feat: update extentions for pdf

Author: phv2312

libs/kotaemon/kotaemon/indices/ingests/extensions.py

@@ -45,6 +45,8 @@ def get_current_loader(self) -> dict[str, BaseReader]:
 
     @staticmethod
     def _init_supported() -> tuple[dict[str, list[BaseReader]], dict[str, str]]:
+        gocr = GOCR2ImageReader()
+
         supported: dict[str, list[BaseReader]] = {
             ".xlsx": [PandasExcelReader()],
             ".docx": [unstructured],
@@ -53,12 +55,12 @@ def _init_supported() -> tuple[dict[str, list[BaseReader]], dict[str, str]]:
             ".doc": [unstructured],
             ".html": [HtmlReader()],
             ".mhtml": [MhtmlReader()],
-            ".png": [unstructured, GOCR2ImageReader()],
-            ".jpeg": [unstructured, GOCR2ImageReader()],
-            ".jpg": [unstructured, GOCR2ImageReader()],
+            ".png": [unstructured, gocr],
+            ".jpeg": [unstructured, gocr],
+            ".jpg": [unstructured, gocr],
             ".tiff": [unstructured],
             ".tif": [unstructured],
-            ".pdf": [PDFThumbnailReader()],
+            ".pdf": [PDFThumbnailReader(), adobe_reader, azure_reader],
             ".txt": [TxtReader()],
             ".md": [TxtReader()],
         }

libs/kotaemon/kotaemon/indices/ingests/files.py

@@ -18,13 +18,8 @@
     HtmlReader,
     MathpixPDFReader,
     OCRReader,
-    PandasExcelReader,
-    PDFThumbnailReader,
-    TxtReader,
     UnstructuredReader,
     WebReader,
-    UnstructuredReader, 
-    ImageReader,
 )
 
 web_reader = WebReader()

libs/kotaemon/kotaemon/loaders/ocr_loader.py

@@ -262,4 +262,3 @@ def _tenacious_api_post(
             )
 
         return result
-    

libs/ktem/ktem/pages/chat/__init__.py

@@ -5,7 +5,6 @@
 from typing import Optional
 
 import gradio as gr
-from filelock import FileLock
 from ktem.app import BasePage
 from ktem.components import reasonings
 from ktem.db.models import Conversation, engine