- Stream Notes
- Catch up
- Helped family move! Had to focus on that for a while
- Haven’t done much coding due to that and interview stuff
- Doing
- Since we kinda finished FastAPI, figured we could try out the Tencent Persona-Hub repo
- Trying to set up headless Raspberry Pi 3b+ to scrape websites again
- Had wanted to use Tencent’s Persona-Hub to play around with recipe query refinement, but need vector database
- Figured, if I need a vector database, I might as well start scraping again to add to the recipe database
- Tried to get Pi working off stream, no luck, it’s quite slow
- Seems like should just get Vespa to make the existing database, then add new recipes after
- This is probably fine/quickest action/result
- Where to store the embeddings?
- Vespa has documentation to upload embeddings in cloud, and instructions for running server locally
- Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
- From chat / derail
Socials
Related