Loading pdf files from directory gives the following error

[Kashif-Raza6]

System Info

0.0.160

Who can help?

No response

Information

• [ ] The official example notebooks/scripts
• [ ] My own modified scripts

Related Components

• [ ] LLMs/Chat Models
• [ ] Embedding Models
• [ ] Prompts / Prompt Templates / Prompt Selectors
• [ ] Output Parsers
• [X] Document Loaders
• [ ] Vector Stores / Retrievers
• [ ] Memory
• [ ] Agents / Agent Executors
• [ ] Tools / Toolkits
• [ ] Chains
• [ ] Callbacks/Tracing
• [ ] Async

Reproduction

from langchain.document_loaders import DirectoryLoader loader = DirectoryLoader('data', glob="**/*.pdf") docs = loader.load() len(docs) error: cannot import name 'open_filename' from 'pdfminer.utils'

Expected behavior

load the pdf files from directory

[rajib76]

I also faced the same issue and for now I bumped down unstructured to 0.6.1

[Kashif-Raza6]

Finally I was able to solve this issue. Pdfminer is last updated in 2019. It work on python 3.7 , 3.8 and 3.9. When I run switch from 3.10 to 3.9 it start working.