The community member is experiencing an issue with the SimpleDirectoryReader from the llama_index.core library when trying to load a PDF file. The error message is not clear on the missing dependency, and the community member is unsure if it's a Linux or Python issue. Another community member, @dosu, provided the solution, which was to install the pymupdf and pdfminer.six dependencies.
Hi - SimpleDirectoryReader error message not very clear on what dependency is missing.
When using SimpleDirectoryReader to load a PDF file, I'm getting a dependency error but not sure if is for Linux or Python. Has anyone seen this before?
from llama_index.core import SimpleDirectoryReader
loader = SimpleDirectoryReader(input_dir="./data")
documents = loader.load_data()
Failed to load file /home/ubuntu/.../data/digital-piano.pdf with error: RetryError[<Future at 0x... state=finished raised DependencyError