UnstructuredPDFLoader - No module named 'pdf2image'

[Magnuti]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

# main.py
from langchain_community.document_loaders import UnstructuredPDFLoader
loader = UnstructuredPDFLoader("example.pdf")
docs = loader.load()

pip install -U langchain-community unstructured
python3 main.py

Error Message and Stack Trace (if applicable)

File "/Users/.../env/lib/python3.13/site-packages/unstructured/partition/pdf.py", line 25, in <module> import pdf2image
ModuleNotFoundError: No module named 'pdf2image'

Description

I follow this guide on UnstructuredPDFLoader.

I am trying to use UnstructuredPDFLoader but .load() throws the ModuleNotFoundError: No module named 'pdf2image' error.

Expected: Running python3 main.py should work.

Actual: ModuleNotFoundError: No module named 'pdf2image'

System Info

Python: 3.13.0
langchain-community==0.3.14
unstructured==0.11.8

[ccurme]

You likely need to install "unstructured[pdf]".

I'd suggest using the langchain-unstructured package, as dependencies are managed there (vs. the community integration, which requires separate pip installs).