AI-powered document classification system built using FastAPI, Machine Learning, scikit-learn, NLP, and Streamlit. The application extracts text from uploaded PDF documents, preprocesses the content using NLP techniques, converts text into TF-IDF vectors, and predicts document such as invoices, orders and reports using a ML classification model.
machine-learning natural-language-processing logistic-regression document-classification rest-apis text-preprocessing fastapi pdf-text-extraction tf-idf-vectorization file-upload-handling model-training-inference
-
Updated
May 26, 2026 - Python