Add unified indexing configuration -- detect file type based on mime type/extension

khoj-ai / khoj

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (e.g gpt, claude, gemini, llama, qwen, mistral).

https://khoj.dev

GNU Affero General Public License v3.0

14.75k stars 735 forks source link

Add unified indexing configuration -- detect file type based on mime type/extension #451

Closed sabaimran closed 1 year ago

sabaimran commented 1 year ago

We have several "types" of data that we index, but it's not necessary to force the user to specify which directories to look in for which files. Rather, we may just want to ask the user which directories they're interested in indexing, and in the back-end take care of indexing the relevant data.

sabaimran commented 1 year ago

With the new desktop client + Khoj server changes, it's now possible to simply select a folder and let the backend handle the process of determine how to parse it. Hence, I'm marking this as closed as another option exists.

Here are the instructions for installing the Desktop app: https://docs.khoj.dev/#/setup?id=_13-download-the-desktop-client-optional