In this project, you’ll use a mix of AI tools to uncover major themes in employee feedback and dig into the root causes behind key frustrations. You’ll visualize how sentiment varies by theme and map out cause-effect patterns, just like consultants do when turning noise into strategy.

[Week] 5-6

Before AI can process documents, it must first understand them. In this project, you'll explore Machine Learning, Deep Learning, LLMs, and NLP to see how AI reads and processes text. You'll also dive into Computer Vision and OCR, learning how AI extracts information from scanned documents. Finally, you'll work with a real pharmaceutical documentation file, analyzing how AI models handle structured and unstructured data. By the end, you'll have a strong AI foundation and a clear understanding of how AI improves document processing in the pharmaceutical industry.

AI models require clean, structured data to function effectively. In this project, you'll learn how to use Python for data processing, cleaning, and organizing pharmaceutical documents to prepare them for AI automation. You'll begin by exploring Google Colab and learning Python basics. Then, you'll dive into data preparation techniques to clean and standardize information. Finally, you'll work with image processing to enhance OCR (Optical Character Recognition) accuracy. By the end of this project, you'll be able to prepare pharmaceutical data for AI models, ensuring accurate and efficient document intelligence.

Before AI can make sense of documents, it needs clean, structured data. In this project, you'll learn how to turn digital PDFs into machine-readable formats using Python. You'll explore tools like PyMuPDF and pdfplumber to extract text from multi-page pharmaceutical SDFs. Then, you'll apply field heuristics—like regex patterns, anchor phrases, and layout clues—to identify key fields such as dates (manufacturing, effective, revision), vendor names, and document types. This is the foundation for Pfizer's compliance workflow: flagging documents that are more than 3-4 years old.

OCR (Optical Character Recognition) is at the heart of document intelligence. In this project, you’ll get hands-on with three OCR engines—Tesseract, PaddleOCR, and EasyOCR—to see how they perform on scanned pharmaceutical supplier documentation (SDFs). You'll start by learning how to clean and extract text from scanned PDFs using Tesseract. Then, you'll explore layout-aware tools that better preserve formatting and structure. Finally, you'll run comparisons and recommend the most effective tool for real-world automation. By the end, you'll be able to confidently select and justify OCR tools based on both technical and business needs.

AI models can process vast amounts of text, but finding the right information quickly is a challenge. In this project, you’ll learn how to build a Retrieval-Augmented Generation (RAG) pipeline using LlamaIndex to help AI retrieve relevant data from large document sets.

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.

Pharmaceutical regulatory files often arrive as large, unstructured PDFs containing multiple document types. In this project, you'll design a system to split these files into individual documents, classify each one, and route them to the appropriate extraction pipeline. You'll use layout-based clues, rule-based methods, or simple machine learning to identify documents like SDFs, vendor certificates, and compliance forms. By the end, you'll have created a modular system that mirrors real-world pharmaceutical document workflows.

In this module, you'll learn how to turn your local RAG pipeline into an interactive chatbot using Gradio. Instead of running queries in a notebook cell, users can ask questions through a clean web-based UI — just like ChatGPT. You'll split your code into two functions: one that builds the Gradio interface, and one that handles user prompts by sending them through your retrieval engine and LLM. This structure not only helps modularize your pipeline, but also makes it easy to plug in different models — including Gemini, Mistral, Phi-2, or any LLM of your choice. By the end, you'll have a working local chatbot that can answer questions about a PDF document.