Merge branch 'main' of https://github.com/songquanpeng/one-api

feat: support 360's models (close #331, close #461)

README.md

@@ -68,6 +68,7 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
    + [x] [阿里通义千问系列模型](https://help.aliyun.com/document_detail/2400395.html)
    + [x] [讯飞星火认知大模型](https://www.xfyun.cn/doc/spark/Web.html)
    + [x] [智谱 ChatGLM 系列模型](https://bigmodel.cn)
+   + [x] [360 智脑](https://ai.360.cn)
 2. 支持配置镜像以及众多第三方代理服务：
    + [x] [OpenAI-SB](https://openai-sb.com)
    + [x] [API2D](https://api2d.com/r/197971)

common/constants.go

@@ -173,6 +173,7 @@ const (
 	ChannelTypeZhipu     = 16
 	ChannelTypeAli       = 17
 	ChannelTypeXunfei    = 18
+	ChannelType360       = 19
 )
 
 var ChannelBaseURLs = []string{
@@ -195,4 +196,5 @@ var ChannelBaseURLs = []string{
 	"https://open.bigmodel.cn",       // 16
 	"https://dashscope.aliyuncs.com", // 17
 	"",                               // 18
+	"https://ai.360.cn",              // 19
 }

common/model-ratio.go

@@ -13,46 +13,51 @@ import (
 // 1 === $0.002 / 1K tokens
 // 1 === ￥0.014 / 1k tokens
 var ModelRatio = map[string]float64{
-	"gpt-4":                   15,
+	"gpt-4":                     15,
-	"gpt-4-0314":              15,
+	"gpt-4-0314":                15,
-	"gpt-4-0613":              15,
+	"gpt-4-0613":                15,
-	"gpt-4-32k":               30,
+	"gpt-4-32k":                 30,
-	"gpt-4-32k-0314":          30,
+	"gpt-4-32k-0314":            30,
-	"gpt-4-32k-0613":          30,
+	"gpt-4-32k-0613":            30,
-	"gpt-3.5-turbo":           0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo":             0.75, // $0.0015 / 1K tokens
-	"gpt-3.5-turbo-0301":      0.75,
+	"gpt-3.5-turbo-0301":        0.75,
-	"gpt-3.5-turbo-0613":      0.75,
+	"gpt-3.5-turbo-0613":        0.75,
-	"gpt-3.5-turbo-16k":       1.5, // $0.003 / 1K tokens
+	"gpt-3.5-turbo-16k":         1.5, // $0.003 / 1K tokens
-	"gpt-3.5-turbo-16k-0613":  1.5,
+	"gpt-3.5-turbo-16k-0613":    1.5,
-	"text-ada-001":            0.2,
+	"text-ada-001":              0.2,
-	"text-babbage-001":        0.25,
+	"text-babbage-001":          0.25,
-	"text-curie-001":          1,
+	"text-curie-001":            1,
-	"text-davinci-002":        10,
+	"text-davinci-002":          10,
-	"text-davinci-003":        10,
+	"text-davinci-003":          10,
-	"text-davinci-edit-001":   10,
+	"text-davinci-edit-001":     10,
-	"code-davinci-edit-001":   10,
+	"code-davinci-edit-001":     10,
-	"whisper-1":               10,
+	"whisper-1":                 10,
-	"davinci":                 10,
+	"davinci":                   10,
-	"curie":                   10,
+	"curie":                     10,
-	"babbage":                 10,
+	"babbage":                   10,
-	"ada":                     10,
+	"ada":                       10,
-	"text-embedding-ada-002":  0.05,
+	"text-embedding-ada-002":    0.05,
-	"text-search-ada-doc-001": 10,
+	"text-search-ada-doc-001":   10,
-	"text-moderation-stable":  0.1,
+	"text-moderation-stable":    0.1,
-	"text-moderation-latest":  0.1,
+	"text-moderation-latest":    0.1,
-	"dall-e":                  8,
+	"dall-e":                    8,
-	"claude-instant-1":        0.815,  // $1.63 / 1M tokens
+	"claude-instant-1":          0.815,  // $1.63 / 1M tokens
-	"claude-2":                5.51,   // $11.02 / 1M tokens
+	"claude-2":                  5.51,   // $11.02 / 1M tokens
-	"ERNIE-Bot":               0.8572, // ￥0.012 / 1k tokens
+	"ERNIE-Bot":                 0.8572, // ￥0.012 / 1k tokens
-	"ERNIE-Bot-turbo":         0.5715, // ￥0.008 / 1k tokens
+	"ERNIE-Bot-turbo":           0.5715, // ￥0.008 / 1k tokens
-	"Embedding-V1":            0.1429, // ￥0.002 / 1k tokens
+	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
-	"PaLM-2":                  1,
+	"PaLM-2":                    1,
-	"chatglm_pro":             0.7143, // ￥0.01 / 1k tokens
+	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
-	"chatglm_std":             0.3572, // ￥0.005 / 1k tokens
+	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
-	"chatglm_lite":            0.1429, // ￥0.002 / 1k tokens
+	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens
-	"qwen-v1":                 0.8572, // TBD: https://help.aliyun.com/document_detail/2399482.html?spm=a2c4g.2399482.0.0.1ad347feilAgag
+	"qwen-v1":                   0.8572, // TBD: https://help.aliyun.com/document_detail/2399482.html?spm=a2c4g.2399482.0.0.1ad347feilAgag
-	"qwen-plus-v1":            0.5715, // Same as above
+	"qwen-plus-v1":              0.5715, // Same as above
-	"SparkDesk":               0.8572, // TBD
+	"SparkDesk":                 0.8572, // TBD
+	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
+	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
+	"embedding_s1_v1":           0.0715, // ¥0.001 / 1k tokens
+	"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
+	"360GPT_S2_V9.4":            0.8572, // ¥0.012 / 1k tokens
 }
 
 func ModelRatio2JSONString() string {

controller/channel-test.go

@@ -24,6 +24,10 @@ func testChannel(channel *model.Channel, request ChatRequest) (error, *OpenAIErr
 		fallthrough
 	case common.ChannelTypeZhipu:
 		fallthrough
+	case common.ChannelTypeAli:
+		fallthrough
+	case common.ChannelType360:
+		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:
@@ -174,7 +178,7 @@ func testAllChannels(notify bool) error {
 				err = errors.New(fmt.Sprintf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0))
 				disableChannel(channel.Id, channel.Name, err.Error())
 			}
-			if shouldDisableChannel(openaiErr) {
+			if shouldDisableChannel(openaiErr, -1) {
 				disableChannel(channel.Id, channel.Name, err.Error())
 			}
 			channel.UpdateResponseTime(milliseconds)

controller/model.go

@@ -360,6 +360,51 @@ func init() {
 			Root:       "SparkDesk",
 			Parent:     nil,
 		},
+		{
+			Id:         "360GPT_S2_V9",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "360",
+			Permission: permission,
+			Root:       "360GPT_S2_V9",
+			Parent:     nil,
+		},
+		{
+			Id:         "embedding-bert-512-v1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "360",
+			Permission: permission,
+			Root:       "embedding-bert-512-v1",
+			Parent:     nil,
+		},
+		{
+			Id:         "embedding_s1_v1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "360",
+			Permission: permission,
+			Root:       "embedding_s1_v1",
+			Parent:     nil,
+		},
+		{
+			Id:         "semantic_similarity_s1_v1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "360",
+			Permission: permission,
+			Root:       "semantic_similarity_s1_v1",
+			Parent:     nil,
+		},
+		{
+			Id:         "360GPT_S2_V9.4",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "360",
+			Permission: permission,
+			Root:       "360GPT_S2_V9.4",
+			Parent:     nil,
+		},
 	}
 	openAIModelsMap = make(map[string]OpenAIModels)
 	for _, model := range openAIModels {

controller/relay-text.go

@@ -315,11 +315,10 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
 		}
 		isStream = isStream || strings.HasPrefix(resp.Header.Get("Content-Type"), "text/event-stream")
-	}
 
-	if resp.StatusCode != http.StatusOK {
+		if resp.StatusCode != http.StatusOK {
-		return errorWrapper(
+			return relayErrorHandler(resp)
-			fmt.Errorf("bad status code: %d", resp.StatusCode), "bad_status_code", resp.StatusCode)
+		}
 	}
 
 	var textResponse TextResponse

controller/relay-utils.go

@@ -1,16 +1,38 @@
 package controller
 
 import (
+	"encoding/json"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"github.com/pkoukk/tiktoken-go"
+	"io"
+	"net/http"
 	"one-api/common"
+	"strconv"
 )
 
 var stopFinishReason = "stop"
 
 var tokenEncoderMap = map[string]*tiktoken.Tiktoken{}
 
+func InitTokenEncoders() {
+	common.SysLog("initializing token encoders")
+	fallbackTokenEncoder, err := tiktoken.EncodingForModel("gpt-3.5-turbo")
+	if err != nil {
+		common.FatalLog(fmt.Sprintf("failed to get fallback token encoder: %s", err.Error()))
+	}
+	for model, _ := range common.ModelRatio {
+		tokenEncoder, err := tiktoken.EncodingForModel(model)
+		if err != nil {
+			common.SysError(fmt.Sprintf("using fallback encoder for model %s", model))
+			tokenEncoderMap[model] = fallbackTokenEncoder
+			continue
+		}
+		tokenEncoderMap[model] = tokenEncoder
+	}
+	common.SysLog("token encoders initialized")
+}
+
 func getTokenEncoder(model string) *tiktoken.Tiktoken {
 	if tokenEncoder, ok := tokenEncoderMap[model]; ok {
 		return tokenEncoder
@@ -95,13 +117,16 @@ func errorWrapper(err error, code string, statusCode int) *OpenAIErrorWithStatus
 	}
 }
 
-func shouldDisableChannel(err *OpenAIError) bool {
+func shouldDisableChannel(err *OpenAIError, statusCode int) bool {
 	if !common.AutomaticDisableChannelEnabled {
 		return false
 	}
 	if err == nil {
 		return false
 	}
+	if statusCode == http.StatusUnauthorized {
+		return true
+	}
 	if err.Type == "insufficient_quota" || err.Code == "invalid_api_key" || err.Code == "account_deactivated" {
 		return true
 	}
@@ -115,3 +140,30 @@ func setEventStreamHeaders(c *gin.Context) {
 	c.Writer.Header().Set("Transfer-Encoding", "chunked")
 	c.Writer.Header().Set("X-Accel-Buffering", "no")
 }
+
+func relayErrorHandler(resp *http.Response) (openAIErrorWithStatusCode *OpenAIErrorWithStatusCode) {
+	openAIErrorWithStatusCode = &OpenAIErrorWithStatusCode{
+		StatusCode: resp.StatusCode,
+		OpenAIError: OpenAIError{
+			Message: fmt.Sprintf("bad response status code %d", resp.StatusCode),
+			Type:    "one_api_error",
+			Code:    "bad_response_status_code",
+			Param:   strconv.Itoa(resp.StatusCode),
+		},
+	}
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return
+	}
+	var textResponse TextResponse
+	err = json.Unmarshal(responseBody, &textResponse)
+	if err != nil {
+		return
+	}
+	openAIErrorWithStatusCode.OpenAIError = textResponse.Error
+	return
+}

controller/relay.go

@@ -40,6 +40,7 @@ type GeneralOpenAIRequest struct {
 	Input       any       `json:"input,omitempty"`
 	Instruction string    `json:"instruction,omitempty"`
 	Size        string    `json:"size,omitempty"`
+	Functions   any       `json:"functions,omitempty"`
 }
 
 type ChatRequest struct {
@@ -185,7 +186,7 @@ func Relay(c *gin.Context) {
 		channelId := c.GetInt("channel_id")
 		common.SysError(fmt.Sprintf("relay error (channel #%d): %s", channelId, err.Message))
 		// https://platform.openai.com/docs/guides/error-codes/api-errors
-		if shouldDisableChannel(&err.OpenAIError) {
+		if shouldDisableChannel(&err.OpenAIError, err.StatusCode) {
 			channelId := c.GetInt("channel_id")
 			channelName := c.GetString("channel_name")
 			disableChannel(channelId, channelName, err.Message)

main.go

@@ -77,6 +77,7 @@ func main() {
 		}
 		go controller.AutomaticallyTestChannels(frequency)
 	}
+	controller.InitTokenEncoders()
 
 	// Initialize HTTP server
 	server := gin.Default()

web/src/constants/channel.constants.js

@@ -7,6 +7,7 @@ export const CHANNEL_OPTIONS = [
   { key: 17, text: '阿里通义千问', value: 17, color: 'orange' },
   { key: 18, text: '讯飞星火认知', value: 18, color: 'blue' },
   { key: 16, text: '智谱 ChatGLM', value: 16, color: 'violet' },
+  { key: 19, text: '360 智脑', value: 19, color: 'blue' },
   { key: 8, text: '自定义渠道', value: 8, color: 'pink' },
   { key: 2, text: '代理：API2D', value: 2, color: 'blue' },
   { key: 5, text: '代理：OpenAI-SB', value: 5, color: 'brown' },

web/src/pages/Channel/EditChannel.js

@@ -61,6 +61,9 @@ const EditChannel = () => {
         case 18:
           localModels = ['SparkDesk'];
           break;
+        case 19:
+          localModels = ['360GPT_S2_V9', 'embedding-bert-512-v1', 'embedding_s1_v1', 'semantic_similarity_s1_v1', '360GPT_S2_V9.4']
+          break;
       }
       setInputs((inputs) => ({ ...inputs, models: localModels }));
     }