31 lines
766 B
Markdown
31 lines
766 B
Markdown
|
# Sentient Jimmy
|
||
|
|
|
||
|
|
Another Ollama bot for discord, however designed for mesh self-hosting.
|
||
|
|
|
||
|
|
## Example config.toml
|
||
|
|
|
||
|
|
```toml
|
||
|
|
[bot]
|
||
|
|
token = "your-bot-token"
|
||
|
|
debug_guilds = [0123456789] # omit for global commands
|
||
|
|
|
||
|
|
[ollama]
|
||
|
|
order = ["server1", "server2", "fallback"]
|
||
|
|
# ^ order of preference for Ollama servers. If server1 is offline, server2 will be tried, and so on
|
||
|
|
|
||
|
|
[ollama.server1]
|
||
|
|
base_url = "https://hosted.ollama.internal" # default port is 443, because HTTPS
|
||
|
|
gpu = true
|
||
|
|
vram_gb = 8
|
||
|
|
|
||
|
|
[ollama.server2]
|
||
|
|
base_url = "http://192.168.1.2:11434"
|
||
|
|
gpu = true
|
||
|
|
vram_gb = 4 # <8GB will enable "low VRAM mode" in ollama
|
||
|
|
|
||
|
|
[ollama.fallback]
|
||
|
|
base_url = "http://192.168.1.250:11434"
|
||
|
|
gpu = false
|
||
|
|
vram_gb = 32 # in the case of CPU Ollama, "vram" is actually just regular RAM.
|
||
|
|
```
|