cache translation in minio instead of mongo
This commit is contained in:
@@ -4,7 +4,6 @@ import (
|
||||
"context"
|
||||
"errors"
|
||||
"strings"
|
||||
"time"
|
||||
"tm/internal/tender"
|
||||
"tm/pkg/ai_summarizer"
|
||||
"tm/pkg/logger"
|
||||
@@ -12,7 +11,7 @@ import (
|
||||
)
|
||||
|
||||
// TranslationWorker backfills missing tender translations using the AI pipeline
|
||||
// and on-demand translate API, syncing results from MinIO when available.
|
||||
// and on-demand translate API. Results are persisted by the AI service in MinIO only.
|
||||
type TranslationWorker struct {
|
||||
Mongo *mongo.ConnectionManager
|
||||
Logger logger.Logger
|
||||
@@ -95,20 +94,22 @@ func (w *TranslationWorker) Run() {
|
||||
}
|
||||
|
||||
func (w *TranslationWorker) runForLanguage(language string) {
|
||||
skip := 0
|
||||
for {
|
||||
tenders, totalCount, err := w.TenderRepo.GetUnTranslatedTenders(context.Background(), language, w.BatchSize, 0)
|
||||
tenders, totalCount, err := w.TenderRepo.GetUnTranslatedTenders(context.Background(), language, w.BatchSize, skip)
|
||||
if err != nil {
|
||||
w.Logger.Error("Failed to fetch untranslated tenders", map[string]interface{}{
|
||||
w.Logger.Error("Failed to fetch tenders for translation backfill", map[string]interface{}{
|
||||
"target_language": language,
|
||||
"error": err.Error(),
|
||||
})
|
||||
return
|
||||
}
|
||||
|
||||
w.Logger.Info("Fetched untranslated tenders batch", map[string]interface{}{
|
||||
w.Logger.Info("Fetched tenders for translation backfill", map[string]interface{}{
|
||||
"target_language": language,
|
||||
"batch_count": len(tenders),
|
||||
"total_count": totalCount,
|
||||
"skip": skip,
|
||||
})
|
||||
|
||||
if len(tenders) == 0 {
|
||||
@@ -118,6 +119,11 @@ func (w *TranslationWorker) runForLanguage(language string) {
|
||||
for _, t := range tenders {
|
||||
w.translateTender(&t, language)
|
||||
}
|
||||
|
||||
skip += len(tenders)
|
||||
if int64(skip) >= totalCount {
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -131,8 +137,8 @@ func (w *TranslationWorker) translateTender(t *tender.Tender, language string) {
|
||||
})
|
||||
return
|
||||
}
|
||||
if existing, ok := t.Translations[language]; ok && strings.TrimSpace(existing.Title) != "" {
|
||||
w.Logger.Debug("Skipping tender translation because target language already exists", map[string]interface{}{
|
||||
if w.hasTranslationInStorage(t, language) {
|
||||
w.Logger.Debug("Skipping tender translation: already available in MinIO", map[string]interface{}{
|
||||
"tender_id": t.ID.Hex(),
|
||||
"notice_id": t.NoticePublicationID,
|
||||
"target_language": language,
|
||||
@@ -143,23 +149,11 @@ func (w *TranslationWorker) translateTender(t *tender.Tender, language string) {
|
||||
title, description, source, err := w.resolveTranslation(t, language)
|
||||
if err != nil {
|
||||
w.Logger.Error("Failed to translate tender", map[string]interface{}{
|
||||
"tender_id": t.ID.Hex(),
|
||||
"notice_id": t.NoticePublicationID,
|
||||
"target_language": language,
|
||||
"tender_id": t.ID.Hex(),
|
||||
"notice_id": t.NoticePublicationID,
|
||||
"target_language": language,
|
||||
"translation_source": source,
|
||||
"translation_error": err.Error(),
|
||||
})
|
||||
return
|
||||
}
|
||||
|
||||
persistTranslation(t, language, title, description)
|
||||
if err := w.TenderRepo.Update(context.Background(), t); err != nil {
|
||||
w.Logger.Error("Failed to persist translated tender", map[string]interface{}{
|
||||
"tender_id": t.ID.Hex(),
|
||||
"notice_id": t.NoticePublicationID,
|
||||
"target_language": language,
|
||||
"translation_source": source,
|
||||
"persistence_error": err.Error(),
|
||||
"translation_error": err.Error(),
|
||||
})
|
||||
return
|
||||
}
|
||||
@@ -169,9 +163,24 @@ func (w *TranslationWorker) translateTender(t *tender.Tender, language string) {
|
||||
"notice_id": t.NoticePublicationID,
|
||||
"target_language": language,
|
||||
"translation_source": source,
|
||||
"title_len": len(title),
|
||||
"description_len": len(description),
|
||||
})
|
||||
}
|
||||
|
||||
func (w *TranslationWorker) hasTranslationInStorage(t *tender.Tender, language string) bool {
|
||||
if w.AIStorage == nil {
|
||||
return false
|
||||
}
|
||||
stored, err := w.AIStorage.GetTranslationFromStorage(
|
||||
context.Background(),
|
||||
t.ContractFolderID,
|
||||
t.NoticePublicationID,
|
||||
language,
|
||||
)
|
||||
return err == nil && strings.TrimSpace(stored.Title) != ""
|
||||
}
|
||||
|
||||
func (w *TranslationWorker) resolveTranslation(t *tender.Tender, language string) (title, description, source string, err error) {
|
||||
if w.AIStorage != nil {
|
||||
stored, storageErr := w.AIStorage.GetTranslationFromStorage(
|
||||
@@ -207,21 +216,3 @@ func (w *TranslationWorker) resolveTranslation(t *tender.Tender, language string
|
||||
}
|
||||
return resp.TranslatedTitle, resp.TranslatedDescription, "api", nil
|
||||
}
|
||||
|
||||
func persistTranslation(t *tender.Tender, language, title, description string) {
|
||||
if t.Translations == nil {
|
||||
t.Translations = make(map[string]tender.TranslationEntry)
|
||||
}
|
||||
now := time.Now().Unix()
|
||||
t.Translations[language] = tender.TranslationEntry{
|
||||
Title: title,
|
||||
Description: description,
|
||||
Language: language,
|
||||
TranslatedAt: now,
|
||||
}
|
||||
if t.ProcessingMetadata.TranslatedData == nil {
|
||||
t.ProcessingMetadata.TranslatedData = make(map[string]string)
|
||||
}
|
||||
t.ProcessingMetadata.TranslatedData[language] = "done"
|
||||
t.ProcessingMetadata.TranslatedAt = now
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user