Merged in feature/textExtractionsPart1 (pull request #192)

all schema and rest apis for text extraction support

* in progress

* stage 8 complete

* phase 9 completed

* phase 9 complete

* ongoing - s3 path fix

* working

* optimize ci build

* e2e tests

* missing test

api/docInitRunner/runner.go

@@ -9,6 +9,8 @@ import (
 	"queryorchestration/internal/database/repository"
 	documentinit "queryorchestration/internal/document/init"
 	"queryorchestration/internal/serviceconfig/objectstore"
+
+	"github.com/google/uuid"
 )
 
 const Name = "docInitRunner"
@@ -41,8 +43,9 @@ func (s Runner) Process(ctx context.Context, body Body) bool {
 		return false
 	}
 
-	// Get filename from documentUploads table
+	// Get filename and folder_id from documentUploads table
 	var filename *string
+	var folderID *uuid.UUID
 	upload, err := s.svc.Queries.GetDocumentUploadByKey(ctx, &repository.GetDocumentUploadByKeyParams{
 		Bucket: body.Bucket,
 		Key:    body.Key,
@@ -51,20 +54,25 @@ func (s Runner) Process(ctx context.Context, body Body) bool {
 		slog.Error("unable to get document upload", "bucket", body.Bucket, "key", body.Key, "error", err)
 		return false
 	}
-	if err == nil && upload.Filename != nil {
-		filename = upload.Filename
+	if err == nil {
+		if upload.Filename != nil {
+			filename = upload.Filename
+		}
+		folderID = upload.FolderID
 	}
 
 	id, err := s.svc.Document.Create(ctx, &documentinit.Create{
-		Key:      key,
-		Bucket:   body.Bucket,
-		Hash:     body.Hash,
-		Filename: filename,
+		Key:          key,
+		Bucket:       body.Bucket,
+		Hash:         body.Hash,
+		Filename:     filename,
+		OriginalPath: filename, // For batch uploads, filename contains the full original path
+		FolderID:     folderID,
 	})
 	if err != nil {
 		return false
 	}
-	slog.Debug("created document", "id", id, "filename", filename)
+	slog.Debug("created document", "id", id, "filename", filename, "folder_id", folderID)
 
 	return true
 }