static demo — simulated responses
⚡ This is a static demo running in-browser. Responses are simulated from the actual model outputs. The live API (FastAPI + Llama 3.1 8B) runs locally or on Azure — see the GitHub repo to run it yourself.

Ask your fine-tuned model

Llama 3.1 8B · QLoRA exp2_lr2e-4_r16 · RTX 3060 · 4-bit NF4 · Pinecone RAG

● Retrieval-augmented · semantic search over Genshin corpus
try these
What weapons should Hu Tao use on a budget?
How did Venti become the Anemo Archon?
Compare Zhongli and Ei's ruling philosophies
How does the Vaporize reaction work?
What is Scaramouche's backstory?
Best team comp for Ayaka?
query
top_k retrieved chunks
response
—
sources