TravelMate
Generative AI / RAG / Final Year Project
An AI-powered travel assistant developed as the final year project for a BS in Data Science — combining retrieval over travel knowledge with generative planning to answer destination and itinerary questions.
- Year
- 2025
- Role
- Final year project — FAST NUCES
- Source
- Public repository
Technologies
- Python
- LLMs
- RAG
- Vector Search
- AI Assistant
The problem
Trip planning is a research task spread across a dozen tabs. A general chatbot answers confidently but without grounding, which is exactly the wrong failure mode when someone is about to book something.
The solution
A retrieval-augmented assistant: relevant travel content is retrieved first, and generation is conditioned on what was retrieved, so answers stay tied to actual source material rather than model recall.
Architecture
How it is put together.
Knowledge ingestion
Travel content is collected, chunked and embedded into a vector store.
Retrieval
A user question retrieves the most relevant passages.
Grounded generation
The language model answers conditioned on retrieved context.
Itinerary assembly
Multi-part answers are composed into a usable plan.
Key features
What it actually does.
- Retrieval-augmented answering over travel knowledge
- Conversational destination and planning queries
- Itinerary generation from grounded context
Engineering challenges
The parts that were hard.
Retrieval quality caps answer quality
Weak retrieval produces confident nonsense. Chunking and embedding choices mattered more than prompt wording.
Travel data goes stale
Prices and schedules change, so the assistant is framed around planning guidance rather than live booking facts.
Outcomes
What came out of it.
Qualitative outcomes only — no invented benchmarks or metrics.
A complete RAG application delivered as a final year project
Grounded answers traceable to retrieved source content
Next project
Minimum Viable Product Set
Reduced a catalogue of nearly 6,000 SKUs to 20 essential products for a lean launch.
Let’s build
Want something like this for your business?
Tell me the problem and I will come back with an architecture, a scope and a timeline.