A Python-based AI platform for analyzing large text corpora using modern NLP techniques.
Supports semantic search, summarization, and document-grounded chat workflows — powered by Hugging Face models and FastAPI, with a Streamlit UI.
- 📄 Document Upload: Upload and index
.txtfiles. - 🔍 Semantic Search: Vector-based retrieval using embeddings.
- 🧠 Summarization: Single and multi-document summarization.
- 💬 Chat With Documents: RAG-style document-grounded Q&A.
- ⬇ Download Originals: Retrieve uploaded documents.
- 🛠 REST API Endpoints: FastAPI backend with auto docs (
/docs).
- 🖥 Streamlit Frontend: Simple interface for searching, uploading, and interacting with your documents.