Home / Projects / Document RAG assistant
Year 3 · AI/ML Engineering
Document RAGassistant
Build a document question-answering assistant using retrieval-augmented generation. Ingest your documents, retrieve relevant information and generate accurate answers with source citations.
- Python
- RAG
- Vector Search
- LLMs
Illustrative demo data. Not real student work.
- Documents
- Knowledge base
- Chat history
Recent
- Eligibility criteria
- Program structure
- Career directions
- Application process
What are the eligibility criteria for the AI/ML Engineering program?
Based on the provided document, the AI/ML Engineering program is open to students from Class 11 onwards, with basic school-level mathematics and computer familiarity. [1] [2] [3]
Sources
- 1Admissions_Guide.pdfPage 4 · Eligibility criteria
- 2Program_Structure.pdfPage 2 · Overview
- 3FAQs.pdfPage 1 · General requirements
How it works
From documents
to grounded answers.
The assistant combines your documents with a language model to find relevant information and generate accurate, well-cited answers.
- 01Upload documentsAdd PDFs, docs or text files to your knowledge base.
- 02Split into chunksBreak documents into smaller passages for better retrieval.
- 03Retrieve relevant passagesFind the most relevant chunks using vector search.
- 04Generate answerUse an LLM to generate a clear answer with source citations.
Project walkthrough
Inside the assistant.
Explore the interface, try example questions and see how the assistant finds relevant information and gives grounded answers with source citations.
- Documents
- Knowledge base
- Chat history
Recent
- Eligibility criteria
- Program structure
- Career directions
- Application process
What topics are covered in the AI/ML Engineering program?
The AI/ML Engineering program covers Python, mathematics for machine learning, classical machine learning, deep learning, generative AI and MLOps. Later years move into real-world projects and specialised modules. [1] [2] [3]
Sources
- 1Program_Structure.pdfPage 3 · Core modules
- 2Curriculum_year1.pdfPage 1 · Year 1 overview
- 3Curriculum_year2.pdfPage 2 · Advanced topics
- Python Fundamentals
- AI Fundamentals + Google AI Essentials
- Classical ML
- Time Series + Recommendation
- Generative AI Foundations
- MLOps I
Illustrative demo data
Technical architecture
How the system works.
A simple architecture that combines document processing, vector search and a large language model.
- DocumentsPDFs, docs, text files
- Text extractionExtract and clean text content
- Chunking & embeddingsSplit into passages and create embeddings
- Vector indexStore embeddings in a vector database
- RetrieverFind relevant passages
- LLM responseGenerate grounded answer
- Source citationsLink to original documents
Tools and technologies
Built with modern
AI tools.
Use widely adopted tools and frameworks to build a document assistant.
- PythonCore development
- Document parsingPDF, DOCX, TXT
- EmbeddingsText representations
- Vector searchSimilarity search
- LLMsAnswer generation
- API & UIBuild and deploy
Skills you practise
Gain practical skills.
Build real experience working with document understanding, retrieval systems and large language models.
- Document processing and text extraction
- Prompt and context assembly
- Designing effective retrieval pipelines
- Generating grounded responses with citations
- Working with embeddings and vector search
- Evaluation and testing
Part of a larger program
Part of the AI/ML
Engineering program.
This project is part of Year 3, where you work on advanced AI systems, real-world applications and a portfolio of projects.
Your next step
Ready to explore more projects?
Discover more hands-on projects from the AI/ML Engineering program and build a portfolio you can show.



