Add multi-provider generation chain with extractive fallback

Entity-aware retrieval for complex multi-character queries

Handle API errors: retry on 429/5xx with backoff + friendly messages

Polish chat UI: blend into page, soft theme, disclaimer footer

Pin gradio, add disclaimer, fix source dedup + mislabeled links

Prompt: lead with signature/BiS recommendation before caveats

Merge branch 'main' of https://huggingface.co/spaces/42Cummer/Paimon.AI

Update README.md

initial commit

Add embedding vectors for Space deployment

Add Gradio chatbot app (CPU Space, no ZeroGPU)

Add ask CLI: retrieve + rerank + generate in one command

Add optional cross-encoder reranker over hybrid candidates

Close retrieval gap: hybrid search + suitability reasoning

Add RAG generation via HF Inference Providers

Add incremental diff-update pipeline

Split chunk taxonomy into topic + format for intuitive filtering

Untrack re-embedded vectors after transfer

add embedding vectors

Clean nav-label noise from chunks + add Qdrant store/retriever

Untrack embedding vectors after transfer

add embedding vectors

Add embedding build artifact + model presets

Add embedding verification harness

Add phase 2 embedding: model downloader + bge-large embedder

Add phase 2 chunker: embedding-ready RAG chunks

Add phase 1 theorycrafting scraper + dataset

Update README.md

Initial commit