With the simple idea of using the directory structure of a PDF file, I get the tree of section and traversed each section with the corresponding chunk text information, then inserted it into ES.
docker-compose up -d
python main.py
python search.py
-
Notifications
You must be signed in to change notification settings - Fork 1
zantetran/PDF_Parser2ES
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Get information from file PDF and insert all information into ElasticSearch
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published