2025-07-18 12:53:00 +02:00
|
|
|
# lydia
|
|
|
|
|
your friendly ai assistant. frontend for ollama.
|
|
|
|
|
|
|
|
|
|
> fair warning: lydia is very stupid
|
|
|
|
|
|
|
|
|
|
# Installation
|
2025-07-18 17:02:52 +02:00
|
|
|
- git clone repository
|
2025-07-18 12:53:00 +02:00
|
|
|
- install ollama from `https://ollama.ai/download`
|
2025-07-18 17:14:49 +02:00
|
|
|
- pull a model from ollama (i recommend gemma3n:e4b for laptops like mine (i7-10750h + rtx 3050ti laptop edition))
|
2025-07-18 17:03:01 +02:00
|
|
|
- copy config.example.toml to config.toml and edit it to have the model you selected, optionally set your name in [user]
|
2025-07-18 17:02:52 +02:00
|
|
|
- npm i
|
2025-07-18 12:53:00 +02:00
|
|
|
- node index.js
|
|
|
|
|
- enjoy
|
2025-07-18 17:14:49 +02:00
|
|
|
|
|
|
|
|
# Configuration
|
2025-07-18 17:37:11 +02:00
|
|
|
lydia is written to be easily configurable through a toml file which is easier to read and understand than json
|
2025-07-18 17:14:49 +02:00
|
|
|
## Assistant settings
|
|
|
|
|
- name = change the name you want the assistant to use for itself. changes it everywhere, including all placeholder text. default is "lydia"
|
|
|
|
|
- model = the ollama model you want lydia to use. default is "gemma3n:e4b"
|
|
|
|
|
- system_prompt = the system prompt you want lydia to use.
|
|
|
|
|
- assistantface = the default face you want lydia to have before waking up. default is "=w="
|
|
|
|
|
|
|
|
|
|
## User settings
|
|
|
|
|
- name = the name you want lydia to call you. default is "user"
|
