Tender Summarizer
Auto Summarizer and key extractor of Tendor Documents
Timeline
17 Hours
Role
Backend Developer
Team
Piyush Dhoka, Varun Inamdar, Aadarsh Pathre
Status
CompletedTechnology Stack
Key Challenges
- Model Accuracy
- Database Integration
- Real-time Operations
Key Learnings
- Model Building
- Server Architecture
- Database Operations
Overview
Orchestrated an NLP pipeline utilizing Transformers, NER, and advanced text preprocessing techniques to extract key entities from tender PDFs, yielding structured outputs.Deployed and integrated the solution into company workflow, significantly reducing manual review time and improving efficiency
Key Features
Tools I've Implemented
PDF Processing Pipeline: Upload and preprocess complex tender PDFs for automated analysis.
Automated NLP Summarization: Leverage a Transformer-based pipeline to generate concise, accurate summaries of lengthy documents.
Key Insight Extraction: Utilize Named Entity Recognition (NER) and advanced text processing to pull out crucial data points and key entities.
Structured Data Output: Export extracted insights and summaries into structured formats (like JSON) for easy integration and review.
Flask API Integration: Deploy the NLP model via a Flask API, allowing seamless integration into company workflows to boost efficiency.
Reduced Manual Review: Designed the end-to-end solution to significantly cut down on manual review time and improve productivity.