I explained how Large Language Models work, covering architecture, training stages, and attention mechanisms.

I prepared and cleaned pharmaceutical documents with Python in Google Colab, applied data-frame cleaning, JSON normalization, text standardization, and image preprocessing to improve OCR readiness.

I extracted text and bounding boxes from multi-page SDF PDFs using PyMuPDF, then identified and structured key fields like manufacture and expiration dates.

I compared Tesseract, PaddleOCR, and EasyOCR on a scanned pharmaceutical supplier PDF and documented their accuracy, confidence, and term detection.

I built and tuned a RAG pipeline for document retrieval using LlamaIndex and experimented with retrieval/reranking parameters.

I ran three RAG retrieval configurations against a sample SDF document, compared retrieved chunks and answers, and identified the best top_k setting.

I built a segmentation and classification pipeline that split large PDF blobs into page-level documents and assigned doc types and metadata for routing.

I built a Gradio-based chatbot UI and connected it to a local RAG pipeline for answering questions about uploaded PDFs.