|
01:08
leppard joined
01:13
hulk joined
01:14
kylese left
01:59
mehbark joined
02:15
hulk left,
kylese joined
03:17
lichtkind__ joined
03:20
lichtkind_ left
04:42
hurufu joined
06:31
Sgeo left
06:32
topnep left
06:35
topnep joined
06:51
perryprog left
06:52
perryprog joined
08:11
azval joined
08:39
topnep left
08:40
topnep joined
08:54
lichtkind__ left
09:23
Pixi` joined
09:27
Pixi left
09:30
topnep_ joined
09:33
topnep left
10:54
azval left
12:01
Pixi joined
12:02
Pixi` left
15:49
perryprog left,
perryprog joined
16:39
johnjay left
16:41
johnjay joined
17:31
belluzj joined
17:45
belluzj left
18:10
librasteve_ left
19:29
Sgeo joined
19:57
topnep_ left,
topnep joined
20:00
librasteve_ joined
20:10
Ekho left
20:14
Ekho joined
|
|||
| tbrowder | have you ai users seen the ads for pirag to use local docs? anyone try it? | 21:07 | |
|
21:17
hurufu left
21:18
hurufu joined
|
|||
| disbot4 | <antononcube> There are many RAG systems. It is not hard to make and use a RAG vector database. | 21:27 | |
|
21:34
[Coke] left,
[Coke] joined
22:43
hurufu left
23:10
swaggboi left
|
|||
| tbrowder | ok, thnx | 23:33 | |
| disbot4 | <antononcube> I am tempted to advice to use Raku and Ollama for RAG of local documents, but that would require figuring out how to customize certain workflows / scripts. | 23:50 | |
| <antononcube> Also, Raku's I/O of RAG vector databases is slow. After a vector database is loaded, though, the retrieval is fast (enough.) | 23:52 | ||
|
23:57
swaggboi joined
|
|||