Design and implement a dynamic pipeline that processes multiple PDF documents from a single domain in a desktop folder, generates domain-specific summaries and keywords, and stores them in a MongoDB database. The system must efficiently handle documents of varying lengths, from short to long, and update the database with summary and keyword data after each document is processed.
-
Notifications
You must be signed in to change notification settings - Fork 0
NilotpalMaitra/Domain-Specific-PDF-Summarization-Keyword-Extraction-Pipeline
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Domain-Specific PDF Summarization & Keyword Extraction Pipeline using MongoDB database
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published