Source description
About the role
About the program Completed a 7week 45day internship focused on developing an Intelligent Chat with Your PDF system using RetrievalAugmented Generation RAG architecture. The project enabled users to upload PDF documents and interact with them through a conversational AI interface that provides contextaware and accurate responses. Key responsibilities included: Understanding and implementing the RAG architecture retriever + generator pipeline Extracting and preprocessing text from PDF documents Text chunking and embedding generation using transformerbased models Storing embeddings in a vector database for efficient similarity search Implementing semantic search to retrieve relevant document sections Integrating Large Language Models LLMs for contextbased response generation Designing a userfriendly chat interface Evaluating response accuracy, relevance, and latency Optimizing retrieval performance and reducing hallucinations The final system allowed users to query large PDF documents and receive precise, sourcegrounded answers in real time. Perks Hands-on experience with advanced AI concepts like RAG and LLM integration Practical exposure to vector databases and semantic search Deep understanding of Natural Language Processing (NLP) workflows Experience working with embeddings and transformer models Improved problem-solving and system design skills Internship completion certificate Mentorship and real-world AI project development experience Who can apply? Only those candidates can apply who: are from Any and specialisation from Any are available for duration of 7 Weeks have relevant skills and interests Terms of Engagement Duration: 7 weeks (45 days) Confidentiality: Required adherence to data privacy and document security policies Deliverables: Weekly progress reports and final system demonstration Evaluation: Based on implementation quality, retrieval accuracy, system performance, and presentation Number of openings 8
More at Doneswari Technologies LLP