Deepdoctection Loader
DeepdoctectionPDFLoader Class Documentation
Last updated
DeepdoctectionPDFLoader Class Documentation
Last updated
The DeepdoctectionPDFLoader
class is a powerful tool for loading academic document PDF files. It leverages the capabilities of the Deepdoctection model, developed by deepdoctection, to provide an accurate conversion of academic papers from PDF format.
You must run Deepdoctection API server for using this loader. You will need server with CUDA installed for running deepdoctection model properly. More detailed installation of deepdoctection, please go to .
First, clone NomaDamas/deepdoctection repository to your machine, and move to docker/NomaDamas-api-server folder.
Then, build and run your docker container following this .
First, clone NomaDamas/deepdoctection-api-server repository to your machine, and move to folder.
Then, run api server with this command.
After runs your Deepdoctection API server, you first need to create an instance by providing two parameters: file_path
and deepdoctection_host
.
file_path: This is a string representing the path to your PDF file.
deepdoctection_host: This is a string representing the host address where your Deepdoctection API server is running.
Example:
During initialization, it checks if it can establish a connection with the provided Deepdoctection server host. If it cannot establish a connection, it raises a ValueError.
The class provides two methods for loading documents: load()
and lazy_load()
.
Example:
or
These methods return instances of Document objects that contain processed content from your PDF file.