---
title: Movie recommender 
emoji: 🌖
colorFrom: pink
colorTo: gray
sdk: docker
pinned: false
---
## Movie recommender (RAG and Chainlit demo)
This movie recommender is a demo of RAG using Chainlit.

Run the demo: https://huggingface.co/spaces/key2xanadu/chainlit-movie-rag

Demo screenshot:

![Demo screenshot](screenshot.png "Demo screenshot")

Code files: https://huggingface.co/spaces/key2xanadu/chainlit-movie-rag/tree/main

Next steps / ideas:
 * Use more caching. For example, load the vector store instead of creating a new one.
   (try downloading the files created in co-lab session)
 * Download the files from your notebook and store them in your Chainlit repo so you won't be recreating them every time you run the notebook (which will be a lot faster). 
 * Get FAISS working on local files [see reference](https://python.langchain.com/v0.1/docs/integrations/vectorstores/faiss/#saving-and-loading)