Chatbot (LoRA + RAG)

RAG Chatbot Fine-Tuned with LoRA

Demo

Ask a question and get an answer grounded in the site content (with citations).

Click a quick prompt to submit it automatically, or type your own question in the chat box.
Press Enter or click “Send” to submit custom questions.
Use the citations in the response to jump to the referenced pages.
Bedrock is the default live backend; choose Qwen / SageMaker only when comparing cold-start behavior.

Crawled Visit Grand Junction pages, built a FAISS retrieval index, and generated a tourism-specific Q&A dataset with an open-source LLM through Ollama.
Fine-tuned a Mistral 7B/Qwen-style chatbot path with LoRA and deployed the custom model behind AWS SageMaker/Lambda for cold-start and model-control comparison.
Added a Bedrock backend as the default live path, keeping the same RAG/citation experience while providing faster always-available responses for the website demo.
The project now demonstrates both architectures: Bedrock as the practical live production path and LoRA/SageMaker as the custom fine-tuning path.
Viewers can compare managed-model reliability, streaming responses, and citation behavior against the custom model's cold-start and deployment tradeoffs.
The demo keeps source-grounded answers and citation links while making the model choice transparent through the backend selector.

Uses public Visit Grand Junction pages; retrieval provides citation links, and cold-start checks are part of the deployed demo.