erik/dumant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix ordering in readme

Browse source
This commit is contained in:
Erik Stambaugh 2025-07-13 09:49:05 -07:00
parent ccbcebf0e8
commit 0510747a67
2 changed files with 11 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
.gitignore vendored
View file

@ -1,3 +1,6 @@
env env
data/* data/*
__pycache__ __pycache__
orig
scripts/are.txt
scripts/is.txt

16
README.md
View file

@ -17,14 +17,6 @@ Huh?
# How do I use it?
You need CUDA working in Docker, or to edit the docker compose files to take that stuff out and rely on CPU.
At present the LLM seems to require about 2GB of GPU RAM, which is really small as LLMs go. My PC works harder playing Balatro.
# What are its limitations? # What are its limitations?
It doesn't have heaps of feature parity with the old perl infobot. The right way to get that might be to hack on the old bot code and use it as the main chat parser for this. I don't have a ton of desire to sit down and code my own implementation of the entire thing. It doesn't have heaps of feature parity with the old perl infobot. The right way to get that might be to hack on the old bot code and use it as the main chat parser for this. I don't have a ton of desire to sit down and code my own implementation of the entire thing.
@ -41,6 +33,14 @@ And some non-infobot stuff we could use:
# How do I use it?
You need CUDA working in Docker, or to edit the docker compose files to take that stuff out and rely on CPU.
At present the LLM seems to require about 2GB of GPU RAM, which is really small as LLMs go. My PC works harder playing Balatro.
## Initialize the database ## Initialize the database
This took around an hour to do 300k factoids and a fair amount of compute/GPU power. There's no consistency or duplicate checking at the moment so you're best off trashing the postgres data dir first This took around an hour to do 300k factoids and a fair amount of compute/GPU power. There's no consistency or duplicate checking at the moment so you're best off trashing the postgres data dir first