tv.algora.io• May 2, 2024• 1 min read
Show HN: I built vector search for COSS podcasts & livestreamsHey HN! I built COSSgpt using videos from the Open Source Founder Podcast [1] and livestreams from COSS Office Hours [2][3]I transcribed the VODs using Whisper and vectorized fixed-size segments from the transcripts with MPNet on Replicate GPUs. I made these segments overlap a little to prevent semantic meaning being lost inbetween segmentsThen I indexed the vectors using HNSWLib in-memory vectorstore [4] and persisted the entire vectorstore into Tigris object storage [5] to cache multimedia and vectors across all Fly.io regionsI built the app in Elixir, almost entirely server-side rendered with minimal diffs sent to the client over WebSockets using Phoenix LiveView. I also used Livebook [6] a ton when I was building the multimedia processing & ML pipeline. I'm super bullish on Elixir for building webapps and/or MLops!Let me know what you think :) If you're curious you can find the code at https://github.com/algora-io/tv[1]: https://algora.io/podcast [2]: https://tv.algora.io/peerrich