v0.21.1-fastapi

rag/flow/hierarchical_merger/hierarchical_merger.py

@@ -22,7 +22,7 @@ import trio
 
 from api.utils import get_uuid
 from api.utils.base64_image import id2image, image2id
-from ocr.service import get_ocr_service
+from deepdoc.parser.pdf_parser import RAGFlowPdfParser
 from rag.flow.base import ProcessBase, ProcessParamBase
 from rag.flow.hierarchical_merger.schema import HierarchicalMergerFromUpstream
 from rag.nlp import concat_img
@@ -166,24 +166,21 @@ class HierarchicalMerger(ProcessBase):
                 img = None
                 for i in path:
                     txt += lines[i] + "\n"
-                    concat_img(img, id2image(section_images[i], partial(STORAGE_IMPL.get)))
+                    concat_img(img, id2image(section_images[i], partial(STORAGE_IMPL.get, tenant_id=self._canvas._tenant_id)))
                 cks.append(txt)
                 images.append(img)
 
-            ocr_service = get_ocr_service()
-            processed_cks = []
-            for c, img in zip(cks, images):
-                cleaned_text = await ocr_service.remove_tag(c)
-                positions = await ocr_service.extract_positions(c)
-                processed_cks.append({
-                    "text": cleaned_text,
+            cks = [
+                {
+                    "text": RAGFlowPdfParser.remove_tag(c),
                     "image": img,
-                    "positions": positions,
-                })
-            cks = processed_cks
+                    "positions": RAGFlowPdfParser.extract_positions(c),
+                }
+                for c, img in zip(cks, images)
+            ]
             async with trio.open_nursery() as nursery:
                 for d in cks:
-                    nursery.start_soon(image2id, d, partial(STORAGE_IMPL.put), get_uuid())
+                    nursery.start_soon(image2id, d, partial(STORAGE_IMPL.put, tenant_id=self._canvas._tenant_id), get_uuid())
             self.set_output("chunks", cks)
 
         self.callback(1, "Done.")