mindforger VS Joplin

Rear is a really interesting project with admirable goals. I believe this is just the beginning, but you have already done a great job!

I have been working on my note-taking application (https://github.com/dvorka/mindforger) for some time and wanted to go in the same direction. However, I gave up (for now). I used ggerganov/llama.cpp to host LLM models locally on a CPU-only machine with 32GB RAM, and used them for both RAG and note-taking use cases (like https://www.mindforger.com/index-200.html#llm). However, it did not work well for me - the performance was poor (high hardware utilization, long response times, failures, and crashes) and the actual responses were rarely useful (off-topic and impractical responses, hallucinations). I tried llama-2 7B with 4b quantization and a couple of similar models. Although I'm not happy about it, I switched to an online commercial LLM because it performs really well in terms of response quality, speed, and affordability. I frequently use the integrated LLM in my note-taking app as it can be used for many things.

Anyway, Reor "only" uses the locally hosted LLM in the generation phase of the RAG, which is a nicely constraint use case. I believe that a really lightweight LLM - I'm thinking about a tiny base model fine-tuned for summarization - could be the way to go (fast, non-hallucinating). I'm really curious to know if you have any suggestions or if you will have any in the future!

As for the vector DB, considering the resource-related problems I mentioned earlier, I was thinking about something similar to facebookresearch/faiss, which, unlike LanceDB, is not a fully-fledged vector DB. Have you made any experiments with similarity search projects or vector DBs? I would be interested in the trade-offs similar to small/large/hosted LLMs.

Overall, I think that both RAG with my personal notes as a corpus and a locally hosted generic purpose LLM for the use cases I mentioned above can take personal note-taking apps to a new level. This is the way! ;)

Good luck with your project!

Please share your suggestions, ideas or constructive criticism! You may install or update from GitHubreleases or PPA.

I finally managed to complete new MindForger release:

https://www.mindforger.com/NimbusnoteWikidpadBecause you mentioned writing:

Neat, the Similarity type reminds me of MindForger's Associations feature that also displays similarity scores between your current note and other existing notes

[Mindfrogger](https://github.com/dvorka/mindforger)

Mindforger: https://github.com/dvorka/mindforger/

I've had great success with using Joplin for this, with Syncthing as a sync backend. Works well across OSes; I use it on Linux, macOS, Windows and Android.

https://joplinapp.org/

The tools to manipulate SQL aren't that bad, no.

But rather than having a self explanatory markdown & flat file, now I have to start learning about the schema & making specific tools (in my preferred language) for manipulating Joplin's schema.

Suddenly I'm digging through 20 different technic specs to decode what data is where, how it works, and what I can do to it. Want to edit history? This is the best help you'll get, pray it's adequately technical to expedite you to your purpose: https://github.com/laurent22/joplin/blob/dev/readme/dev/spec...

As I began with, I struggle to imagine anything that generates anywhere near as much user agency as flat files and markdown. Having boring common data & systems lets me apply portable skills I already have, rather than having to skill up in some particular product's own ecosystem.

Joplin is a good open source option too, feels more like the original Evernote in terms of UI/UX https://github.com/laurent22/joplin/

Joplin, an open source, extendable, Markdown-based hierarchical note-taking app: https://joplinapp.org/

It lets you choose a synchronization backend, offers applications for every major desktop and mobile OS (also has a terminal version). You can create notebooks and subnotebooks to organize your notes. You can also add tags for better search experience. I created notebooks for specific domains (work-related, home improvement, etc.) and also keep a "temp" for quick notes and W.I.P. snippets.

Its only con that it uses Electron on desktop which causes relatively slow start of the application.

done