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)
+		})
+	}
+}