Smart text chunker for LLM preprocessing (sections → paragraphs → sentences → hard splits).
-
Updated
Dec 7, 2025 - Python
Smart text chunker for LLM preprocessing (sections → paragraphs → sentences → hard splits).
A simple RAG project to fetch answers from Wikipedia/Research papers
This is a comprehensive Retrieval-Augmented Generation (RAG) system built with Gemini 2.5 Flash and Qdrant. It features a modular multi-page Streamlit interface for seamless configuration, document ingestion, and intelligent chatting.
A robust, production-grade pipeline converting complex Medical PDFs into structured, RAG-ready JSONL datasets. Features smart table merging, multimodal extraction, and dynamic layout analysis using Detectron2 & PaddleOCR.
Add a description, image, and links to the rag-pipelines topic page so that developers can more easily learn about it.
To associate your repository with the rag-pipelines topic, visit your repo's landing page and select "manage topics."