zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-08-15 13:14:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

deepdoc: send lossless PNG instead of JPEG to the DeepDoc inference service (#18282)

Browse Source
This commit is contained in:
Jack
2026-08-14 18:49:33 +08:00
committed by GitHub
parent 3d50f8bcfc
commit 2678a0c5f5
3 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
internal/deepdoc/parser/pdf/inference/cache.go
View File

@@ -123,16 +123,16 @@ func newDocAnalyzerCacheWithStore(inner doctype.DocAnalyzer, s cacheStore, ttl t
}
// cacheKey returns the cache key used for the given method +
// image. It encodes the image to JPEG (matching what the
// image. It encodes the image to PNG (matching what the
// inference HTTP client actually sends) and hashes the
// resulting bytes. JPEG encoding is deterministic for a given
// image and quality, so two DocAnalyzer calls with the same
// resulting bytes. PNG encoding is deterministic for a given
// image, so two DocAnalyzer calls with the same
// image content produce the same key.
func cacheKey(method string, img image.Image) (string, error) {
if img == nil {
return "", fmt.Errorf("%s: nil image", method)
}
data, err := util.EncodeJPEG(img)
data, err := util.EncodePNG(img)
if err != nil {
return "", fmt.Errorf("%s: encode: %w", method, err)
}

16
internal/deepdoc/parser/pdf/inference/client.go
View File

@@ -78,12 +78,12 @@ type bboxesResponse struct {
// DLA analyzes a full page image and returns labeled regions.
func (c *Client) DLA(ctx context.Context, pageImage image.Image) ([]pdf.DLARegion, error) {
data, err := util.EncodeJPEG(pageImage)
data, err := util.EncodePNG(pageImage)
if err != nil {
return nil, fmt.Errorf("dla: encode: %w", err)
}
var resp bboxesResponse
if err := c.post(ctx, "/predict/dla", data, "dla.jpeg", &resp); err != nil {
if err := c.post(ctx, "/predict/dla", data, "dla.png", &resp); err != nil {
return nil, fmt.Errorf("dla: %w", err)
}
regions := make([]pdf.DLARegion, 0, len(resp.BBoxes))
@@ -107,12 +107,12 @@ func (c *Client) DLA(ctx context.Context, pageImage image.Image) ([]pdf.DLARegio
// TSR recognises table structure from a cropped image.
func (c *Client) TSR(ctx context.Context, cropped image.Image) ([]pdf.TSRCell, error) {
data, err := util.EncodeJPEG(cropped)
data, err := util.EncodePNG(cropped)
if err != nil {
return nil, fmt.Errorf("tsr: encode: %w", err)
}
var resp bboxesResponse
if err := c.post(ctx, "/predict/tsr", data, "tsr.jpeg", &resp); err != nil {
if err := c.post(ctx, "/predict/tsr", data, "tsr.png", &resp); err != nil {
return nil, fmt.Errorf("tsr: %w", err)
}
cells := make([]pdf.TSRCell, 0, len(resp.BBoxes))
@@ -152,7 +152,7 @@ type ocrRecognizeResponse struct {
// OCRDetect detects text regions (bounding boxes) in an image.
// DeepDoc /predict/ocr with operator=det returns quad boxes: [[[x0,y0],[x1,y1],[x2,y2],[x3,y3]], ...]
func (c *Client) OCRDetect(ctx context.Context, cropped image.Image) ([]pdf.OCRBox, error) {
data, err := util.EncodeJPEG(cropped)
data, err := util.EncodePNG(cropped)
if err != nil {
return nil, fmt.Errorf("ocr detect: encode: %w", err)
}
@@ -161,7 +161,7 @@ func (c *Client) OCRDetect(ctx context.Context, cropped image.Image) ([]pdf.OCRB
var rawEnvelope struct {
Output json.RawMessage `json:"output"`
}
if err := c.post(ctx, "/predict/ocr", data, "ocr_detect.jpeg", &rawEnvelope, "operator", "det"); err != nil {
if err := c.post(ctx, "/predict/ocr", data, "ocr_detect.png", &rawEnvelope, "operator", "det"); err != nil {
return nil, fmt.Errorf("ocr detect: %w", err)
}
@@ -197,12 +197,12 @@ func (c *Client) OCRDetect(ctx context.Context, cropped image.Image) ([]pdf.OCRB
// OCRRecognize recognizes text in a cropped image region.
// DeepDoc /predict/ocr with operator=rec returns [[["text", confidence], ...]]
func (c *Client) OCRRecognize(ctx context.Context, cropped image.Image) ([]pdf.OCRText, error) {
data, err := util.EncodeJPEG(cropped)
data, err := util.EncodePNG(cropped)
if err != nil {
return nil, fmt.Errorf("ocr rec: encode: %w", err)
}
var result ocrRecognizeResponse
if err := c.post(ctx, "/predict/ocr", data, "ocr_rec.jpeg", &result, "operator", "rec"); err != nil {
if err := c.post(ctx, "/predict/ocr", data, "ocr_rec.png", &result, "operator", "rec"); err != nil {
return nil, fmt.Errorf("ocr rec: %w", err)
}
var texts []pdf.OCRText

10
internal/deepdoc/parser/pdf/inference/client_test.go
View File

@@ -50,8 +50,8 @@ func TestDeepDocHTTP_DLA(t *testing.T) {
t.Fatalf("missing 'request' multipart field: %v", err)
}
defer file.Close()
if !strings.HasSuffix(header.Filename, ".jpeg") {
t.Errorf("filename = %q, want *.jpeg", header.Filename)
if !strings.HasSuffix(header.Filename, ".png") {
t.Errorf("filename = %q, want *.png", header.Filename)
}
// Return canned DLA response: one table region (classId=5).
@@ -124,11 +124,11 @@ func TestDeepDocHTTP_OCRDetect(t *testing.T) {
if op := r.FormValue("operator"); op != "det" {
t.Errorf("operator = %q, want 'det'", op)
}
// Verify image is JPEG (not PNG).
// Verify image is PNG (not JPEG).
file, header, _ := r.FormFile("request")
defer file.Close()
if !strings.HasSuffix(header.Filename, ".jpeg") {
t.Errorf("filename = %q, want *.jpeg", header.Filename)
if !strings.HasSuffix(header.Filename, ".png") {
t.Errorf("filename = %q, want *.png", header.Filename)
}
// Return canned OCR detect response: 1 quad box.