My internship at Aunwesha Knowledge Technologies was centered toward creating low-cost techniques for data extraction and analysis from CAD files. My main duties were as follows: 1.Data Extraction: Data from AutoCAD files (.dwg and.pdf) was extracted using software like OCR.space, Aspose.CAD, Cloud OCR, and Cloudmersive. Overcame difficulties handling files more than 5 MB by investigating effective data management techniques. 2.Java Application Development: Using Apache Lucene, a Java application was created to offer document search features. Developed SimpleSearcher.java to run search queries and SimpleFileIndexer.java for text extraction and indexing. 3.Problem Solving: Recognized and fixed problems with data extraction, including missing company names, improper data arrangement, and challenges with extracting slanted or vertical text from PDFs. 4.Data Export: To guarantee smooth data integration and display, all file names, sizes, and creation dates were gathered and exported to Excel. 5.GUI Development: To make data extraction from DWG files easier, a graphical user interface (GUI) was designed. Issues with Maven builds and missing dependencies were resolved to produce a functioning and user-friendly interface.During my internship, I gained hands-on experience in data processing, GUI programming, and search tool creation.