+ revert remote strategy

+ use default pdf file format for pdf instead of using docling for that

Author: choinek

config/strategies.yaml

@@ -11,8 +11,8 @@ strategies:
       class: text_extract_api.extract.strategies.easyocr.EasyOCRStrategy
    docling:
       class: text_extract_api.extract.strategies.docling.DoclingStrategy
-
-   # remote strategy example:
-   #remote:
-   #   class: text_extract_api.extract.strategies.remote.RemoteStrategy
-   #   url:
+      model: llama3.1
+      prompt: You are OCR. Convert image to markdown. Return only the markdown with no explanation text. Do not exclude any content from the page.
+   remote:
+      class: text_extract_api.extract.strategies.remote.RemoteStrategy
+      url:

text_extract_api/extract/strategies/docling.py

@@ -48,7 +48,7 @@ def text_gatherer(self, docling_document: DoclingDocument) -> str:
 
     def _convert_to_docling(self, file_path: str) -> DoclingDocument:
         """
-        Converts a PDF file into a DoclingDocument instance.
+        Converts a file into a DoclingDocument instance.
 
         :param file_path: Path to the PDF file to be converted.
         :return: DoclingDocument instance.

text_extract_api/files/file_formats/docling.py

@@ -9,20 +9,18 @@ class DoclingFileFormat(FileFormat):
     @staticmethod
     def accepted_mime_types() -> list[str]:
         return [
-            "application/pdf",  # PDF documents
             "application/vnd.docling",  # Docling documents
+            # Do not put all formats handled by docling here - only those that are not supported by dedicated file formats"
             "text/plain",
             "text/markdown",
-            "text/html",  # HTML documents
+            "text/html",
             "application/msword",
             "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
             "application/vnd.oasis.opendocument.text",
             "application/vnd.ms-excel",
             "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
             "application/vnd.ms-powerpoint",
             "application/vnd.openxmlformats-officedocument.presentationml.presentation",
-            "image/jpeg",
-            "image/png",
             "text/csv",
             "application/json",
             "application/xml",