
||||
return
|
||||
}
|
||||
if common.EmailDomainRestrictionEnabled {
|
||||
allowed := false
|
||||
for _, domain := range common.EmailDomainWhitelist {
|
||||
if strings.HasSuffix(email, "@"+domain) {
|
||||
allowed = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !allowed {
|
||||
c.JSON(http.StatusOK, gin.H{
|
||||
"success": false,
|
||||
"message": "管理员启用了邮箱域名白名单,您的邮箱地址的域名不在白名单中",
|
||||
})
|
||||
return
|
||||
}
|
||||
}
|
||||
if model.IsEmailAlreadyTaken(email) {
|
||||
c.JSON(http.StatusOK, gin.H{
|
||||
"success": false,
|
||||
|
||||
@@ -289,6 +289,15 @@ func init() {
|
||||
Root: "ERNIE-Bot-turbo",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "Embedding-V1",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "baidu",
|
||||
Permission: permission,
|
||||
Root: "Embedding-V1",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "PaLM-2",
|
||||
Object: "model",
|
||||
@@ -325,6 +334,33 @@ func init() {
|
||||
Root: "chatglm_lite",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "qwen-v1",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "ali",
|
||||
Permission: permission,
|
||||
Root: "qwen-v1",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "qwen-plus-v1",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "ali",
|
||||
Permission: permission,
|
||||
Root: "qwen-plus-v1",
|
||||
Parent: nil,
|
||||
},
|
||||
{
|
||||
Id: "SparkDesk",
|
||||
Object: "model",
|
||||
Created: 1677649963,
|
||||
OwnedBy: "xunfei",
|
||||
Permission: permission,
|
||||
Root: "SparkDesk",
|
||||
Parent: nil,
|
||||
},
|
||||
}
|
||||
openAIModelsMap = make(map[string]OpenAIModels)
|
||||
for _, model := range openAIModels {
|
||||
|
||||
@@ -2,11 +2,12 @@ package controller
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"github.com/gin-gonic/gin"
|
||||
"net/http"
|
||||
"one-api/common"
|
||||
"one-api/model"
|
||||
"strings"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
)
|
||||
|
||||
func GetOptions(c *gin.Context) {
|
||||
@@ -49,6 +50,14 @@ func UpdateOption(c *gin.Context) {
|
||||
})
|
||||
return
|
||||
}
|
||||
case "EmailDomainRestrictionEnabled":
|
||||
if option.Value == "true" && len(common.EmailDomainWhitelist) == 0 {
|
||||
c.JSON(http.StatusOK, gin.H{
|
||||
"success": false,
|
||||
"message": "无法启用邮箱域名限制,请先填入限制的邮箱域名!",
|
||||
})
|
||||
return
|
||||
}
|
||||
case "WeChatAuthEnabled":
|
||||
if option.Value == "true" && common.WeChatServerAddress == "" {
|
||||
c.JSON(http.StatusOK, gin.H{
|
||||
|
||||
240
controller/relay-ali.go
Normal file
240
controller/relay-ali.go
Normal file
@@ -0,0 +1,240 @@
|
||||
package controller
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"encoding/json"
|
||||
"github.com/gin-gonic/gin"
|
||||
"io"
|
||||
"net/http"
|
||||
"one-api/common"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// https://help.aliyun.com/document_detail/613695.html?spm=a2c4g.2399480.0.0.1adb778fAdzP9w#341800c0f8w0r
|
||||
|
||||
type AliMessage struct {
|
||||
User string `json:"user"`
|
||||
Bot string `json:"bot"`
|
||||
}
|
||||
|
||||
type AliInput struct {
|
||||
Prompt string `json:"prompt"`
|
||||
History []AliMessage `json:"history"`
|
||||
}
|
||||
|
||||
type AliParameters struct {
|
||||
TopP float64 `json:"top_p,omitempty"`
|
||||
TopK int `json:"top_k,omitempty"`
|
||||
Seed uint64 `json:"seed,omitempty"`
|
||||
EnableSearch bool `json:"enable_search,omitempty"`
|
||||
}
|
||||
|
||||
type AliChatRequest struct {
|
||||
Model string `json:"model"`
|
||||
Input AliInput `json:"input"`
|
||||
Parameters AliParameters `json:"parameters,omitempty"`
|
||||
}
|
||||
|
||||
type AliError struct {
|
||||
Code string `json:"code"`
|
||||
Message string `json:"message"`
|
||||
RequestId string `json:"request_id"`
|
||||
}
|
||||
|
||||
type AliUsage struct {
|
||||
InputTokens int `json:"input_tokens"`
|
||||
OutputTokens int `json:"output_tokens"`
|
||||
}
|
||||
|
||||
type AliOutput struct {
|
||||
Text string `json:"text"`
|
||||
FinishReason string `json:"finish_reason"`
|
||||
}
|
||||
|
||||
type AliChatResponse struct {
|
||||
Output AliOutput `json:"output"`
|
||||
Usage AliUsage `json:"usage"`
|
||||
AliError
|
||||
}
|
||||
|
||||
func requestOpenAI2Ali(request GeneralOpenAIRequest) *AliChatRequest {
|
||||
messages := make([]AliMessage, 0, len(request.Messages))
|
||||
prompt := ""
|
||||
for i := 0; i < len(request.Messages); i++ {
|
||||
message := request.Messages[i]
|
||||
if message.Role == "system" {
|
||||
messages = append(messages, AliMessage{
|
||||
User: message.Content,
|
||||
Bot: "Okay",
|
||||
})
|
||||
continue
|
||||
} else {
|
||||
if i == len(request.Messages)-1 {
|
||||
prompt = message.Content
|
||||
break
|
||||
}
|
||||
messages = append(messages, AliMessage{
|
||||
User: message.Content,
|
||||
Bot: request.Messages[i+1].Content,
|
||||
})
|
||||
i++
|
||||
}
|
||||
}
|
||||
return &AliChatRequest{
|
||||
Model: request.Model,
|
||||
Input: AliInput{
|
||||
Prompt: prompt,
|
||||
History: messages,
|
||||
},
|
||||
//Parameters: AliParameters{ // ChatGPT's parameters are not compatible with Ali's
|
||||
// TopP: request.TopP,
|
||||
// TopK: 50,
|
||||
// //Seed: 0,
|
||||
// //EnableSearch: false,
|
||||
//},
|
||||
}
|
||||
}
|
||||
|
||||
func responseAli2OpenAI(response *AliChatResponse) *OpenAITextResponse {
|
||||
choice := OpenAITextResponseChoice{
|
||||
Index: 0,
|
||||
Message: Message{
|
||||
Role: "assistant",
|
||||
Content: response.Output.Text,
|
||||
},
|
||||
FinishReason: response.Output.FinishReason,
|
||||
}
|
||||
fullTextResponse := OpenAITextResponse{
|
||||
Id: response.RequestId,
|
||||
Object: "chat.completion",
|
||||
Created: common.GetTimestamp(),
|
||||
Choices: []OpenAITextResponseChoice{choice},
|
||||
Usage: Usage{
|
||||
PromptTokens: response.Usage.InputTokens,
|
||||
CompletionTokens: response.Usage.OutputTokens,
|
||||
TotalTokens: response.Usage.InputTokens + response.Usage.OutputTokens,
|
||||
},
|
||||
}
|
||||
return &fullTextResponse
|
||||
}
|
||||
|
||||
func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *ChatCompletionsStreamResponse {
|
||||
var choice ChatCompletionsStreamResponseChoice
|
||||
choice.Delta.Content = aliResponse.Output.Text
|
||||
choice.FinishReason = aliResponse.Output.FinishReason
|
||||
response := ChatCompletionsStreamResponse{
|
||||
Id: aliResponse.RequestId,
|
||||
Object: "chat.completion.chunk",
|
||||
Created: common.GetTimestamp(),
|
||||
Model: "ernie-bot",
|
||||
Choices: []ChatCompletionsStreamResponseChoice{choice},
|
||||
}
|
||||
return &response
|
||||
}
|
||||
|
||||
func aliStreamHandler(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
|
||||
}()
|
||||
c.Writer.Header().Set("Content-Type", "text/event-stream")
|
||||
c.Writer.Header().Set("Cache-Control", "no-cache")
|
||||
c.Writer.Header().Set("Connection", "keep-alive")
|
||||
c.Writer.Header().Set("Transfer-Encoding", "chunked")
|
||||
c.Writer.Header().Set("X-Accel-Buffering", "no")
|
||||
lastResponseText := ""
|
||||
c.Stream(func(w io.Writer) bool {
|
||||
select {
|
||||
case data := <-dataChan:
|
||||
var aliResponse AliChatResponse
|
||||
err := json.Unmarshal([]byte(data), &aliResponse)
|
||||
if err != nil {
|
||||
common.SysError("error unmarshalling stream response: " + err.Error())
|
||||
return true
|
||||
}
|
||||
usage.PromptTokens += aliResponse.Usage.InputTokens
|
||||
usage.CompletionTokens += aliResponse.Usage.OutputTokens
|
||||
usage.TotalTokens += aliResponse.Usage.InputTokens + aliResponse.Usage.OutputTokens
|
||||
response := streamResponseAli2OpenAI(&aliResponse)
|
||||
response.Choices[0].Delta.Content = strings.TrimPrefix(response.Choices[0].Delta.Content, lastResponseText)
|
||||
lastResponseText = aliResponse.Output.Text
|
||||
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:
|
||||
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 aliHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
var aliResponse AliChatResponse
|
||||
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, &aliResponse)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "unmarshal_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 := responseAli2OpenAI(&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
|
||||
}
|
||||
@@ -54,13 +54,43 @@ type BaiduChatStreamResponse struct {
|
||||
IsEnd bool `json:"is_end"`
|
||||
}
|
||||
|
||||
type BaiduEmbeddingRequest struct {
|
||||
Input []string `json:"input"`
|
||||
}
|
||||
|
||||
type BaiduEmbeddingData struct {
|
||||
Object string `json:"object"`
|
||||
Embedding []float64 `json:"embedding"`
|
||||
Index int `json:"index"`
|
||||
}
|
||||
|
||||
type BaiduEmbeddingResponse struct {
|
||||
Id string `json:"id"`
|
||||
Object string `json:"object"`
|
||||
Created int64 `json:"created"`
|
||||
Data []BaiduEmbeddingData `json:"data"`
|
||||
Usage Usage `json:"usage"`
|
||||
BaiduError
|
||||
}
|
||||
|
||||
func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
|
||||
messages := make([]BaiduMessage, 0, len(request.Messages))
|
||||
for _, message := range request.Messages {
|
||||
messages = append(messages, BaiduMessage{
|
||||
Role: message.Role,
|
||||
Content: message.Content,
|
||||
})
|
||||
if message.Role == "system" {
|
||||
messages = append(messages, BaiduMessage{
|
||||
Role: "user",
|
||||
Content: message.Content,
|
||||
})
|
||||
messages = append(messages, BaiduMessage{
|
||||
Role: "assistant",
|
||||
Content: "Okay",
|
||||
})
|
||||
} else {
|
||||
messages = append(messages, BaiduMessage{
|
||||
Role: message.Role,
|
||||
Content: message.Content,
|
||||
})
|
||||
}
|
||||
}
|
||||
return &BaiduChatRequest{
|
||||
Messages: messages,
|
||||
@@ -101,6 +131,36 @@ func streamResponseBaidu2OpenAI(baiduResponse *BaiduChatStreamResponse) *ChatCom
|
||||
return &response
|
||||
}
|
||||
|
||||
func embeddingRequestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduEmbeddingRequest {
|
||||
baiduEmbeddingRequest := BaiduEmbeddingRequest{
|
||||
Input: nil,
|
||||
}
|
||||
switch request.Input.(type) {
|
||||
case string:
|
||||
baiduEmbeddingRequest.Input = []string{request.Input.(string)}
|
||||
case []string:
|
||||
baiduEmbeddingRequest.Input = request.Input.([]string)
|
||||
}
|
||||
return &baiduEmbeddingRequest
|
||||
}
|
||||
|
||||
func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *OpenAIEmbeddingResponse {
|
||||
openAIEmbeddingResponse := OpenAIEmbeddingResponse{
|
||||
Object: "list",
|
||||
Data: make([]OpenAIEmbeddingResponseItem, 0, len(response.Data)),
|
||||
Model: "baidu-embedding",
|
||||
Usage: response.Usage,
|
||||
}
|
||||
for _, item := range response.Data {
|
||||
openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, OpenAIEmbeddingResponseItem{
|
||||
Object: item.Object,
|
||||
Index: item.Index,
|
||||
Embedding: item.Embedding,
|
||||
})
|
||||
}
|
||||
return &openAIEmbeddingResponse
|
||||
}
|
||||
|
||||
func baiduStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
var usage Usage
|
||||
scanner := bufio.NewScanner(resp.Body)
|
||||
@@ -201,3 +261,39 @@ func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
|
||||
_, err = c.Writer.Write(jsonResponse)
|
||||
return nil, &fullTextResponse.Usage
|
||||
}
|
||||
|
||||
func baiduEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
var baiduResponse BaiduEmbeddingResponse
|
||||
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, &baiduResponse)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
if baiduResponse.ErrorMsg != "" {
|
||||
return &OpenAIErrorWithStatusCode{
|
||||
OpenAIError: OpenAIError{
|
||||
Message: baiduResponse.ErrorMsg,
|
||||
Type: "baidu_error",
|
||||
Param: "",
|
||||
Code: baiduResponse.ErrorCode,
|
||||
},
|
||||
StatusCode: resp.StatusCode,
|
||||
}, nil
|
||||
}
|
||||
fullTextResponse := embeddingResponseBaidu2OpenAI(&baiduResponse)
|
||||
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
|
||||
}
|
||||
|
||||
@@ -69,11 +69,11 @@ func requestOpenAI2Claude(textRequest GeneralOpenAIRequest) *ClaudeRequest {
|
||||
prompt += fmt.Sprintf("\n\nHuman: %s", message.Content)
|
||||
} else if message.Role == "assistant" {
|
||||
prompt += fmt.Sprintf("\n\nAssistant: %s", message.Content)
|
||||
} else {
|
||||
// ignore other roles
|
||||
} else if message.Role == "system" {
|
||||
prompt += fmt.Sprintf("\n\nSystem: %s", message.Content)
|
||||
}
|
||||
prompt += "\n\nAssistant:"
|
||||
}
|
||||
prompt += "\n\nAssistant:"
|
||||
claudeRequest.Prompt = prompt
|
||||
return &claudeRequest
|
||||
}
|
||||
|
||||
@@ -34,6 +34,9 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
|
||||
if len(data) < 6 { // ignore blank line or wrong format
|
||||
continue
|
||||
}
|
||||
if data[:6] != "data: " && data[:6] != "[DONE]" {
|
||||
continue
|
||||
}
|
||||
dataChan <- data
|
||||
data = data[6:]
|
||||
if !strings.HasPrefix(data, "[DONE]") {
|
||||
@@ -43,7 +46,7 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
|
||||
err := json.Unmarshal([]byte(data), &streamResponse)
|
||||
if err != nil {
|
||||
common.SysError("error unmarshalling stream response: " + err.Error())
|
||||
return
|
||||
continue // just ignore the error
|
||||
}
|
||||
for _, choice := range streamResponse.Choices {
|
||||
responseText += choice.Delta.Content
|
||||
@@ -53,7 +56,7 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
|
||||
err := json.Unmarshal([]byte(data), &streamResponse)
|
||||
if err != nil {
|
||||
common.SysError("error unmarshalling stream response: " + err.Error())
|
||||
return
|
||||
continue
|
||||
}
|
||||
for _, choice := range streamResponse.Choices {
|
||||
responseText += choice.Text
|
||||
@@ -89,7 +92,7 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
|
||||
return nil, responseText
|
||||
}
|
||||
|
||||
func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
var textResponse TextResponse
|
||||
if consumeQuota {
|
||||
responseBody, err := io.ReadAll(resp.Body)
|
||||
@@ -129,5 +132,17 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool) (*Ope
|
||||
if err != nil {
|
||||
return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
|
||||
if textResponse.Usage.TotalTokens == 0 {
|
||||
completionTokens := 0
|
||||
for _, choice := range textResponse.Choices {
|
||||
completionTokens += countTokenText(choice.Message.Content, model)
|
||||
}
|
||||
textResponse.Usage = Usage{
|
||||
PromptTokens: promptTokens,
|
||||
CompletionTokens: completionTokens,
|
||||
TotalTokens: promptTokens + completionTokens,
|
||||
}
|
||||
}
|
||||
return nil, &textResponse.Usage
|
||||
}
|
||||
|
||||
@@ -20,6 +20,8 @@ const (
|
||||
APITypePaLM
|
||||
APITypeBaidu
|
||||
APITypeZhipu
|
||||
APITypeAli
|
||||
APITypeXunfei
|
||||
)
|
||||
|
||||
var httpClient *http.Client
|
||||
@@ -73,7 +75,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
// map model name
|
||||
modelMapping := c.GetString("model_mapping")
|
||||
isModelMapped := false
|
||||
if modelMapping != "" {
|
||||
if modelMapping != "" && modelMapping != "{}" {
|
||||
modelMap := make(map[string]string)
|
||||
err := json.Unmarshal([]byte(modelMapping), &modelMap)
|
||||
if err != nil {
|
||||
@@ -94,6 +96,10 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
apiType = APITypePaLM
|
||||
case common.ChannelTypeZhipu:
|
||||
apiType = APITypeZhipu
|
||||
case common.ChannelTypeAli:
|
||||
apiType = APITypeAli
|
||||
case common.ChannelTypeXunfei:
|
||||
apiType = APITypeXunfei
|
||||
}
|
||||
baseURL := common.ChannelBaseURLs[channelType]
|
||||
requestURL := c.Request.URL.String()
|
||||
@@ -135,6 +141,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
|
||||
case "BLOOMZ-7B":
|
||||
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
|
||||
case "Embedding-V1":
|
||||
fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
|
||||
}
|
||||
apiKey := c.Request.Header.Get("Authorization")
|
||||
apiKey = strings.TrimPrefix(apiKey, "Bearer ")
|
||||
@@ -153,6 +161,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
method = "sse-invoke"
|
||||
}
|
||||
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"
|
||||
}
|
||||
var promptTokens int
|
||||
var completionTokens int
|
||||
@@ -206,12 +216,20 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
}
|
||||
requestBody = bytes.NewBuffer(jsonStr)
|
||||
case APITypeBaidu:
|
||||
baiduRequest := requestOpenAI2Baidu(textRequest)
|
||||
jsonStr, err := json.Marshal(baiduRequest)
|
||||
var jsonData []byte
|
||||
var err error
|
||||
switch relayMode {
|
||||
case RelayModeEmbeddings:
|
||||
baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(textRequest)
|
||||
jsonData, err = json.Marshal(baiduEmbeddingRequest)
|
||||
default:
|
||||
baiduRequest := requestOpenAI2Baidu(textRequest)
|
||||
jsonData, err = json.Marshal(baiduRequest)
|
||||
}
|
||||
if err != nil {
|
||||
return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
|
||||
}
|
||||
requestBody = bytes.NewBuffer(jsonStr)
|
||||
requestBody = bytes.NewBuffer(jsonData)
|
||||
case APITypePaLM:
|
||||
palmRequest := requestOpenAI2PaLM(textRequest)
|
||||
jsonStr, err := json.Marshal(palmRequest)
|
||||
@@ -226,49 +244,68 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
|
||||
}
|
||||
requestBody = bytes.NewBuffer(jsonStr)
|
||||
}
|
||||
req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "new_request_failed", http.StatusInternalServerError)
|
||||
}
|
||||
apiKey := c.Request.Header.Get("Authorization")
|
||||
apiKey = strings.TrimPrefix(apiKey, "Bearer ")
|
||||
switch apiType {
|
||||
case APITypeOpenAI:
|
||||
if channelType == common.ChannelTypeAzure {
|
||||
req.Header.Set("api-key", apiKey)
|
||||
} else {
|
||||
req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
|
||||
case APITypeAli:
|
||||
aliRequest := requestOpenAI2Ali(textRequest)
|
||||
jsonStr, err := json.Marshal(aliRequest)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
|
||||
}
|
||||
case APITypeClaude:
|
||||
req.Header.Set("x-api-key", apiKey)
|
||||
anthropicVersion := c.Request.Header.Get("anthropic-version")
|
||||
if anthropicVersion == "" {
|
||||
anthropicVersion = "2023-06-01"
|
||||
requestBody = bytes.NewBuffer(jsonStr)
|
||||
}
|
||||
|
||||
var req *http.Request
|
||||
var resp *http.Response
|
||||
isStream := textRequest.Stream
|
||||
|
||||
if apiType != APITypeXunfei { // cause xunfei use websocket
|
||||
req, err = http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "new_request_failed", http.StatusInternalServerError)
|
||||
}
|
||||
req.Header.Set("anthropic-version", anthropicVersion)
|
||||
case APITypeZhipu:
|
||||
token := getZhipuToken(apiKey)
|
||||
req.Header.Set("Authorization", token)
|
||||
}
|
||||
req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
|
||||
req.Header.Set("Accept", c.Request.Header.Get("Accept"))
|
||||
//req.Header.Set("Connection", c.Request.Header.Get("Connection"))
|
||||
resp, err := httpClient.Do(req)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "do_request_failed", http.StatusInternalServerError)
|
||||
}
|
||||
err = req.Body.Close()
|
||||
if err != nil {
|
||||
return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
|
||||
}
|
||||
err = c.Request.Body.Close()
|
||||
if err != nil {
|
||||
return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
|
||||
apiKey := c.Request.Header.Get("Authorization")
|
||||
apiKey = strings.TrimPrefix(apiKey, "Bearer ")
|
||||
switch apiType {
|
||||
case APITypeOpenAI:
|
||||
if channelType == common.ChannelTypeAzure {
|
||||
req.Header.Set("api-key", apiKey)
|
||||
} else {
|
||||
req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
|
||||
}
|
||||
case APITypeClaude:
|
||||
req.Header.Set("x-api-key", apiKey)
|
||||
anthropicVersion := c.Request.Header.Get("anthropic-version")
|
||||
if anthropicVersion == "" {
|
||||
anthropicVersion = "2023-06-01"
|
||||
}
|
||||
req.Header.Set("anthropic-version", anthropicVersion)
|
||||
case APITypeZhipu:
|
||||
token := getZhipuToken(apiKey)
|
||||
req.Header.Set("Authorization", token)
|
||||
case APITypeAli:
|
||||
req.Header.Set("Authorization", "Bearer "+apiKey)
|
||||
if textRequest.Stream {
|
||||
req.Header.Set("X-DashScope-SSE", "enable")
|
||||
}
|
||||
}
|
||||
req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
|
||||
req.Header.Set("Accept", c.Request.Header.Get("Accept"))
|
||||
//req.Header.Set("Connection", c.Request.Header.Get("Connection"))
|
||||
resp, err = httpClient.Do(req)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "do_request_failed", http.StatusInternalServerError)
|
||||
}
|
||||
err = req.Body.Close()
|
||||
if err != nil {
|
||||
return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
|
||||
}
|
||||
err = c.Request.Body.Close()
|
||||
if err != nil {
|
||||
return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
|
||||
}
|
||||
isStream = isStream || strings.HasPrefix(resp.Header.Get("Content-Type"), "text/event-stream")
|
||||
}
|
||||
|
||||
var textResponse TextResponse
|
||||
isStream := strings.HasPrefix(resp.Header.Get("Content-Type"), "text/event-stream")
|
||||
var streamResponseText string
|
||||
|
||||
defer func() {
|
||||
if consumeQuota {
|
||||
@@ -280,16 +317,10 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
if strings.HasPrefix(textRequest.Model, "gpt-4") {
|
||||
completionRatio = 2
|
||||
}
|
||||
if isStream && apiType != APITypeBaidu && apiType != APITypeZhipu {
|
||||
completionTokens = countTokenText(streamResponseText, textRequest.Model)
|
||||
} else {
|
||||
promptTokens = textResponse.Usage.PromptTokens
|
||||
completionTokens = textResponse.Usage.CompletionTokens
|
||||
if apiType == APITypeZhipu {
|
||||
// zhipu's API does not return prompt tokens & completion tokens
|
||||
promptTokens = textResponse.Usage.TotalTokens
|
||||
}
|
||||
}
|
||||
|
||||
promptTokens = textResponse.Usage.PromptTokens
|
||||
completionTokens = textResponse.Usage.CompletionTokens
|
||||
|
||||
quota = promptTokens + int(float64(completionTokens)*completionRatio)
|
||||
quota = int(float64(quota) * ratio)
|
||||
if ratio != 0 && quota <= 0 {
|
||||
@@ -327,10 +358,11 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
streamResponseText = responseText
|
||||
textResponse.Usage.PromptTokens = promptTokens
|
||||
textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
|
||||
return nil
|
||||
} else {
|
||||
err, usage := openaiHandler(c, resp, consumeQuota)
|
||||
err, usage := openaiHandler(c, resp, consumeQuota, promptTokens, textRequest.Model)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -345,7 +377,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
streamResponseText = responseText
|
||||
textResponse.Usage.PromptTokens = promptTokens
|
||||
textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
|
||||
return nil
|
||||
} else {
|
||||
err, usage := claudeHandler(c, resp, promptTokens, textRequest.Model)
|
||||
@@ -368,7 +401,14 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
}
|
||||
return nil
|
||||
} else {
|
||||
err, usage := baiduHandler(c, resp)
|
||||
var err *OpenAIErrorWithStatusCode
|
||||
var usage *Usage
|
||||
switch relayMode {
|
||||
case RelayModeEmbeddings:
|
||||
err, usage = baiduEmbeddingHandler(c, resp)
|
||||
default:
|
||||
err, usage = baiduHandler(c, resp)
|
||||
}
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -383,7 +423,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
streamResponseText = responseText
|
||||
textResponse.Usage.PromptTokens = promptTokens
|
||||
textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
|
||||
return nil
|
||||
} else {
|
||||
err, usage := palmHandler(c, resp, promptTokens, textRequest.Model)
|
||||
@@ -404,6 +445,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
if usage != nil {
|
||||
textResponse.Usage = *usage
|
||||
}
|
||||
// zhipu's API does not return prompt tokens & completion tokens
|
||||
textResponse.Usage.PromptTokens = textResponse.Usage.TotalTokens
|
||||
return nil
|
||||
} else {
|
||||
err, usage := zhipuHandler(c, resp)
|
||||
@@ -413,8 +456,49 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
|
||||
if usage != nil {
|
||||
textResponse.Usage = *usage
|
||||
}
|
||||
// zhipu's API does not return prompt tokens & completion tokens
|
||||
textResponse.Usage.PromptTokens = textResponse.Usage.TotalTokens
|
||||
return nil
|
||||
}
|
||||
case APITypeAli:
|
||||
if isStream {
|
||||
err, usage := aliStreamHandler(c, resp)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if usage != nil {
|
||||
textResponse.Usage = *usage
|
||||
}
|
||||
return nil
|
||||
} else {
|
||||
err, usage := aliHandler(c, resp)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if usage != nil {
|
||||
textResponse.Usage = *usage
|
||||
}
|
||||
return nil
|
||||
}
|
||||
case APITypeXunfei:
|
||||
if isStream {
|
||||
auth := c.Request.Header.Get("Authorization")
|
||||
auth = strings.TrimPrefix(auth, "Bearer ")
|
||||
splits := strings.Split(auth, "|")
|
||||
if len(splits) != 3 {
|
||||
return errorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)
|
||||
}
|
||||
err, usage := xunfeiStreamHandler(c, textRequest, splits[0], splits[1], splits[2])
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if usage != nil {
|
||||
textResponse.Usage = *usage
|
||||
}
|
||||
return nil
|
||||
} else {
|
||||
return errorWrapper(errors.New("xunfei api does not support non-stream mode"), "invalid_api_type", http.StatusBadRequest)
|
||||
}
|
||||
default:
|
||||
return errorWrapper(errors.New("unknown api type"), "unknown_api_type", http.StatusInternalServerError)
|
||||
}
|
||||
|
||||
278
controller/relay-xunfei.go
Normal file
278
controller/relay-xunfei.go
Normal file
@@ -0,0 +1,278 @@
|
||||
package controller
|
||||
|
||||
import (
|
||||
"crypto/hmac"
|
||||
"crypto/sha256"
|
||||
"encoding/base64"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"github.com/gin-gonic/gin"
|
||||
"github.com/gorilla/websocket"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"one-api/common"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
// https://console.xfyun.cn/services/cbm
|
||||
// https://www.xfyun.cn/doc/spark/Web.html
|
||||
|
||||
type XunfeiMessage struct {
|
||||
Role string `json:"role"`
|
||||
Content string `json:"content"`
|
||||
}
|
||||
|
||||
type XunfeiChatRequest struct {
|
||||
Header struct {
|
||||
AppId string `json:"app_id"`
|
||||
} `json:"header"`
|
||||
Parameter struct {
|
||||
Chat struct {
|
||||
Domain string `json:"domain,omitempty"`
|
||||
Temperature float64 `json:"temperature,omitempty"`
|
||||
TopK int `json:"top_k,omitempty"`
|
||||
MaxTokens int `json:"max_tokens,omitempty"`
|
||||
Auditing bool `json:"auditing,omitempty"`
|
||||
} `json:"chat"`
|
||||
} `json:"parameter"`
|
||||
Payload struct {
|
||||
Message struct {
|
||||
Text []XunfeiMessage `json:"text"`
|
||||
} `json:"message"`
|
||||
} `json:"payload"`
|
||||
}
|
||||
|
||||
type XunfeiChatResponseTextItem struct {
|
||||
Content string `json:"content"`
|
||||
Role string `json:"role"`
|
||||
Index int `json:"index"`
|
||||
}
|
||||
|
||||
type XunfeiChatResponse struct {
|
||||
Header struct {
|
||||
Code int `json:"code"`
|
||||
Message string `json:"message"`
|
||||
Sid string `json:"sid"`
|
||||
Status int `json:"status"`
|
||||
} `json:"header"`
|
||||
Payload struct {
|
||||
Choices struct {
|
||||
Status int `json:"status"`
|
||||
Seq int `json:"seq"`
|
||||
Text []XunfeiChatResponseTextItem `json:"text"`
|
||||
} `json:"choices"`
|
||||
Usage struct {
|
||||
//Text struct {
|
||||
// QuestionTokens string `json:"question_tokens"`
|
||||
// PromptTokens string `json:"prompt_tokens"`
|
||||
// CompletionTokens string `json:"completion_tokens"`
|
||||
// TotalTokens string `json:"total_tokens"`
|
||||
//} `json:"text"`
|
||||
Text Usage `json:"text"`
|
||||
} `json:"usage"`
|
||||
} `json:"payload"`
|
||||
}
|
||||
|
||||
func requestOpenAI2Xunfei(request GeneralOpenAIRequest, xunfeiAppId string) *XunfeiChatRequest {
|
||||
messages := make([]XunfeiMessage, 0, len(request.Messages))
|
||||
for _, message := range request.Messages {
|
||||
if message.Role == "system" {
|
||||
messages = append(messages, XunfeiMessage{
|
||||
Role: "user",
|
||||
Content: message.Content,
|
||||
})
|
||||
messages = append(messages, XunfeiMessage{
|
||||
Role: "assistant",
|
||||
Content: "Okay",
|
||||
})
|
||||
} else {
|
||||
messages = append(messages, XunfeiMessage{
|
||||
Role: message.Role,
|
||||
Content: message.Content,
|
||||
})
|
||||
}
|
||||
}
|
||||
xunfeiRequest := XunfeiChatRequest{}
|
||||
xunfeiRequest.Header.AppId = xunfeiAppId
|
||||
xunfeiRequest.Parameter.Chat.Domain = "general"
|
||||
xunfeiRequest.Parameter.Chat.Temperature = request.Temperature
|
||||
xunfeiRequest.Parameter.Chat.TopK = request.N
|
||||
xunfeiRequest.Parameter.Chat.MaxTokens = request.MaxTokens
|
||||
xunfeiRequest.Payload.Message.Text = messages
|
||||
return &xunfeiRequest
|
||||
}
|
||||
|
||||
func responseXunfei2OpenAI(response *XunfeiChatResponse) *OpenAITextResponse {
|
||||
if len(response.Payload.Choices.Text) == 0 {
|
||||
response.Payload.Choices.Text = []XunfeiChatResponseTextItem{
|
||||
{
|
||||
Content: "",
|
||||
},
|
||||
}
|
||||
}
|
||||
choice := OpenAITextResponseChoice{
|
||||
Index: 0,
|
||||
Message: Message{
|
||||
Role: "assistant",
|
||||
Content: response.Payload.Choices.Text[0].Content,
|
||||
},
|
||||
}
|
||||
fullTextResponse := OpenAITextResponse{
|
||||
Object: "chat.completion",
|
||||
Created: common.GetTimestamp(),
|
||||
Choices: []OpenAITextResponseChoice{choice},
|
||||
Usage: response.Payload.Usage.Text,
|
||||
}
|
||||
return &fullTextResponse
|
||||
}
|
||||
|
||||
func streamResponseXunfei2OpenAI(xunfeiResponse *XunfeiChatResponse) *ChatCompletionsStreamResponse {
|
||||
if len(xunfeiResponse.Payload.Choices.Text) == 0 {
|
||||
xunfeiResponse.Payload.Choices.Text = []XunfeiChatResponseTextItem{
|
||||
{
|
||||
Content: "",
|
||||
},
|
||||
}
|
||||
}
|
||||
var choice ChatCompletionsStreamResponseChoice
|
||||
choice.Delta.Content = xunfeiResponse.Payload.Choices.Text[0].Content
|
||||
response := ChatCompletionsStreamResponse{
|
||||
Object: "chat.completion.chunk",
|
||||
Created: common.GetTimestamp(),
|
||||
Model: "SparkDesk",
|
||||
Choices: []ChatCompletionsStreamResponseChoice{choice},
|
||||
}
|
||||
return &response
|
||||
}
|
||||
|
||||
func buildXunfeiAuthUrl(hostUrl string, apiKey, apiSecret string) string {
|
||||
HmacWithShaToBase64 := func(algorithm, data, key string) string {
|
||||
mac := hmac.New(sha256.New, []byte(key))
|
||||
mac.Write([]byte(data))
|
||||
encodeData := mac.Sum(nil)
|
||||
return base64.StdEncoding.EncodeToString(encodeData)
|
||||
}
|
||||
ul, err := url.Parse(hostUrl)
|
||||
if err != nil {
|
||||
fmt.Println(err)
|
||||
}
|
||||
date := time.Now().UTC().Format(time.RFC1123)
|
||||
signString := []string{"host: " + ul.Host, "date: " + date, "GET " + ul.Path + " HTTP/1.1"}
|
||||
sign := strings.Join(signString, "\n")
|
||||
sha := HmacWithShaToBase64("hmac-sha256", sign, apiSecret)
|
||||
authUrl := fmt.Sprintf("hmac username=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"", apiKey,
|
||||
"hmac-sha256", "host date request-line", sha)
|
||||
authorization := base64.StdEncoding.EncodeToString([]byte(authUrl))
|
||||
v := url.Values{}
|
||||
v.Add("host", ul.Host)
|
||||
v.Add("date", date)
|
||||
v.Add("authorization", authorization)
|
||||
callUrl := hostUrl + "?" + v.Encode()
|
||||
return callUrl
|
||||
}
|
||||
|
||||
func xunfeiStreamHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
var usage Usage
|
||||
d := websocket.Dialer{
|
||||
HandshakeTimeout: 5 * time.Second,
|
||||
}
|
||||
hostUrl := "wss://aichat.xf-yun.com/v1/chat"
|
||||
conn, resp, err := d.Dial(buildXunfeiAuthUrl(hostUrl, apiKey, apiSecret), nil)
|
||||
if err != nil || resp.StatusCode != 101 {
|
||||
return errorWrapper(err, "dial_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
data := requestOpenAI2Xunfei(textRequest, appId)
|
||||
err = conn.WriteJSON(data)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "write_json_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
dataChan := make(chan XunfeiChatResponse)
|
||||
stopChan := make(chan bool)
|
||||
go func() {
|
||||
for {
|
||||
_, msg, err := conn.ReadMessage()
|
||||
if err != nil {
|
||||
common.SysError("error reading stream response: " + err.Error())
|
||||
break
|
||||
}
|
||||
var response XunfeiChatResponse
|
||||
err = json.Unmarshal(msg, &response)
|
||||
if err != nil {
|
||||
common.SysError("error unmarshalling stream response: " + err.Error())
|
||||
break
|
||||
}
|
||||
dataChan <- response
|
||||
if response.Payload.Choices.Status == 2 {
|
||||
err := conn.Close()
|
||||
if err != nil {
|
||||
common.SysError("error closing websocket connection: " + err.Error())
|
||||
}
|
||||
break
|
||||
}
|
||||
}
|
||||
stopChan <- true
|
||||
}()
|
||||
c.Writer.Header().Set("Content-Type", "text/event-stream")
|
||||
c.Writer.Header().Set("Cache-Control", "no-cache")
|
||||
c.Writer.Header().Set("Connection", "keep-alive")
|
||||
c.Writer.Header().Set("Transfer-Encoding", "chunked")
|
||||
c.Writer.Header().Set("X-Accel-Buffering", "no")
|
||||
c.Stream(func(w io.Writer) bool {
|
||||
select {
|
||||
case xunfeiResponse := <-dataChan:
|
||||
usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
|
||||
usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
|
||||
usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
|
||||
response := streamResponseXunfei2OpenAI(&xunfeiResponse)
|
||||
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:
|
||||
c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
|
||||
return false
|
||||
}
|
||||
})
|
||||
return nil, &usage
|
||||
}
|
||||
|
||||
func xunfeiHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
var xunfeiResponse XunfeiChatResponse
|
||||
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, &xunfeiResponse)
|
||||
if err != nil {
|
||||
return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
if xunfeiResponse.Header.Code != 0 {
|
||||
return &OpenAIErrorWithStatusCode{
|
||||
OpenAIError: OpenAIError{
|
||||
Message: xunfeiResponse.Header.Message,
|
||||
Type: "xunfei_error",
|
||||
Param: "",
|
||||
Code: xunfeiResponse.Header.Code,
|
||||
},
|
||||
StatusCode: resp.StatusCode,
|
||||
}, nil
|
||||
}
|
||||
fullTextResponse := responseXunfei2OpenAI(&xunfeiResponse)
|
||||
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
|
||||
}
|
||||
@@ -111,10 +111,21 @@ func getZhipuToken(apikey string) string {
|
||||
func requestOpenAI2Zhipu(request GeneralOpenAIRequest) *ZhipuRequest {
|
||||
messages := make([]ZhipuMessage, 0, len(request.Messages))
|
||||
for _, message := range request.Messages {
|
||||
messages = append(messages, ZhipuMessage{
|
||||
Role: message.Role,
|
||||
Content: message.Content,
|
||||
})
|
||||
if message.Role == "system" {
|
||||
messages = append(messages, ZhipuMessage{
|
||||
Role: "system",
|
||||
Content: message.Content,
|
||||
})
|
||||
messages = append(messages, ZhipuMessage{
|
||||
Role: "user",
|
||||
Content: "Okay",
|
||||
})
|
||||
} else {
|
||||
messages = append(messages, ZhipuMessage{
|
||||
Role: message.Role,
|
||||
Content: message.Content,
|
||||
})
|
||||
}
|
||||
}
|
||||
return &ZhipuRequest{
|
||||
Prompt: messages,
|
||||
@@ -183,8 +194,8 @@ func zhipuStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSt
|
||||
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 i := strings.Index(string(data), "\n\n"); i >= 0 && strings.Index(string(data), ":") >= 0 {
|
||||
return i + 2, data[0:i], nil
|
||||
}
|
||||
if atEOF {
|
||||
return len(data), data, nil
|
||||
@@ -197,14 +208,19 @@ func zhipuStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSt
|
||||
go func() {
|
||||
for scanner.Scan() {
|
||||
data := scanner.Text()
|
||||
data = strings.Trim(data, "\"")
|
||||
if len(data) < 5 { // ignore blank line or wrong format
|
||||
continue
|
||||
}
|
||||
if data[:5] == "data:" {
|
||||
dataChan <- data[5:]
|
||||
} else if data[:5] == "meta:" {
|
||||
metaChan <- data[5:]
|
||||
lines := strings.Split(data, "\n")
|
||||
for i, line := range lines {
|
||||
if len(line) < 5 {
|
||||
continue
|
||||
}
|
||||
if line[:5] == "data:" {
|
||||
dataChan <- line[5:]
|
||||
if i != len(lines)-1 {
|
||||
dataChan <- "\n"
|
||||
}
|
||||
} else if line[:5] == "meta:" {
|
||||
metaChan <- line[5:]
|
||||
}
|
||||
}
|
||||
}
|
||||
stopChan <- true
|
||||
|
||||
@@ -81,8 +81,9 @@ type OpenAIErrorWithStatusCode struct {
|
||||
}
|
||||
|
||||
type TextResponse struct {
|
||||
Usage `json:"usage"`
|
||||
Error OpenAIError `json:"error"`
|
||||
Choices []OpenAITextResponseChoice `json:"choices"`
|
||||
Usage `json:"usage"`
|
||||
Error OpenAIError `json:"error"`
|
||||
}
|
||||
|
||||
type OpenAITextResponseChoice struct {
|
||||
@@ -99,6 +100,19 @@ type OpenAITextResponse struct {
|
||||
Usage `json:"usage"`
|
||||
}
|
||||
|
||||
type OpenAIEmbeddingResponseItem struct {
|
||||
Object string `json:"object"`
|
||||
Index int `json:"index"`
|
||||
Embedding []float64 `json:"embedding"`
|
||||
}
|
||||
|
||||
type OpenAIEmbeddingResponse struct {
|
||||
Object string `json:"object"`
|
||||
Data []OpenAIEmbeddingResponseItem `json:"data"`
|
||||
Model string `json:"model"`
|
||||
Usage `json:"usage"`
|
||||
}
|
||||
|
||||
type ImageResponse struct {
|
||||
Created int `json:"created"`
|
||||
Data []struct {
|
||||
|
||||
Reference in New Issue
Block a user