Merge branch 'songquanpeng' into sync_upstream

common/client.go

@@ -130,12 +130,53 @@ func SendRequest(req *http.Request, response any, outputResp bool) (*http.Respon
 	return nil, nil
 }
 
+type GeneralErrorResponse struct {
+	Error    types.OpenAIError `json:"error"`
+	Message  string            `json:"message"`
+	Msg      string            `json:"msg"`
+	Err      string            `json:"err"`
+	ErrorMsg string            `json:"error_msg"`
+	Header   struct {
+		Message string `json:"message"`
+	} `json:"header"`
+	Response struct {
+		Error struct {
+			Message string `json:"message"`
+		} `json:"error"`
+	} `json:"response"`
+}
+
+func (e GeneralErrorResponse) ToMessage() string {
+	if e.Error.Message != "" {
+		return e.Error.Message
+	}
+	if e.Message != "" {
+		return e.Message
+	}
+	if e.Msg != "" {
+		return e.Msg
+	}
+	if e.Err != "" {
+		return e.Err
+	}
+	if e.ErrorMsg != "" {
+		return e.ErrorMsg
+	}
+	if e.Header.Message != "" {
+		return e.Header.Message
+	}
+	if e.Response.Error.Message != "" {
+		return e.Response.Error.Message
+	}
+	return ""
+}
+
 // 处理错误响应
 func HandleErrorResp(resp *http.Response) (openAIErrorWithStatusCode *types.OpenAIErrorWithStatusCode) {
 	openAIErrorWithStatusCode = &types.OpenAIErrorWithStatusCode{
 		StatusCode: resp.StatusCode,
 		OpenAIError: types.OpenAIError{
-			Message: fmt.Sprintf("bad response status code %d", resp.StatusCode),
+			Message: "",
 			Type:    "upstream_error",
 			Code:    "bad_response_status_code",
 			Param:   strconv.Itoa(resp.StatusCode),
@@ -149,16 +190,23 @@ func HandleErrorResp(resp *http.Response) (openAIErrorWithStatusCode *types.Open
 	if err != nil {
 		return
 	}
-	var errorResponse types.OpenAIErrorResponse
+	// var errorResponse types.OpenAIErrorResponse
+	var errorResponse GeneralErrorResponse
 	err = json.Unmarshal(responseBody, &errorResponse)
 	if err != nil {
 		return
 	}
-	if errorResponse.Error.Type != "" {
+
+	if errorResponse.Error.Message != "" {
+		// OpenAI format error, so we override the default one
 		openAIErrorWithStatusCode.OpenAIError = errorResponse.Error
 	} else {
-		openAIErrorWithStatusCode.OpenAIError.Message = string(responseBody)
+		openAIErrorWithStatusCode.OpenAIError.Message = errorResponse.ToMessage()
 	}
+	if openAIErrorWithStatusCode.OpenAIError.Message == "" {
+		openAIErrorWithStatusCode.OpenAIError.Message = fmt.Sprintf("bad response status code %d", resp.StatusCode)
+	}
+
 	return
 }
 

common/constants.go

@@ -78,6 +78,7 @@ var QuotaForInviter = 0
 var QuotaForInvitee = 0
 var ChannelDisableThreshold = 5.0
 var AutomaticDisableChannelEnabled = false
+var AutomaticEnableChannelEnabled = false
 var QuotaRemindThreshold = 1000
 var PreConsumedQuota = 500
 var ApproximateTokenEnabled = false
@@ -187,6 +188,7 @@ const (
 	ChannelTypeFastGPT        = 22
 	ChannelTypeTencent        = 23
 	ChannelTypeAzureSpeech    = 24
+	ChannelTypeGemini         = 25
 )
 
 var ChannelBaseURLs = []string{
@@ -213,8 +215,9 @@ var ChannelBaseURLs = []string{
 	"https://openrouter.ai/api",         // 20
 	"https://api.aiproxy.io",            // 21
 	"https://fastgpt.run/api/openapi",   // 22
-	"https://hunyuan.cloud.tencent.com", // 23
-	"",                                  // 24
+	"https://hunyuan.cloud.tencent.com", //23
+	"",                                  //24
+	"",                                  //25
 }
 
 const (

common/database.go

@@ -4,3 +4,4 @@ var UsingSQLite = false
 var UsingPostgreSQL = false
 
 var SQLitePath = "one-api.db"
+var SQLiteBusyTimeout = GetOrDefault("SQLITE_BUSY_TIMEOUT", 3000)

common/email.go

@@ -1,11 +1,13 @@
 package common
 
 import (
+	"crypto/rand"
 	"crypto/tls"
 	"encoding/base64"
 	"fmt"
 	"net/smtp"
 	"strings"
+	"time"
 )
 
 func SendEmail(subject string, receiver string, content string) error {
@@ -13,15 +15,32 @@ func SendEmail(subject string, receiver string, content string) error {
 		SMTPFrom = SMTPAccount
 	}
 	encodedSubject := fmt.Sprintf("=?UTF-8?B?%s?=", base64.StdEncoding.EncodeToString([]byte(subject)))
+
+	// Extract domain from SMTPFrom
+	parts := strings.Split(SMTPFrom, "@")
+	var domain string
+	if len(parts) > 1 {
+		domain = parts[1]
+	}
+	// Generate a unique Message-ID
+	buf := make([]byte, 16)
+	_, err := rand.Read(buf)
+	if err != nil {
+		return err
+	}
+	messageId := fmt.Sprintf("<%x@%s>", buf, domain)
+
 	mail := []byte(fmt.Sprintf("To: %s\r\n"+
 		"From: %s<%s>\r\n"+
 		"Subject: %s\r\n"+
+		"Message-ID: %s\r\n"+ // add Message-ID header to avoid being treated as spam, RFC 5322
+		"Date: %s\r\n"+
 		"Content-Type: text/html; charset=UTF-8\r\n\r\n%s\r\n",
-		receiver, SystemName, SMTPFrom, encodedSubject, content))
+		receiver, SystemName, SMTPFrom, encodedSubject, messageId, time.Now().Format(time.RFC1123Z), content))
 	auth := smtp.PlainAuth("", SMTPAccount, SMTPToken, SMTPServer)
 	addr := fmt.Sprintf("%s:%d", SMTPServer, SMTPPort)
 	to := strings.Split(receiver, ";")
-	var err error
+
 	if SMTPPort == 465 {
 		tlsConfig := &tls.Config{
 			InsecureSkipVerify: true,

common/image/image.go

@@ -0,0 +1,47 @@
+package image
+
+import (
+	"image"
+	_ "image/gif"
+	_ "image/jpeg"
+	_ "image/png"
+	"net/http"
+	"regexp"
+	"strings"
+
+	_ "golang.org/x/image/webp"
+)
+
+func GetImageSizeFromUrl(url string) (width int, height int, err error) {
+	resp, err := http.Get(url)
+	if err != nil {
+		return
+	}
+	defer resp.Body.Close()
+	img, _, err := image.DecodeConfig(resp.Body)
+	if err != nil {
+		return
+	}
+	return img.Width, img.Height, nil
+}
+
+var (
+	reg = regexp.MustCompile(`data:image/([^;]+);base64,`)
+)
+
+func GetImageSizeFromBase64(encoded string) (width int, height int, err error) {
+	encoded = strings.TrimPrefix(encoded, "data:image/png;base64,")
+	base64 := strings.NewReader(reg.ReplaceAllString(encoded, ""))
+	img, _, err := image.DecodeConfig(base64)
+	if err != nil {
+		return
+	}
+	return img.Width, img.Height, nil
+}
+
+func GetImageSize(image string) (width int, height int, err error) {
+	if strings.HasPrefix(image, "data:image/") {
+		return GetImageSizeFromBase64(image)
+	}
+	return GetImageSizeFromUrl(image)
+}

common/image/image_test.go

@@ -0,0 +1,154 @@
+package image_test
+
+import (
+	"encoding/base64"
+	"image"
+	_ "image/gif"
+	_ "image/jpeg"
+	_ "image/png"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+	"testing"
+
+	img "one-api/common/image"
+
+	"github.com/stretchr/testify/assert"
+	_ "golang.org/x/image/webp"
+)
+
+type CountingReader struct {
+	reader    io.Reader
+	BytesRead int
+}
+
+func (r *CountingReader) Read(p []byte) (n int, err error) {
+	n, err = r.reader.Read(p)
+	r.BytesRead += n
+	return n, err
+}
+
+var (
+	cases = []struct {
+		url    string
+		format string
+		width  int
+		height int
+	}{
+		{"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", "jpeg", 2560, 1669},
+		{"https://upload.wikimedia.org/wikipedia/commons/9/97/Basshunter_live_performances.png", "png", 4500, 2592},
+		{"https://upload.wikimedia.org/wikipedia/commons/c/c6/TO_THE_ONE_SOMETHINGNESS.webp", "webp", 984, 985},
+		{"https://upload.wikimedia.org/wikipedia/commons/d/d0/01_Das_Sandberg-Modell.gif", "gif", 1917, 1533},
+		{"https://upload.wikimedia.org/wikipedia/commons/6/62/102Cervus.jpg", "jpeg", 270, 230},
+	}
+)
+
+func TestDecode(t *testing.T) {
+	// Bytes read: varies sometimes
+	// jpeg: 1063892
+	// png: 294462
+	// webp: 99529
+	// gif: 956153
+	// jpeg#01: 32805
+	for _, c := range cases {
+		t.Run("Decode:"+c.format, func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			reader := &CountingReader{reader: resp.Body}
+			img, format, err := image.Decode(reader)
+			assert.NoError(t, err)
+			size := img.Bounds().Size()
+			assert.Equal(t, c.format, format)
+			assert.Equal(t, c.width, size.X)
+			assert.Equal(t, c.height, size.Y)
+			t.Logf("Bytes read: %d", reader.BytesRead)
+		})
+	}
+
+	// Bytes read:
+	// jpeg: 4096
+	// png: 4096
+	// webp: 4096
+	// gif: 4096
+	// jpeg#01: 4096
+	for _, c := range cases {
+		t.Run("DecodeConfig:"+c.format, func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			reader := &CountingReader{reader: resp.Body}
+			config, format, err := image.DecodeConfig(reader)
+			assert.NoError(t, err)
+			assert.Equal(t, c.format, format)
+			assert.Equal(t, c.width, config.Width)
+			assert.Equal(t, c.height, config.Height)
+			t.Logf("Bytes read: %d", reader.BytesRead)
+		})
+	}
+}
+
+func TestBase64(t *testing.T) {
+	// Bytes read:
+	// jpeg: 1063892
+	// png: 294462
+	// webp: 99072
+	// gif: 953856
+	// jpeg#01: 32805
+	for _, c := range cases {
+		t.Run("Decode:"+c.format, func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			data, err := io.ReadAll(resp.Body)
+			assert.NoError(t, err)
+			encoded := base64.StdEncoding.EncodeToString(data)
+			body := base64.NewDecoder(base64.StdEncoding, strings.NewReader(encoded))
+			reader := &CountingReader{reader: body}
+			img, format, err := image.Decode(reader)
+			assert.NoError(t, err)
+			size := img.Bounds().Size()
+			assert.Equal(t, c.format, format)
+			assert.Equal(t, c.width, size.X)
+			assert.Equal(t, c.height, size.Y)
+			t.Logf("Bytes read: %d", reader.BytesRead)
+		})
+	}
+
+	// Bytes read:
+	// jpeg: 1536
+	// png: 768
+	// webp: 768
+	// gif: 1536
+	// jpeg#01: 3840
+	for _, c := range cases {
+		t.Run("DecodeConfig:"+c.format, func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			data, err := io.ReadAll(resp.Body)
+			assert.NoError(t, err)
+			encoded := base64.StdEncoding.EncodeToString(data)
+			body := base64.NewDecoder(base64.StdEncoding, strings.NewReader(encoded))
+			reader := &CountingReader{reader: body}
+			config, format, err := image.DecodeConfig(reader)
+			assert.NoError(t, err)
+			assert.Equal(t, c.format, format)
+			assert.Equal(t, c.width, config.Width)
+			assert.Equal(t, c.height, config.Height)
+			t.Logf("Bytes read: %d", reader.BytesRead)
+		})
+	}
+}
+
+func TestGetImageSize(t *testing.T) {
+	for i, c := range cases {
+		t.Run("Decode:"+strconv.Itoa(i), func(t *testing.T) {
+			width, height, err := img.GetImageSize(c.url)
+			assert.NoError(t, err)
+			assert.Equal(t, c.width, width)
+			assert.Equal(t, c.height, height)
+		})
+	}
+}

common/init.go

@@ -43,7 +43,11 @@ func init() {
 	}
 
 	if os.Getenv("SESSION_SECRET") != "" {
-		SessionSecret = os.Getenv("SESSION_SECRET")
+		if os.Getenv("SESSION_SECRET") == "random_string" {
+			SysError("SESSION_SECRET is set to an example value, please change it to a random string.")
+		} else {
+			SessionSecret = os.Getenv("SESSION_SECRET")
+		}
 	}
 	if os.Getenv("SQLITE_PATH") != "" {
 		SQLitePath = os.Getenv("SQLITE_PATH")

common/model-ratio.go

@@ -76,17 +76,22 @@ var ModelRatio = map[string]float64{
 	"dall-e-3":                  20,     // $0.040 - $0.120 / image
 	"claude-instant-1":          0.815,  // $1.63 / 1M tokens
 	"claude-2":                  5.51,   // $11.02 / 1M tokens
+	"claude-2.0":                5.51,   // $11.02 / 1M tokens
+	"claude-2.1":                5.51,   // $11.02 / 1M tokens
 	"ERNIE-Bot":                 0.8572, // ￥0.012 / 1k tokens
 	"ERNIE-Bot-turbo":           0.5715, // ￥0.008 / 1k tokens
 	"ERNIE-Bot-4":               8.572,  // ￥0.12 / 1k tokens
 	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
 	"PaLM-2":                    1,
+	"gemini-pro":                1,      // $0.00025 / 1k characters -> $0.001 / 1k tokens
 	"chatglm_turbo":             0.3572, // ￥0.005 / 1k tokens
 	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
 	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens
-	"qwen-turbo":                0.8572, // ￥0.012 / 1k tokens
-	"qwen-plus":                 10,     // ￥0.14 / 1k tokens
+	"qwen-turbo":                0.5715, // ￥0.008 / 1k tokens  // https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-thousand-questions-metering-and-billing
+	"qwen-plus":                 1.4286, // ￥0.02 / 1k tokens
+	"qwen-max":                  1.4286, // ￥0.02 / 1k tokens
+	"qwen-max-longcontext":      1.4286, // ￥0.02 / 1k tokens
 	"text-embedding-v1":         0.05,   // ￥0.0007 / 1k tokens
 	"SparkDesk":                 1.2858, // ￥0.018 / 1k tokens
 	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens

common/token.go

@@ -3,8 +3,10 @@ package common
 import (
 	"errors"
 	"fmt"
+	"math"
 	"strings"
 
+	"one-api/common/image"
 	"one-api/types"
 
 	"github.com/pkoukk/tiktoken-go"
@@ -79,6 +81,33 @@ func CountTokenMessages(messages []types.ChatCompletionMessage, model string) in
 	tokenNum := 0
 	for _, message := range messages {
 		tokenNum += tokensPerMessage
+		switch v := message.Content.(type) {
+		case string:
+			tokenNum += getTokenNum(tokenEncoder, v)
+		case []any:
+			for _, it := range v {
+				m := it.(map[string]any)
+				switch m["type"] {
+				case "text":
+					tokenNum += getTokenNum(tokenEncoder, m["text"].(string))
+				case "image_url":
+					imageUrl, ok := m["image_url"].(map[string]any)
+					if ok {
+						url := imageUrl["url"].(string)
+						detail := ""
+						if imageUrl["detail"] != nil {
+							detail = imageUrl["detail"].(string)
+						}
+						imageTokens, err := countImageTokens(url, detail)
+						if err != nil {
+							SysError("error counting image tokens: " + err.Error())
+						} else {
+							tokenNum += imageTokens
+						}
+					}
+				}
+			}
+		}
 		tokenNum += getTokenNum(tokenEncoder, message.StringContent())
 		tokenNum += getTokenNum(tokenEncoder, message.Role)
 		if message.Name != nil {
@@ -90,16 +119,84 @@ func CountTokenMessages(messages []types.ChatCompletionMessage, model string) in
 	return tokenNum
 }
 
+const (
+	lowDetailCost         = 85
+	highDetailCostPerTile = 170
+	additionalCost        = 85
+)
+
+// https://platform.openai.com/docs/guides/vision/calculating-costs
+// https://github.com/openai/openai-cookbook/blob/05e3f9be4c7a2ae7ecf029a7c32065b024730ebe/examples/How_to_count_tokens_with_tiktoken.ipynb
+func countImageTokens(url string, detail string) (_ int, err error) {
+	var fetchSize = true
+	var width, height int
+	// Reference: https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding
+	// detail == "auto" is undocumented on how it works, it just said the model will use the auto setting which will look at the image input size and decide if it should use the low or high setting.
+	// According to the official guide, "low" disable the high-res model,
+	// and only receive low-res 512px x 512px version of the image, indicating
+	// that image is treated as low-res when size is smaller than 512px x 512px,
+	// then we can assume that image size larger than 512px x 512px is treated
+	// as high-res. Then we have the following logic:
+	// if detail == "" || detail == "auto" {
+	// 	width, height, err = image.GetImageSize(url)
+	// 	if err != nil {
+	// 		return 0, err
+	// 	}
+	// 	fetchSize = false
+	// 	// not sure if this is correct
+	// 	if width > 512 || height > 512 {
+	// 		detail = "high"
+	// 	} else {
+	// 		detail = "low"
+	// 	}
+	// }
+
+	// However, in my test, it seems to be always the same as "high".
+	// The following image, which is 125x50, is still treated as high-res, taken
+	// 255 tokens in the response of non-stream chat completion api.
+	// https://upload.wikimedia.org/wikipedia/commons/1/10/18_Infantry_Division_Messina.jpg
+	if detail == "" || detail == "auto" {
+		// assume by test, not sure if this is correct
+		detail = "high"
+	}
+	switch detail {
+	case "low":
+		return lowDetailCost, nil
+	case "high":
+		if fetchSize {
+			width, height, err = image.GetImageSize(url)
+			if err != nil {
+				return 0, err
+			}
+		}
+		if width > 2048 || height > 2048 { // max(width, height) > 2048
+			ratio := float64(2048) / math.Max(float64(width), float64(height))
+			width = int(float64(width) * ratio)
+			height = int(float64(height) * ratio)
+		}
+		if width > 768 && height > 768 { // min(width, height) > 768
+			ratio := float64(768) / math.Min(float64(width), float64(height))
+			width = int(float64(width) * ratio)
+			height = int(float64(height) * ratio)
+		}
+		numSquares := int(math.Ceil(float64(width)/512) * math.Ceil(float64(height)/512))
+		result := numSquares*highDetailCostPerTile + additionalCost
+		return result, nil
+	default:
+		return 0, errors.New("invalid detail option")
+	}
+}
+
 func CountTokenInput(input any, model string) int {
-	switch input.(type) {
+	switch v := input.(type) {
 	case string:
-		return CountTokenText(input.(string), model)
+		return CountTokenInput(v, model)
 	case []string:
 		text := ""
-		for _, s := range input.([]string) {
+		for _, s := range v {
 			text += s
 		}
-		return CountTokenText(text, model)
+		return CountTokenInput(text, model)
 	}
 	return 0
 }