SARVANDANI - Text and PDF analysis

Sentiment Analysis • Named Entity Recognition • Text Classification • Summarization

Ready to Analyze?

Upload a PDF or enter text to get started with AI-powered NLP analysis

About This Project

This application uses advanced Natural Language Processing (NLP) models to analyze text and PDF documents. The system provides sentiment analysis, named entity recognition, text classification, and summarization using lightweight, fast-running models optimized for local inference.

How It Works

1

Upload or Enter Text

Upload a PDF file or enter text directly through our intuitive interface. The system accepts PDF files and plain text input.

2

Text Processing

The uploaded text is automatically processed and prepared for analysis. PDF files are extracted and converted to text format.

3

AI Analysis

Our trained NLP models analyze the text through multiple pipelines, extracting sentiment, entities, categories, and generating summaries.

4

Results & Insights

Get instant results with detailed insights including sentiment scores, named entities, text classification, and concise summaries.

Key Features

📊

Sentiment Analysis

Analyze text sentiment with confidence scores using DistilBERT

🏷️

Entity Recognition

Extract named entities like names, locations, organizations using spaCy

📝

Text Classification

Classify text into 30+ categories using DistilBERT zero-shot classification (fast and accurate)

✂️

Summarization

Generate concise summaries using DistilBART model

Fast Processing

Get results in seconds with lightweight, optimized models

📄

PDF Support

Upload and process PDF files directly with automatic text extraction

Technology Stack

Frontend

  • HTML5
  • CSS3
  • Vanilla JavaScript
  • Fetch API

Backend

  • FastAPI
  • Python
  • Uvicorn
  • PyPDF2

AI/ML

  • Transformers (Hugging Face) - Sentiment Analysis, Classification, Summarization
  • PyTorch - Deep Learning Framework
  • spaCy - Named Entity Recognition
  • DistilBERT - Sentiment Analysis & Text Classification (Primary)
  • DeBERTa-v3 - Text Classification (Fallback, Best Accuracy)
  • DistilBART - Text Summarization

⚠️ Important Disclaimer

This application is provided "as is" without any warranties or guarantees. The NLP models used are pre-trained and may not always produce 100% accurate results. Results are for informational purposes only and should not be used as the sole basis for important decisions.

The author is not responsible for any consequences arising from the use of this application.