feat: publish v1.0.0-rc.36-custom.1

relay/channel/tencent/adaptor.go

@@ -0,0 +1,118 @@
+package tencent
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/relay/channel"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/relaykit/dto"
+	"github.com/QuantumNous/new-api/relaykit/types"
+
+	"github.com/gin-gonic/gin"
+)
+
+type Adaptor struct {
+	Sign      string
+	AppID     int64
+	Action    string
+	Version   string
+	Timestamp int64
+}
+
+func (a *Adaptor) ConvertGeminiRequest(*gin.Context, *relaycommon.RelayInfo, *dto.GeminiChatRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertClaudeRequest(*gin.Context, *relaycommon.RelayInfo, *dto.ClaudeRequest) (any, error) {
+	//TODO implement me
+	panic("implement me")
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+	a.Action = "ChatCompletions"
+	a.Version = "2023-09-01"
+	a.Timestamp = common.GetTimestamp()
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/", info.ChannelBaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", a.Sign)
+	req.Set("X-TC-Action", a.Action)
+	req.Set("X-TC-Version", a.Version)
+	req.Set("X-TC-Timestamp", strconv.FormatInt(a.Timestamp, 10))
+	return nil
+}
+
+func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	apiKey := common.GetContextKeyString(c, constant.ContextKeyChannelKey)
+	apiKey = strings.TrimPrefix(apiKey, "Bearer ")
+	appId, secretId, secretKey, err := parseTencentConfig(apiKey)
+	a.AppID = appId
+	if err != nil {
+		return nil, err
+	}
+	tencentRequest := requestOpenAI2Tencent(a, *request)
+	// we have to calculate the sign here
+	a.Sign = getTencentSign(*tencentRequest, a, secretId, secretKey)
+	return tencentRequest, nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
+	if info.IsStream {
+		usage, err = tencentStreamHandler(c, info, resp)
+	} else {
+		usage, err = tencentHandler(c, info, resp)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/tencent/constants.go

@@ -0,0 +1,10 @@
+package tencent
+
+var ModelList = []string{
+	"hunyuan-lite",
+	"hunyuan-standard",
+	"hunyuan-standard-256K",
+	"hunyuan-pro",
+}
+
+var ChannelName = "tencent"

relay/channel/tencent/dispatch.go

@@ -0,0 +1,37 @@
+package tencent
+
+import (
+	"strings"
+
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/relay/channel"
+	"github.com/QuantumNous/new-api/relay/channel/openai"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+)
+
+const tokenHubBaseURL = "https://tokenhub.tencentmaas.com"
+
+// DispatchAdaptor 按密钥格式分流:三段式 ak/sk 走原生 TC3,单段 TokenHub key 走 OpenAI 兼容。
+type DispatchAdaptor struct {
+	channel.Adaptor
+}
+
+func (a *DispatchAdaptor) Init(info *relaycommon.RelayInfo) {
+	if strings.Contains(info.ApiKey, "|") {
+		a.Adaptor = &Adaptor{}
+	} else {
+		a.Adaptor = &openai.Adaptor{}
+		if info.ChannelBaseUrl == "" || info.ChannelBaseUrl == constant.ChannelBaseURLs[constant.ChannelTypeTencent] {
+			info.ChannelBaseUrl = tokenHubBaseURL
+		}
+	}
+	a.Adaptor.Init(info)
+}
+
+func (a *DispatchAdaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *DispatchAdaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/tencent/dispatch_test.go

@@ -0,0 +1,72 @@
+package tencent
+
+import (
+	"testing"
+
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/relay/channel/openai"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestDispatchAdaptorInit(t *testing.T) {
+	tests := []struct {
+		name        string
+		apiKey      string
+		baseURL     string
+		wantTC3     bool
+		wantBaseURL string
+	}{
+		{
+			name:        "legacy three-segment key selects TC3 adaptor and keeps base url",
+			apiKey:      "1300000000|AKIDxxxxxxxx|secretxxxxxxxx",
+			baseURL:     constant.ChannelBaseURLs[constant.ChannelTypeTencent],
+			wantTC3:     true,
+			wantBaseURL: constant.ChannelBaseURLs[constant.ChannelTypeTencent],
+		},
+		{
+			name:        "tokenhub key with default base url rewrites to tokenhub",
+			apiKey:      "sk-xxxxxxxxxxxxxxxx",
+			baseURL:     constant.ChannelBaseURLs[constant.ChannelTypeTencent],
+			wantTC3:     false,
+			wantBaseURL: tokenHubBaseURL,
+		},
+		{
+			name:        "tokenhub key with empty base url rewrites to tokenhub",
+			apiKey:      "sk-xxxxxxxxxxxxxxxx",
+			baseURL:     "",
+			wantTC3:     false,
+			wantBaseURL: tokenHubBaseURL,
+		},
+		{
+			name:        "tokenhub key with custom base url is preserved",
+			apiKey:      "sk-xxxxxxxxxxxxxxxx",
+			baseURL:     "https://proxy.example.com",
+			wantTC3:     false,
+			wantBaseURL: "https://proxy.example.com",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			info := &relaycommon.RelayInfo{ChannelMeta: &relaycommon.ChannelMeta{
+				ChannelType:    constant.ChannelTypeTencent,
+				ApiKey:         tt.apiKey,
+				ChannelBaseUrl: tt.baseURL,
+			}}
+
+			dispatch := &DispatchAdaptor{}
+			dispatch.Init(info)
+
+			require.NotNil(t, dispatch.Adaptor)
+			if tt.wantTC3 {
+				assert.IsType(t, &Adaptor{}, dispatch.Adaptor)
+			} else {
+				assert.IsType(t, &openai.Adaptor{}, dispatch.Adaptor)
+			}
+			assert.Equal(t, tt.wantBaseURL, info.ChannelBaseUrl)
+		})
+	}
+}

relay/channel/tencent/dto.go

@@ -0,0 +1,75 @@
+package tencent
+
+type TencentMessage struct {
+	Role    string `json:"Role"`
+	Content string `json:"Content"`
+}
+
+type TencentChatRequest struct {
+	// 模型名称，可选值包括 hunyuan-lite、hunyuan-standard、hunyuan-standard-256K、hunyuan-pro。
+	// 各模型介绍请阅读 [产品概述](https://cloud.tencent.com/document/product/1729/104753) 中的说明。
+	//
+	// 注意：
+	// 不同的模型计费不同，请根据 [购买指南](https://cloud.tencent.com/document/product/1729/97731) 按需调用。
+	Model *string `json:"Model"`
+	// 聊天上下文信息。
+	// 说明：
+	// 1. 长度最多为 40，按对话时间从旧到新在数组中排列。
+	// 2. Message.Role 可选值：system、user、assistant。
+	// 其中，system 角色可选，如存在则必须位于列表的最开始。user 和 assistant 需交替出现（一问一答），以 user 提问开始和结束，且 Content 不能为空。Role 的顺序示例：[system（可选） user assistant user assistant user ...]。
+	// 3. Messages 中 Content 总长度不能超过模型输入长度上限（可参考 [产品概述](https://cloud.tencent.com/document/product/1729/104753) 文档），超过则会截断最前面的内容，只保留尾部内容。
+	Messages []*TencentMessage `json:"Messages"`
+	// 流式调用开关。
+	// 说明：
+	// 1. 未传值时默认为非流式调用（false）。
+	// 2. 流式调用时以 SSE 协议增量返回结果（返回值取 Choices[n].Delta 中的值，需要拼接增量数据才能获得完整结果）。
+	// 3. 非流式调用时：
+	// 调用方式与普通 HTTP 请求无异。
+	// 接口响应耗时较长，**如需更低时延建议设置为 true**。
+	// 只返回一次最终结果（返回值取 Choices[n].Message 中的值）。
+	//
+	// 注意：
+	// 通过 SDK 调用时，流式和非流式调用需用**不同的方式**获取返回值，具体参考 SDK 中的注释或示例（在各语言 SDK 代码仓库的 examples/hunyuan/v20230901/ 目录中）。
+	Stream *bool `json:"Stream,omitempty"`
+	// 说明：
+	// 1. 影响输出文本的多样性，取值越大，生成文本的多样性越强。
+	// 2. 取值区间为 [0.0, 1.0]，未传值时使用各模型推荐值。
+	// 3. 非必要不建议使用，不合理的取值会影响效果。
+	TopP *float64 `json:"TopP,omitempty"`
+	// 说明：
+	// 1. 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定。
+	// 2. 取值区间为 [0.0, 2.0]，未传值时使用各模型推荐值。
+	// 3. 非必要不建议使用，不合理的取值会影响效果。
+	Temperature *float64 `json:"Temperature,omitempty"`
+}
+
+type TencentError struct {
+	Code    int    `json:"Code"`
+	Message string `json:"Message"`
+}
+
+type TencentUsage struct {
+	PromptTokens     int `json:"PromptTokens"`
+	CompletionTokens int `json:"CompletionTokens"`
+	TotalTokens      int `json:"TotalTokens"`
+}
+
+type TencentResponseChoices struct {
+	FinishReason string         `json:"FinishReason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
+	Messages     TencentMessage `json:"Message"`                // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
+	Delta        TencentMessage `json:"Delta"`                  // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
+}
+
+type TencentChatResponse struct {
+	Choices []TencentResponseChoices `json:"Choices,omitempty"` // 结果
+	Created int64                    `json:"Created,omitempty"` // unix 时间戳的字符串
+	Id      string                   `json:"Id,omitempty"`      // 会话 id
+	Usage   TencentUsage             `json:"Usage"`             // token 数量
+	Error   TencentError             `json:"Error"`             // 错误信息 注意：此字段可能返回 null，表示取不到有效值
+	Note    string                   `json:"Note,omitempty"`    // 注释
+	ReqID   string                   `json:"Req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
+}
+
+type TencentChatResponseSB struct {
+	Response TencentChatResponse `json:"Response"`
+}

relay/channel/tencent/relay-tencent.go

@@ -0,0 +1,234 @@
+package tencent
+
+import (
+	"bufio"
+	"crypto/hmac"
+	"crypto/sha256"
+	"encoding/hex"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/relay/helper"
+	"github.com/QuantumNous/new-api/relaykit/dto"
+	"github.com/QuantumNous/new-api/relaykit/types"
+	"github.com/QuantumNous/new-api/service"
+
+	"github.com/gin-gonic/gin"
+)
+
+// https://cloud.tencent.com/document/product/1729/97732
+
+func requestOpenAI2Tencent(a *Adaptor, request dto.GeneralOpenAIRequest) *TencentChatRequest {
+	messages := make([]*TencentMessage, 0, len(request.Messages))
+	for i := 0; i < len(request.Messages); i++ {
+		message := request.Messages[i]
+		messages = append(messages, &TencentMessage{
+			Content: message.StringContent(),
+			Role:    message.Role,
+		})
+	}
+	var req = TencentChatRequest{
+		Stream:   request.Stream,
+		Messages: messages,
+		Model:    &request.Model,
+	}
+	if request.TopP != nil {
+		req.TopP = request.TopP
+	}
+	req.Temperature = request.Temperature
+	return &req
+}
+
+func responseTencent2OpenAI(response *TencentChatResponse) *dto.OpenAITextResponse {
+	fullTextResponse := dto.OpenAITextResponse{
+		Id:      response.Id,
+		Object:  "chat.completion",
+		Created: common.GetTimestamp(),
+		Usage: dto.Usage{
+			PromptTokens:     response.Usage.PromptTokens,
+			CompletionTokens: response.Usage.CompletionTokens,
+			TotalTokens:      response.Usage.TotalTokens,
+		},
+	}
+	if len(response.Choices) > 0 {
+		choice := dto.OpenAITextResponseChoice{
+			Index: 0,
+			Message: dto.Message{
+				Role:    "assistant",
+				Content: response.Choices[0].Messages.Content,
+			},
+			FinishReason: response.Choices[0].FinishReason,
+		}
+		fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
+	}
+	return &fullTextResponse
+}
+
+func streamResponseTencent2OpenAI(TencentResponse *TencentChatResponse) *dto.ChatCompletionsStreamResponse {
+	response := dto.ChatCompletionsStreamResponse{
+		Object:  "chat.completion.chunk",
+		Created: common.GetTimestamp(),
+		Model:   "tencent-hunyuan",
+	}
+	if len(TencentResponse.Choices) > 0 {
+		var choice dto.ChatCompletionsStreamResponseChoice
+		choice.Delta.SetContentString(TencentResponse.Choices[0].Delta.Content)
+		if TencentResponse.Choices[0].FinishReason == "stop" {
+			choice.FinishReason = &constant.FinishReasonStop
+		}
+		response.Choices = append(response.Choices, choice)
+	}
+	return &response
+}
+
+func tencentStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
+	var responseText strings.Builder
+	scanner := helper.NewStreamScanner(resp.Body)
+	scanner.Split(bufio.ScanLines)
+
+	helper.SetEventStreamHeaders(c)
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || !strings.HasPrefix(data, "data:") {
+			continue
+		}
+		data = strings.TrimPrefix(data, "data:")
+
+		var tencentResponse TencentChatResponse
+		err := common.Unmarshal([]byte(data), &tencentResponse)
+		if err != nil {
+			common.SysLog("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+
+		response := streamResponseTencent2OpenAI(&tencentResponse)
+		if len(response.Choices) != 0 {
+			responseText.WriteString(response.Choices[0].Delta.GetContentString())
+		}
+
+		err = helper.ObjectData(c, response)
+		if err != nil {
+			common.SysLog(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		common.SysLog("error reading stream: " + err.Error())
+	}
+
+	helper.Done(c)
+
+	service.CloseResponseBodyGracefully(resp)
+
+	return service.ResponseText2Usage(c, responseText.String(), info.UpstreamModelName, info.GetEstimatePromptTokens()), nil
+}
+
+func tencentHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
+	var tencentSb TencentChatResponseSB
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return nil, types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError)
+	}
+	service.CloseResponseBodyGracefully(resp)
+	err = json.Unmarshal(responseBody, &tencentSb)
+	if err != nil {
+		return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+	}
+	if tencentSb.Response.Error.Code != 0 {
+		return nil, types.WithOpenAIError(types.OpenAIError{
+			Message: tencentSb.Response.Error.Message,
+			Code:    tencentSb.Response.Error.Code,
+		}, resp.StatusCode)
+	}
+	fullTextResponse := responseTencent2OpenAI(&tencentSb.Response)
+	jsonResponse, err := common.Marshal(fullTextResponse)
+	if err != nil {
+		return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	service.IOCopyBytesGracefully(c, resp, jsonResponse)
+	return &fullTextResponse.Usage, nil
+}
+
+func parseTencentConfig(config string) (appId int64, secretId string, secretKey string, err error) {
+	parts := strings.Split(config, "|")
+	if len(parts) != 3 {
+		err = errors.New("invalid tencent config")
+		return
+	}
+	appId, err = strconv.ParseInt(parts[0], 10, 64)
+	secretId = parts[1]
+	secretKey = parts[2]
+	return
+}
+
+func sha256hex(s string) string {
+	b := sha256.Sum256([]byte(s))
+	return hex.EncodeToString(b[:])
+}
+
+func hmacSha256(s, key string) string {
+	hashed := hmac.New(sha256.New, []byte(key))
+	hashed.Write([]byte(s))
+	return string(hashed.Sum(nil))
+}
+
+func getTencentSign(req TencentChatRequest, adaptor *Adaptor, secId, secKey string) string {
+	// build canonical request string
+	host := "hunyuan.tencentcloudapi.com"
+	httpRequestMethod := "POST"
+	canonicalURI := "/"
+	canonicalQueryString := ""
+	canonicalHeaders := fmt.Sprintf("content-type:%s\nhost:%s\nx-tc-action:%s\n",
+		"application/json", host, strings.ToLower(adaptor.Action))
+	signedHeaders := "content-type;host;x-tc-action"
+	payload, _ := json.Marshal(req)
+	hashedRequestPayload := sha256hex(string(payload))
+	canonicalRequest := fmt.Sprintf("%s\n%s\n%s\n%s\n%s\n%s",
+		httpRequestMethod,
+		canonicalURI,
+		canonicalQueryString,
+		canonicalHeaders,
+		signedHeaders,
+		hashedRequestPayload)
+	// build string to sign
+	algorithm := "TC3-HMAC-SHA256"
+	requestTimestamp := strconv.FormatInt(adaptor.Timestamp, 10)
+	timestamp, _ := strconv.ParseInt(requestTimestamp, 10, 64)
+	t := time.Unix(timestamp, 0).UTC()
+	// must be the format 2006-01-02, ref to package time for more info
+	date := t.Format("2006-01-02")
+	credentialScope := fmt.Sprintf("%s/%s/tc3_request", date, "hunyuan")
+	hashedCanonicalRequest := sha256hex(canonicalRequest)
+	string2sign := fmt.Sprintf("%s\n%s\n%s\n%s",
+		algorithm,
+		requestTimestamp,
+		credentialScope,
+		hashedCanonicalRequest)
+
+	// sign string
+	secretDate := hmacSha256(date, "TC3"+secKey)
+	secretService := hmacSha256("hunyuan", secretDate)
+	secretKey := hmacSha256("tc3_request", secretService)
+	signature := hex.EncodeToString([]byte(hmacSha256(string2sign, secretKey)))
+
+	// build authorization
+	authorization := fmt.Sprintf("%s Credential=%s/%s, SignedHeaders=%s, Signature=%s",
+		algorithm,
+		secId,
+		credentialScope,
+		signedHeaders,
+		signature)
+	return authorization
+}