Project 1: How AI Reads Pharmaceutical Documents

I explored Machine Learning, Deep Learning, and Natural Language Processing to understand how AI reads and processes pharmaceutical documents. I analyzed a real pharmaceutical documentation file, focusing on how AI models handle both structured and unstructured data, thereby establishing a solid

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 pharmaceutical SDFs. By applying field heuristics, I identified key data fields, contributing to Pfizer's compliance workflow by flagging outdated documents.

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

I built a Retrieval-Augmented Generation (RAG) pipeline using LlamaIndex to enhance AI's ability to retrieve relevant information from extensive document sets. This project improved my understanding of how to structure AI models for efficient data retrieval.

Project 7: Blob Processing, Classification, and Routing

I designed a modular system to process large, unstructured pharmaceutical PDFs, classifying and routing documents to appropriate extraction pipelines. My approach utilized layout-based clues and machine learning methods to identify various document types, reflecting real-world workflows.

Project 9: Final Integration, Testing, and Evaluation

I integrated all components into a comprehensive document intelligence system, testing its performance on full pharmaceutical SDF documents. I evaluated the system's accuracy and reliability, culminating in a professional demo that showcased its real-world potential.

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

I utilized Python for data processing, cleaning, and organizing pharmaceutical documents, ensuring they were ready for AI automation. My work included data preparation techniques to standardize information and enhance OCR accuracy through image processing, laying the groundwork for effective

Project 4: Advanced OCR Comparison and Layout-Aware Extraction

I compared three OCR engines—Tesseract, PaddleOCR, and EasyOCR—on their performance with scanned pharmaceutical documents. I learned to clean and extract text from PDFs, explored layout-aware tools, and made recommendations for the most effective OCR solution based on technical and business needs.

Project 6: Advanced RAG and Open-Source Experiments

I advanced my RAG pipeline by implementing techniques for improved precision and experimenting with open-source LLMs. I explored advanced chunking methods and metadata-based filtering, optimizing the pipeline for pharmaceutical documents and justifying design decisions based on retrieval accuracy.

Project 8: Gradio Chatbot with RAG Integration

I developed an interactive chatbot using Gradio to interface with my local RAG pipeline. This project involved modularizing my code to facilitate user interactions through a web-based interface, allowing users to query documents effectively.