remove now unnecessary post processings

app.py

@@ -14,7 +14,6 @@ def check_additional_requirements():
             os.system("pip install gradio==3.44.3")
     else:
         os.system("pip install gradio==3.44.3")
-    os.system(os.environ["DD_ADDONS"])
     return
 
 
@@ -24,15 +23,12 @@ check_additional_requirements()
 import deepdoctection as dd
 from deepdoctection.dataflow.serialize import DataFromList
 import time
-from dd_addons.extern import PdfTextDetector, PostProcessor, get_xsl_path
-from dd_addons.pipe.conn import PostProcessorService
 import gradio as gr
 from botocore.config import Config
 
 
 # work around: https://discuss.huggingface.co/t/how-to-install-a-specific-version-of-gradio-in-spaces/13552
 _DD_ONE = "conf_dd_one.yaml"
-_XSL_PATH = get_xsl_path()
 
 dd.ModelCatalog.register("xrf_layout/model_final_inf_only.pt",dd.ModelProfile(
             name="xrf_layout/model_final_inf_only.pt",
@@ -106,8 +102,6 @@ categories_item = dd.ModelCatalog.get_profile(cfg.WEIGHTS.D2ITEM).categories
 assert categories_item is not None
 d_item = dd.D2FrcnnDetector(item_config_path, item_weights_path, categories_item, device=cfg.DEVICE)
 
-# pdf miner
-pdf_text = PdfTextDetector(_XSL_PATH)
 
 # text detector
 credentials_kwargs={"aws_access_key_id": os.environ["ACCESS_KEY"],
@@ -164,10 +158,7 @@ def build_gradio_analyzer():
 
     if cfg.OCR:
 
-        d_text = dd.TextExtractionService(pdf_text)
-        pipe_component_list.append(d_text)
-
-        t_text = dd.TextExtractionService(tex_text,skip_if_text_extracted=True)
+        t_text = dd.TextExtractionService(tex_text)
         pipe_component_list.append(t_text)
 
         match_words = dd.MatchingService(
@@ -188,10 +179,6 @@ def build_gradio_analyzer():
 
     pipe = dd.DoctectionPipe(pipeline_component_list=pipe_component_list)
 
-    post_processor = PostProcessor("deepdoctection", **credentials_kwargs)
-    post_service = PostProcessorService(post_processor)
-    pipe_component_list.append(post_service)
-
     return pipe