I 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年前·讨论

I hate how slow the docs have become. Fwiw, we're working on fixing it :p

Strift

提交

Show HN: Semantic search for MTG

Building a retrieval API to search my Obsidian vault from LibreChat

Building the future of search with Meilisearch AI

Building a Next.js Shopify Storefront with Blazity

Meilisearch 1.9

Nuxt releases icon module v1

Results at keystroke speed: inside a full-text search engine

Minimal Auth module for Nuxt 3

[untitled]

Laravel Sail add support for Bun

Vector storage is coming to Meilisearch to empower search through AI

Nine Reasons Why Postgres Might Not Be Good Enough for Full Text Search

评论