mirror of
https://github.com/kevinthedang/discord-ollama.git
synced 2026-09-23 17:08:58 -04:00
Eric Curtin
0beaed85aa
llmman (https://github.com/llmmanorg/llmman) serves the Ollama API on port 17434 and works with the bot as-is, so document it in setup-local and link it from the README. Since the backend is no longer Ollama-only, rename the env vars to LLM_ENDPOINT / LLM_PORT as requested in review. OLLAMA_IP / OLLAMA_PORT are kept as deprecated aliases in keys.ts and docker-compose.yml so existing deployments keep working.
About/Goals
Ollama is an AI model management tool that allows users to install and use custom large language models locally.
The project aims to:
- Create a Discord bot that will utilize Ollama and chat to chat with users!
- User and Server Preferences
- Message Persistance
- Containerization with Docker
- Slash Commands Compatible
- Summary Command
- Model Info Command
- List Models Command
- Pull Model Command
- Switch Model Command
- Delete Model Command
- Create Thread Command
- Create Private Thread Command
- Message Stream Command
- Change Message History Size Command
- Clear Channel History Command (User Only)
- Administrator Role Compatible
- Generated Token Length Handling for >2000
- Token Length Handling of any message size
- Multi-User Chat Generation - This was built in from Ollama
v0.2.1+ - Ollama Tool Support Implementation
- Enhanced Channel Context Awareness
- Improved User Replied Triggers
Further, Ollama provides the functionality to utilize custom models or provide context for the top-layer of any model available through the Ollama model library.
Documentation
These are guides to the features and capabilities of this app.
Environment Setup
- Clone this repo using
git clone https://github.com/kevinthedang/discord-ollama.gitor just use GitHub Desktop to clone the repo. - You will need a
.envfile in the root of the project directory with the bot's token. There is a.env.sampleis provided for you as a reference for what environment variables.- For example,
CLIENT_TOKEN = [Bot Token] - The LLM server is configured with
LLM_ENDPOINT/LLM_PORT(OLLAMA_IP/OLLAMA_PORTstill work as deprecated aliases).
- For example,
- Please refer to the docs for bot setup.
- Creating a Discord App
- Local Machine Setup
- Docker Setup for Servers and Local Machines
- Nvidia is recommended for now, but support for other GPUs should be development.
- Local use is not recommended.
Resources
- NodeJS
- This project runs on
lts\jodand above. - This project requires the use of npm version
10.9.0or above.
- This project runs on
- Ollama
- Ollama Docker Image
- llmman also serves the Ollama API (on port
17434) and can be used in its place, see Local Machine Setup.
- Discord.js Docs
- Setting up Docker (Ubuntu 20.04)
Acknowledgement
discord-ollama © 2023 by Kevin Dang is licensed under CC BY 4.0