Assessfy Pvt. Ltd Moderate 5 milestones 100 marks

RAG-Powered Documentation Chatbot for SME Customer Support

Target year: TE Sem 5-6 (Mini-Project-IIA/IIB) AICTE: 3 credits · ~75 hrs Bloom: Analyze / Create MU CBCS: CSC602/CSC702 Mini-Project 2A/2B Powered by: AI Products Factory

Real-world project · AICTE-aligned · AI-graded · Audit-ready certificate

5
Milestones
0
Available mentors
0
Enrolled students
7
Core skills
About this project

Build a Retrieval-Augmented Generation (RAG) chatbot that answers user questions by retrieving relevant chunks from a company's documentation (PDFs, web pages, FAQs) and synthesizing an answer using an LLM. Includes evaluation harness for answer faithfulness + grounding. This is AI Products Factory's bread-and-butter offering for SME consulting projects.

Course Learning Outcomes (CLOs):
CLO1: Apply document chunking + embedding strategies for retrieval.
CLO2: Build a vector index and query layer.
CLO3: Design grounded prompts that cite source documents.
CLO4: Evaluate RAG answer quality using faithfulness + relevance metrics.
CLO5: Communicate engineering tradeoffs (recall vs cost vs latency).

Industry/societal relevance: AI Products Factory builds custom AI for SMEs + governments. Every SME wants "ChatGPT for our docs" — this project is the exact template you sell. Direct portfolio entry for AI-engineer / ML-engineer roles.

Milestones
1. Doc Corpus + Chunking
15 marks 10d
Pick a real SME doc set (use Assessfy own docs or open dataset). Chunk into 500-token windows. Document strategy.
2. Embeddings + Vector Index
20 marks 14d
Compute embeddings via sentence-transformers (or OpenAI). Build ChromaDB index. Verify nearest-neighbor on sample queries.
3. LLM Answer Synthesis
25 marks 18d
Build prompt: "Given these snippets, answer the question. Cite sources." Test on 20 queries.
4. Eval Harness
20 marks 14d
Implement faithfulness + answer-relevance scoring. Compare top-K=3 vs 5 vs 10. Report table.
5. Streamlit UI + Demo
20 marks 19d
Chat UI showing answers with source citations. Demo on 10 queries. 8-page report.
Open internships using this project -->
Open internships using this project 1

Verified companies are actively hiring interns to work on this exact project. Apply directly.

RAG-Powered Documentation Chatbot for SME Customer Support
AI Products Factory · Remote · 12w
Certificate of Completion 2 of 2 seats

Build a reusable RAG SDK that we deploy across SME client projects. You will design the retrieval + grounded-generation layer: document chunking, embedding (...

Skills you'll learn
PythonLangChain or LlamaIndexVector databases (ChromaDB / Pinecone / FAISS)Embedding models (text-embedding-3 / sentence-transformers)LLM APIs (OpenAI / Anthropic)Prompt engineeringRAG evaluation (faithfulness + recall)
Tools used
Python 3.11LangChainChromaDB or FAISSAnthropic Claude API (or OpenAI)StreamlitPyMuPDF for PDF parsingGitHub
Prerequisites
Python intermediate; basic understanding of embeddings + similarity search; willingness to read LangChain docs
Available mentors

No mentors have signed up for this project yet.

Be the first to mentor
Share
You'll earn — Certificate (PDF)

AICTE-aligned Project Completion Certificate

A formal, audit-ready PDF certificate issued by Assessfy + your institute on successful completion. Includes AICTE credit hours, your evaluator's signature, and a QR code for third-party verification.

Certificate of Project Completion

This is to certify that

has successfully completed the project

RAG-Powered Documentation Chatbot for SME Customer Support

Auto-issued on completion QR-verifiable
You'll earn — Digital Badge

Shareable LinkedIn / Resume Skill Badge

A compact, verifiable Open-Badges-2.0-compliant digital credential. Add to your LinkedIn profile, GitHub README, or resume in one click. Recruiters can validate authenticity via a unique URL.

Moderate
RAG-Powered Documentation Chatbot for…
Assessfy
Auto-issued on completion One-click LinkedIn add

Similar Projects you might like

Hand-picked by the recommender from your program & skill area.

Relevant Certifications to boost your application

From the Assessfy Certification library — take one and add it to your resume / LinkedIn before applying.

100 marks AICTE 3cr
Sign up & enroll