Building a retrieval API to search my Obsidian vault from LibreChatlaurentcazanove.com1 points·by Strift·10 bulan yang lalu·0 comments
Building the future of search with Meilisearch AImeilisearch.com3 points·by Strift·tahun lalu·0 comments
Building a Next.js Shopify Storefront with Blazityblog.meilisearch.com2 points·by Strift·2 tahun yang lalu·0 comments
Results at keystroke speed: inside a full-text search engineblog.meilisearch.com4 points·by Strift·2 tahun yang lalu·0 comments
Vector storage is coming to Meilisearch to empower search through AIblog.meilisearch.com6 points·by Strift·3 tahun yang lalu·0 comments
Nine Reasons Why Postgres Might Not Be Good Enough for Full Text Searchblog.meilisearch.com5 points·by Strift·3 tahun yang lalu·0 comments
Adding site search to your Nuxt ecommerceblog.meilisearch.com3 points·by Strift·3 tahun yang lalu·0 comments
Strift·6 bulan yang lalu·discussI just use a web server and a search engine.TL;DR: - chunk files, index chunks - vector/hybrid search over the index - node app to handle requests (was the quickest to implement, LLMs understand OpenAPI well)I wrote about it here: https://laurentcazanove.com/blog/obsidian-rag-api
Strift·2 tahun yang lalu·discussI hate how slow the docs have become. Fwiw, we're working on fixing it :p
TL;DR: - chunk files, index chunks - vector/hybrid search over the index - node app to handle requests (was the quickest to implement, LLMs understand OpenAPI well)
I wrote about it here: https://laurentcazanove.com/blog/obsidian-rag-api