Mirrored-Projects/paperless-gpt
1
0
Fork 0
mirror of https://github.com/icereed/paperless-gpt.git synced 2025-03-12 12:58:02 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

fix(ocr): fix the auto-tag trigger for OCR (#216)

Browse source
This commit is contained in:
Icereed 2025-02-10 21:21:45 +01:00 committed by GitHub
parent 18ba388af1
commit cf7c93c314
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 19 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
main.go
View file

@ -187,6 +187,21 @@ func main() {
ocrProvider: ocrProvider,
}
if app.isOcrEnabled() {
fmt.Printf("Using %s as manual OCR tag\n", manualOcrTag)
fmt.Printf("Using %s as auto OCR tag\n", autoOcrTag)
rawLimitOcrPages := os.Getenv("OCR_LIMIT_PAGES")
if rawLimitOcrPages == "" {
limitOcrPages = 5
} else {
var err error
limitOcrPages, err = strconv.Atoi(rawLimitOcrPages)
if err != nil {
log.Fatalf("Invalid OCR_LIMIT_PAGES value: %v", err)
}
}
}
// Start background process for auto-tagging
go func() {
minBackoffDuration := 10 * time.Second
@ -197,7 +212,7 @@ func main() {
for {
processedCount, err := func() (int, error) {
count := 0
if isOcrEnabled() {
if app.isOcrEnabled() {
ocrCount, err := app.processAutoOcrTagDocuments()
if err != nil {
return 0, fmt.Errorf("error in processAutoOcrTagDocuments: %w", err)
@ -256,7 +271,7 @@ func main() {
// Endpoint to see if user enabled OCR
api.GET("/experimental/ocr", func(c *gin.Context) {
enabled := isOcrEnabled()
enabled := app.isOcrEnabled()
c.JSON(http.StatusOK, gin.H{"enabled": enabled})
})
@ -366,8 +381,8 @@ func initLogger() {
})
}
func isOcrEnabled() bool {
return visionLlmModel != "" && visionLlmProvider != ""
func (app *App) isOcrEnabled() bool {
return app.ocrProvider != nil
}
// validateOrDefaultEnvVars ensures all necessary environment variables are set
@ -385,16 +400,10 @@ func validateOrDefaultEnvVars() {
if manualOcrTag == "" {
manualOcrTag = "paperless-gpt-ocr"
}
if isOcrEnabled() {
fmt.Printf("Using %s as manual OCR tag\n", manualOcrTag)
}
if autoOcrTag == "" {
autoOcrTag = "paperless-gpt-ocr-auto"
}
if isOcrEnabled() {
fmt.Printf("Using %s as auto OCR tag\n", autoOcrTag)
}
if paperlessBaseURL == "" {
log.Fatal("Please set the PAPERLESS_BASE_URL environment variable.")
@ -420,19 +429,6 @@ func validateOrDefaultEnvVars() {
log.Fatal("Please set the OPENAI_API_KEY environment variable for OpenAI provider.")
}
if isOcrEnabled() {
rawLimitOcrPages := os.Getenv("OCR_LIMIT_PAGES")
if rawLimitOcrPages == "" {
limitOcrPages = 5
} else {
var err error
limitOcrPages, err = strconv.Atoi(rawLimitOcrPages)
if err != nil {
log.Fatalf("Invalid OCR_LIMIT_PAGES value: %v", err)
}
}
}
// Initialize token limit from environment variable
if limit := os.Getenv("TOKEN_LIMIT"); limit != "" {
if parsed, err := strconv.Atoi(limit); err == nil {