feat: support zhipu's ChatGLM (close #289)

This commit is contained in:
JustSong
2023-07-23 11:51:44 +08:00
parent c87e05bfc2
commit 26c6719ea3
9 changed files with 403 additions and 49 deletions

View File

@@ -252,24 +252,6 @@ func init() {
Root: "code-davinci-edit-001",
Parent: nil,
},
{
Id: "ChatGLM",
Object: "model",
Created: 1677649963,
OwnedBy: "thudm",
Permission: permission,
Root: "ChatGLM",
Parent: nil,
},
{
Id: "ChatGLM2",
Object: "model",
Created: 1677649963,
OwnedBy: "thudm",
Permission: permission,
Root: "ChatGLM2",
Parent: nil,
},
{
Id: "claude-instant-1",
Object: "model",
@@ -315,6 +297,33 @@ func init() {
Root: "PaLM-2",
Parent: nil,
},
{
Id: "chatglm_pro",
Object: "model",
Created: 1677649963,
OwnedBy: "zhipu",
Permission: permission,
Root: "chatglm_pro",
Parent: nil,
},
{
Id: "chatglm_std",
Object: "model",
Created: 1677649963,
OwnedBy: "zhipu",
Permission: permission,
Root: "chatglm_std",
Parent: nil,
},
{
Id: "chatglm_lite",
Object: "model",
Created: 1677649963,
OwnedBy: "zhipu",
Permission: permission,
Root: "chatglm_lite",
Parent: nil,
},
}
openAIModelsMap = make(map[string]OpenAIModels)
for _, model := range openAIModels {

View File

@@ -19,6 +19,7 @@ const (
APITypeClaude
APITypePaLM
APITypeBaidu
APITypeZhipu
)
func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
@@ -84,6 +85,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
apiType = APITypeBaidu
} else if strings.HasPrefix(textRequest.Model, "PaLM") {
apiType = APITypePaLM
} else if strings.HasPrefix(textRequest.Model, "chatglm_") {
apiType = APITypeZhipu
}
baseURL := common.ChannelBaseURLs[channelType]
requestURL := c.Request.URL.String()
@@ -134,6 +137,12 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
apiKey := c.Request.Header.Get("Authorization")
apiKey = strings.TrimPrefix(apiKey, "Bearer ")
fullRequestURL += "?key=" + apiKey
case APITypeZhipu:
method := "invoke"
if textRequest.Stream {
method = "sse-invoke"
}
fullRequestURL = fmt.Sprintf("https://open.bigmodel.cn/api/paas/v3/model-api/%s/%s", textRequest.Model, method)
}
var promptTokens int
var completionTokens int
@@ -200,6 +209,13 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
}
requestBody = bytes.NewBuffer(jsonStr)
case APITypeZhipu:
zhipuRequest := requestOpenAI2Zhipu(textRequest)
jsonStr, err := json.Marshal(zhipuRequest)
if err != nil {
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 {
@@ -221,6 +237,9 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
anthropicVersion = "2023-06-01"
}
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"))
@@ -252,11 +271,15 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
if strings.HasPrefix(textRequest.Model, "gpt-4") {
completionRatio = 2
}
if isStream && apiType != APITypeBaidu {
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
}
}
quota = promptTokens + int(float64(completionTokens)*completionRatio)
quota = int(float64(quota) * ratio)
@@ -302,7 +325,9 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
if err != nil {
return err
}
textResponse.Usage = *usage
if usage != nil {
textResponse.Usage = *usage
}
return nil
}
case APITypeClaude:
@@ -318,7 +343,9 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
if err != nil {
return err
}
textResponse.Usage = *usage
if usage != nil {
textResponse.Usage = *usage
}
return nil
}
case APITypeBaidu:
@@ -327,14 +354,18 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
if err != nil {
return err
}
textResponse.Usage = *usage
if usage != nil {
textResponse.Usage = *usage
}
return nil
} else {
err, usage := baiduHandler(c, resp)
if err != nil {
return err
}
textResponse.Usage = *usage
if usage != nil {
textResponse.Usage = *usage
}
return nil
}
case APITypePaLM:
@@ -350,7 +381,29 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
if err != nil {
return err
}
textResponse.Usage = *usage
if usage != nil {
textResponse.Usage = *usage
}
return nil
}
case APITypeZhipu:
if isStream {
err, usage := zhipuStreamHandler(c, resp)
if err != nil {
return err
}
if usage != nil {
textResponse.Usage = *usage
}
return nil
} else {
err, usage := zhipuHandler(c, resp)
if err != nil {
return err
}
if usage != nil {
textResponse.Usage = *usage
}
return nil
}
default:

290
controller/relay-zhipu.go Normal file
View File

@@ -0,0 +1,290 @@
package controller
import (
"bufio"
"encoding/json"
"github.com/gin-gonic/gin"
"github.com/golang-jwt/jwt"
"io"
"net/http"
"one-api/common"
"strings"
"sync"
"time"
)
// https://open.bigmodel.cn/doc/api#chatglm_std
// chatglm_std, chatglm_lite
// https://open.bigmodel.cn/api/paas/v3/model-api/chatglm_std/invoke
// https://open.bigmodel.cn/api/paas/v3/model-api/chatglm_std/sse-invoke
type ZhipuMessage struct {
Role string `json:"role"`
Content string `json:"content"`
}
type ZhipuRequest struct {
Prompt []ZhipuMessage `json:"prompt"`
Temperature float64 `json:"temperature,omitempty"`
TopP float64 `json:"top_p,omitempty"`
RequestId string `json:"request_id,omitempty"`
Incremental bool `json:"incremental,omitempty"`
}
type ZhipuResponseData struct {
TaskId string `json:"task_id"`
RequestId string `json:"request_id"`
TaskStatus string `json:"task_status"`
Choices []ZhipuMessage `json:"choices"`
Usage `json:"usage"`
}
type ZhipuResponse struct {
Code int `json:"code"`
Msg string `json:"msg"`
Success bool `json:"success"`
Data ZhipuResponseData `json:"data"`
}
type ZhipuStreamMetaResponse struct {
RequestId string `json:"request_id"`
TaskId string `json:"task_id"`
TaskStatus string `json:"task_status"`
Usage `json:"usage"`
}
type zhipuTokenData struct {
Token string
ExpiryTime time.Time
}
var zhipuTokens sync.Map
var expSeconds int64 = 24 * 3600
func getZhipuToken(apikey string) string {
data, ok := zhipuTokens.Load(apikey)
if ok {
tokenData := data.(zhipuTokenData)
if time.Now().Before(tokenData.ExpiryTime) {
return tokenData.Token
}
}
split := strings.Split(apikey, ".")
if len(split) != 2 {
common.SysError("invalid zhipu key: " + apikey)
return ""
}
id := split[0]
secret := split[1]
expMillis := time.Now().Add(time.Duration(expSeconds)*time.Second).UnixNano() / 1e6
expiryTime := time.Now().Add(time.Duration(expSeconds) * time.Second)
timestamp := time.Now().UnixNano() / 1e6
payload := jwt.MapClaims{
"api_key": id,
"exp": expMillis,
"timestamp": timestamp,
}
token := jwt.NewWithClaims(jwt.SigningMethodHS256, payload)
token.Header["alg"] = "HS256"
token.Header["sign_type"] = "SIGN"
tokenString, err := token.SignedString([]byte(secret))
if err != nil {
return ""
}
zhipuTokens.Store(apikey, zhipuTokenData{
Token: tokenString,
ExpiryTime: expiryTime,
})
return tokenString
}
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,
})
}
return &ZhipuRequest{
Prompt: messages,
Temperature: request.Temperature,
TopP: request.TopP,
Incremental: false,
}
}
func responseZhipu2OpenAI(response *ZhipuResponse) *OpenAITextResponse {
fullTextResponse := OpenAITextResponse{
Id: response.Data.TaskId,
Object: "chat.completion",
Created: common.GetTimestamp(),
Choices: make([]OpenAITextResponseChoice, 0, len(response.Data.Choices)),
Usage: response.Data.Usage,
}
for i, choice := range response.Data.Choices {
openaiChoice := OpenAITextResponseChoice{
Index: i,
Message: Message{
Role: choice.Role,
Content: strings.Trim(choice.Content, "\""),
},
FinishReason: "",
}
if i == len(response.Data.Choices)-1 {
openaiChoice.FinishReason = "stop"
}
fullTextResponse.Choices = append(fullTextResponse.Choices, openaiChoice)
}
return &fullTextResponse
}
func streamResponseZhipu2OpenAI(zhipuResponse string) *ChatCompletionsStreamResponse {
var choice ChatCompletionsStreamResponseChoice
choice.Delta.Content = zhipuResponse
choice.FinishReason = ""
response := ChatCompletionsStreamResponse{
Object: "chat.completion.chunk",
Created: common.GetTimestamp(),
Model: "chatglm",
Choices: []ChatCompletionsStreamResponseChoice{choice},
}
return &response
}
func streamMetaResponseZhipu2OpenAI(zhipuResponse *ZhipuStreamMetaResponse) (*ChatCompletionsStreamResponse, *Usage) {
var choice ChatCompletionsStreamResponseChoice
choice.Delta.Content = ""
choice.FinishReason = "stop"
response := ChatCompletionsStreamResponse{
Id: zhipuResponse.RequestId,
Object: "chat.completion.chunk",
Created: common.GetTimestamp(),
Model: "chatglm",
Choices: []ChatCompletionsStreamResponseChoice{choice},
}
return &response, &zhipuResponse.Usage
}
func zhipuStreamHandler(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)
metaChan := make(chan string)
stopChan := make(chan bool)
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:]
}
}
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 data := <-dataChan:
response := streamResponseZhipu2OpenAI(data)
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 data := <-metaChan:
var zhipuResponse ZhipuStreamMetaResponse
err := json.Unmarshal([]byte(data), &zhipuResponse)
if err != nil {
common.SysError("error unmarshalling stream response: " + err.Error())
return true
}
response, zhipuUsage := streamMetaResponseZhipu2OpenAI(&zhipuResponse)
jsonResponse, err := json.Marshal(response)
if err != nil {
common.SysError("error marshalling stream response: " + err.Error())
return true
}
usage = zhipuUsage
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 zhipuHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
var zhipuResponse ZhipuResponse
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, &zhipuResponse)
if err != nil {
return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
}
if !zhipuResponse.Success {
return &OpenAIErrorWithStatusCode{
OpenAIError: OpenAIError{
Message: zhipuResponse.Msg,
Type: "zhipu_error",
Param: "",
Code: zhipuResponse.Code,
},
StatusCode: resp.StatusCode,
}, nil
}
fullTextResponse := responseZhipu2OpenAI(&zhipuResponse)
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
}