Project 1: How AI Reads Pharmaceutical Documents

I analyzed how AI interprets pharmaceutical documents by examining specific documentation files. This assessment provided insights into AI's performance with both structured and unstructured data, leading to enhanced efficiency in document processing.

Project 3: Data Extraction from Documents Using Python

I transformed digital PDFs into machine-readable formats using Python, employing tools like PyMuPDF and pdfplumber to extract text from multi-page pharmaceutical SDFs. I applied regex patterns and layout clues to identify key fields essential for compliance.

Project 5: Introduction to Retrieval-Augmented Generation (RAG)

I built a Retrieval-Augmented Generation (RAG) pipeline using LlamaIndex to enhance AI's capability to retrieve relevant data from large document sets. This project addressed the challenge of efficiently processing vast amounts of text.

Project 2: Learn to Work with Python for AI-Powered Document Processing

I utilized Python for data processing, cleaning, and organizing pharmaceutical documents, effectively preparing them for AI automation. My work in Google Colab enhanced my Python skills and contributed to improved OCR accuracy through data preparation techniques.

Project 4: Advanced OCR Comparison and Layout-Aware Extraction

I conducted a comparative analysis of three OCR engines—Tesseract, PaddleOCR, and EasyOCR—on scanned pharmaceutical documentation. This hands-on experience allowed me to clean and extract text from scanned PDFs while exploring layout-aware tools to preserve formatting.

Project 6: Advanced RAG and Open-Source Experiments

In this project, you’ll take your RAG pipeline to the next level by improving precision and experimenting with open-source LLMs. First, you’ll explore advanced chunking techniques—like overlapping and tuning—to improve document segmentation. Then, you’ll implement metadata-based filtering so your system retrieves more contextually relevant answers. You’ll also evaluate the performance of open-source models like Mistral and Phi-2 compared to proprietary options. By the end, you’ll have a fine-tuned, high-performing RAG pipeline optimized for real-world pharmaceutical documents and the ability to justify your design decisions based on retrieval accuracy and model efficiency.