Refactor ZeroxPDFLoader

Author: pprados

docs/docs/integrations/document_loaders/zeroxpdfloader.ipynb

@@ -41,7 +41,7 @@ jq>=1.4.1,<2
 jsonschema>1
 keybert>=0.8.5
 langchain_openai>=0.2.1
-litellm>=1.30,<=1.39.5
+litellm>=1.30
 lxml>=4.9.3,<6.0
 markdownify>=0.11.6,<0.12
 motor>=3.3.1,<4
@@ -62,6 +62,7 @@ pandas>=2.0.1,<3
 pdfminer-six==20231228
 pdfplumber>=0.11
 pgvector>=0.1.6,<0.2
+pillow>=10.4
 playwright>=1.48.0,<2
 praw>=7.7.1,<8
 premai>=0.3.25,<0.4,!=0.3.100
@@ -74,6 +75,7 @@ pymupdf>=1.22.3,<2
 pypdf>=3.4.0,<5
 pypdfium2>=4.10.0,<5
 pyspark>=3.4.0,<4
+py-zerox>=0.0.7
 rank-bm25>=0.2.2,<0.3
 rapidfuzz>=3.1.1,<4
 rapidocr-onnxruntime>=1.3.2,<2

libs/community/extended_testing_deps.txt

@@ -360,6 +360,7 @@
         PyPDFium2Loader,
         PyPDFLoader,
         UnstructuredPDFLoader,
+        ZeroxPDFLoader,
     )
     from langchain_community.document_loaders.pebblo import (
         PebbloSafeLoader,
@@ -732,6 +733,7 @@
     "YoutubeAudioLoader": "langchain_community.document_loaders.blob_loaders",
     "YoutubeLoader": "langchain_community.document_loaders.youtube",
     "YuqueLoader": "langchain_community.document_loaders.yuque",
+    "ZeroxPDFLoader": "langchain_community.document_loaders.pdf",
 }
 
 
@@ -940,4 +942,5 @@ def __getattr__(name: str) -> Any:
     "YoutubeAudioLoader",
     "YoutubeLoader",
     "YuqueLoader",
+    "ZeroxPDFLoader",
 ]

libs/community/langchain_community/document_loaders/__init__.py

@@ -32,6 +32,7 @@
         PyMuPDFParser,
         PyPDFium2Parser,
         PyPDFParser,
+        ZeroxPDFParser,
     )
     from langchain_community.document_loaders.parsers.vsdx import (
         VsdxParser,
@@ -55,6 +56,7 @@
     "RapidOCRBlobParser": "langchain_community.document_loaders.parsers.images",
     "TesseractBlobParser": "langchain_community.document_loaders.parsers.images",
     "VsdxParser": "langchain_community.document_loaders.parsers.vsdx",
+    "ZeroxPDFParser": "langchain_community.document_loaders.parsers.pdf",
 }
 
 
@@ -82,4 +84,5 @@ def __getattr__(name: str) -> Any:
     "RapidOCRBlobParser",
     "TesseractBlobParser",
     "VsdxParser",
+    "ZeroxPDFParser",
 ]