Skip to content
Snippets Groups Projects
Unverified Commit b730fb67 authored by Sourabh Desai's avatar Sourabh Desai Committed by GitHub
Browse files

fix PDFReader for remote fs (#12186)

parent acead0c5
No related branches found
No related tags found
No related merge requests found
...@@ -53,7 +53,7 @@ class PDFReader(BaseReader): ...@@ -53,7 +53,7 @@ class PDFReader(BaseReader):
# This block returns a whole PDF as a single Document # This block returns a whole PDF as a single Document
if self.return_full_document: if self.return_full_document:
text = "" text = ""
metadata = {"file_name": fp.name} metadata = {"file_name": file.name}
for page in range(num_pages): for page in range(num_pages):
# Extract the text from the page # Extract the text from the page
...@@ -71,7 +71,7 @@ class PDFReader(BaseReader): ...@@ -71,7 +71,7 @@ class PDFReader(BaseReader):
page_text = pdf.pages[page].extract_text() page_text = pdf.pages[page].extract_text()
page_label = pdf.page_labels[page] page_label = pdf.page_labels[page]
metadata = {"page_label": page_label, "file_name": fp.name} metadata = {"page_label": page_label, "file_name": file.name}
if extra_info is not None: if extra_info is not None:
metadata.update(extra_info) metadata.update(extra_info)
......
...@@ -50,7 +50,7 @@ license = "MIT" ...@@ -50,7 +50,7 @@ license = "MIT"
maintainers = ["FarisHijazi", "Haowjy", "ephe-meral", "hursh-desai", "iamarunbrahma", "jon-chuang", "mmaatouk", "ravi03071991", "sangwongenip", "thejessezhang"] maintainers = ["FarisHijazi", "Haowjy", "ephe-meral", "hursh-desai", "iamarunbrahma", "jon-chuang", "mmaatouk", "ravi03071991", "sangwongenip", "thejessezhang"]
name = "llama-index-readers-file" name = "llama-index-readers-file"
readme = "README.md" readme = "README.md"
version = "0.1.11" version = "0.1.12"
[tool.poetry.dependencies] [tool.poetry.dependencies]
python = ">=3.8.1,<4.0" python = ">=3.8.1,<4.0"
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment