feat: add image counter for gpt-4 vision (#795)

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)
+		})
+	}
+}

controller/relay-text.go

@@ -410,6 +410,10 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	defer func(ctx context.Context) {
 		// c.Writer.Flush()
 		go func() {
+			if promptTokens != textResponse.PromptTokens {
+				common.SysError(fmt.Sprintf("prompt tokens not match, expected %d, actual %d", promptTokens, textResponse.PromptTokens))
+			}
+
 			quota := 0
 			completionRatio := common.GetCompletionRatio(textRequest.Model)
 			promptTokens = textResponse.Usage.PromptTokens

controller/relay-utils.go

@@ -3,10 +3,13 @@ package controller
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"io"
+	"math"
 	"net/http"
 	"one-api/common"
+	"one-api/common/image"
 	"one-api/model"
 	"strconv"
 	"strings"
@@ -87,7 +90,33 @@ func countTokenMessages(messages []Message, model string) int {
 	tokenNum := 0
 	for _, message := range messages {
 		tokenNum += tokensPerMessage
-		tokenNum += getTokenNum(tokenEncoder, message.StringContent())
+		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 {
+							common.SysError("error counting image tokens: " + err.Error())
+						} else {
+							tokenNum += imageTokens
+						}
+					}
+				}
+			}
+		}
 		tokenNum += getTokenNum(tokenEncoder, message.Role)
 		if message.Name != nil {
 			tokenNum += tokensPerName
@@ -98,13 +127,81 @@ func countTokenMessages(messages []Message, model string) int {
 	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 countTokenText(v, model)
 	case []string:
 		text := ""
-		for _, s := range input.([]string) {
+		for _, s := range v {
 			text += s
 		}
 		return countTokenText(text, model)

go.mod

@@ -15,7 +15,9 @@ require (
 	github.com/google/uuid v1.3.0
 	github.com/gorilla/websocket v1.5.0
 	github.com/pkoukk/tiktoken-go v0.1.5
+	github.com/stretchr/testify v1.8.3
 	golang.org/x/crypto v0.14.0
+	golang.org/x/image v0.14.0
 	gorm.io/driver/mysql v1.4.3
 	gorm.io/driver/postgres v1.5.2
 	gorm.io/driver/sqlite v1.4.3
@@ -26,6 +28,7 @@ require (
 	github.com/bytedance/sonic v1.9.1 // indirect
 	github.com/cespare/xxhash/v2 v2.1.2 // indirect
 	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
+	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.10.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.2 // indirect
@@ -50,12 +53,13 @@ require (
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml/v2 v2.0.8 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.11 // indirect
 	golang.org/x/arch v0.3.0 // indirect
 	golang.org/x/net v0.17.0 // indirect
 	golang.org/x/sys v0.13.0 // indirect
-	golang.org/x/text v0.13.0 // indirect
+	golang.org/x/text v0.14.0 // indirect
 	google.golang.org/protobuf v1.30.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -152,6 +152,8 @@ golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.14.0 h1:wBqGXzWJW6m1XrIKlAH0Hs1JJ7+9KBwnIO8v66Q9cHc=
 golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4=
+golang.org/x/image v0.14.0 h1:tNgSxAFe3jC4uYqvZdTr84SZoM1KfwdC9SKIFrLjFn4=
+golang.org/x/image v0.14.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
 golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
@@ -168,8 +170,8 @@ golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9sn
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k=
+golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
-golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
+golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=