Build your own no-code virtual chat assistant, fully local and open source!

[@fredkzk]

Played with RAG a bit, quite nice. Now looking for a similar solution that generates pair-completion pairs in flat json from MD or TXT files, for prompt augmentation (fine tuning) purposes. Retrieval does not meet 100% my need.

[@simple-rick-tutorials]

Cool, I haven’t been brave enough to try fine tuning yet. If you ever want to come on the channel and give a demo that’d be awesome 🤩

[@sebastian-kra]

nice video!, how can i get the file name of the document used for context?, 'metadata'

[@simple-rick-tutorials]

Normally the “extract from file” node in n8n should give you plenty of metadata, certainly it does for pdfs. Though strangely I didn’t find the file name in the metadata of my pdf either. The secondary option would be to pass it through a code node to add the name of the binary file to the output json.

[@takimdigital3421]

Hi i use google drive and all googles nodes in my localhost .

[@simple-rick-tutorials]

That’s awesome, how the heck did you get the OAuth to work? It didn’t like my redirect URI and I could only run it in test mode, which isn’t a huge deal but just curious how you did it?

[@takimdigital3421]

@@simple-rick-tutorials i found a vidéo that explain This i cant write all the steps , a tips you do not have to do the same for all other Google nodes . You can use the same id , just have to activate the api you want in the same project you created .
th-cam.com/video/pWGXlZBGu4k/w-d-xo.htmlsi=uhRp86OoLa1VIIJB

[@FactScriber]

no volume?

[@FactScriber]

never mind sorted it on my end

[@simple-rick-tutorials]

I can hear it ok. I’ll get some video editing software one day, you’ll see! Until then, it’s au naturel all the way