feat: add retry on pypdf (#12848)

* feat: add retry on pypdf

* chore: correct version

* chore: remove exponential

llama-index-integrations/readers/llama-index-readers-file/llama_index/readers/file/docs/base.py

@@ -11,13 +11,18 @@
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
+from tenacity import retry, stop_after_attempt
+
 from fsspec import AbstractFileSystem
+
 from llama_index.core.readers.base import BaseReader
 from llama_index.core.readers.file.base import get_default_fs, is_default_fs
 from llama_index.core.schema import Document
 
 logger = logging.getLogger(__name__)
 
+RETRY_TIMES = 3
+
 
 class PDFReader(BaseReader):
     """PDF parser."""
@@ -28,6 +33,9 @@ def __init__(self, return_full_document: Optional[bool] = False) -> None:
         """
         self.return_full_document = return_full_document
 
+    @retry(
+        stop=stop_after_attempt(RETRY_TIMES),
+    )
     def load_data(
         self,
         file: Path,

llama-index-integrations/readers/llama-index-readers-file/pyproject.toml

@@ -50,7 +50,7 @@ license = "MIT"
 maintainers = ["FarisHijazi", "Haowjy", "ephe-meral", "hursh-desai", "iamarunbrahma", "jon-chuang", "mmaatouk", "ravi03071991", "sangwongenip", "thejessezhang"]
 name = "llama-index-readers-file"
 readme = "README.md"
-version = "0.1.18"
+version = "0.1.19"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"