Containerize bot and server in one stack.

.gitignore

@@ -1,2 +1,3 @@
 .env
-
+node_modules/
+package-lock.json

Dockerfile

@@ -0,0 +1,10 @@
+FROM node:slim
+
+WORKDIR /app
+
+COPY package*.json ./
+RUN npm install --omit=dev
+
+COPY . .
+
+CMD node llamabot.js

README.md

@@ -32,6 +32,9 @@ Define a generateResponse function that sends a request to the GPT-3 API to gene
 
 Call the generateResponse function within the messageCreate event listener function.
 
+![demo](https://media.discordapp.net/attachments/562897071326101515/1095738407826767922/image.png?width=1038&height=660 "demo")
+
+
 # Backend REQUIIRED
 
 The HTTP Server from https://abetlen.github.io/llama-cpp-python/ is required to use this bot.
@@ -48,7 +51,7 @@ python3 -m llama_cpp.server
 
 Navigate to http://localhost:8000/docs to see the OpenAPI documentation.
 
-# Usage
+# Static Usage
 
 1) Use ```npm i ```
 
@@ -60,5 +63,19 @@ Navigate to http://localhost:8000/docs to see the OpenAPI documentation.
 
 6) Run the bot ```node llamabot.js	```
 
+# Docker Compose 
+This will automatically configure the API for you as well as the bot in two seperate containers within a stack.
+
+1. `git clone https://git.ssh.surf/snxraven/llama-cpp-python-djs-bot.git`
+
+
+2. `cp default.env .env`
+
+3. Set DATA_DIR in .env to the exact location of your model files.
+
+4. Edit docker-compose.yaml MODEL to ensure the correct model bin is set
+
+5. `docker compose up -d`
+
 
 Want to make this better? Issue a pull request!

assets/emptyMessages.js

@@ -1,4 +1,4 @@
-const emptyResponses = [
+export const emptyResponses = [
     "Oh boy, this is a tough one! Unfortunately, I don't have much insight to share on this topic.",
     "Hmm, I'm scratching my head on this one. Sorry to say that I don't have much to offer.",
     "Wish I had a witty remark, but alas, I don't have much to contribute to this discussion.",
@@ -28,5 +28,3 @@ const emptyResponses = [
     "I'm afraid I don't have much experience with this, so I can't be of much help.",
     "I wish I had some grand insight to share, but alas, I don't have much to offer in that regard."
   ];
-
-  module.exports = emptyResponses;

assets/errorMessages.js

@@ -1,4 +1,4 @@
-const errorMessages = [
+export const errorMessages = [
     "Uh oh, looks like something went awry! Try !reset to start fresh.",
     "Oops, we hit a bump in the road! Give !reset a try to start anew.",
     "We've encountered an error, but !reset can help us out! Give it a go.",
@@ -21,7 +21,7 @@ const errorMessages = [
     "Oopsie daisy! Give !reset a try and we'll start over."
   ];
 
-  const busyResponses = [
+export const busyResponses = [
     "Sorry about that! Looks like I'm tied up at the moment. Please try again later.",
     "Oops, I'm currently busy with something else. Please try again later.",
     "Looks like I'm already working on something. Can you try again later?",
@@ -43,5 +43,3 @@ const errorMessages = [
     "Looks like I'm currently engaged with something else. Please try again later.",
     "I'm currently unavailable. Can you try again later?"
   ];
-
-  module.exports = { errorMessages, busyResponses};

assets/resetMessages.js

@@ -1,4 +1,4 @@
-const resetResponses = [
+export const resetResponses = [
     "Whoops, let's start fresh! What can I assist you with now?",
     "Looks like we need a fresh start! What do you need help with?",
     "To avoid any gremlins in the system, let's reset! How can I assist you now?",
@@ -21,7 +21,7 @@ const resetResponses = [
     "Let's hit the restart button to make sure we're on the right track. What can I help you with now?"
   ];
 
-  const userResetMessages = [
+export const userResetMessages = [
     "All good, we're starting fresh! How can I assist you?",
     "Got it, let's start over! How can I help you today?",
     "Alright, starting anew! What can I help you with?",
@@ -43,5 +43,3 @@ const resetResponses = [
     "Sure thing, we'll start over! What can I help you with today?",
     "Conversation reset, confirmed! What do you need help with?"
   ];
-
-  module.exports = {resetResponses, userResetMessages};

default.env

@@ -1,4 +1,6 @@
 THE_TOKEN = "DISCORD_TOKEN_HERE"
 CHANNEL_IDS = 1094494101631680653,1094628334727614605
+# ROOT_IP is only used when running the bot without docker compose
 ROOT_IP = 192.168.0.15
 ROOT_PORT = 8000
+DATA_DIR = /home/USERNAME/weights

docker-compose.yml

@@ -0,0 +1,27 @@
+version: '3.9'
+
+services:
+  llama-python-server:
+    container_name: llama-python-server
+    restart: unless-stopped
+    build:
+      context: ./server
+    env_file: .env
+    volumes:
+      - ${DATA_DIR}/weights:/usr/src/app/models
+    environment:
+      - HOST=llama-python-server
+      - MODEL=./models/30B.bin
+  llama-python-djs-bot:
+    container_name: llama-python-djs-bot
+    restart: unless-stopped
+    build:
+      context: .
+    depends_on:
+      - llama-python-server
+    environment:
+      - THE_TOKEN
+      - CHANNEL_IDS
+      - ROOT_IP=llama-python-server
+      - ROOT_PORT=8000
+      - CACHE=1

llamabot.js

@@ -1,23 +1,16 @@
-const Discord = require('discord.js');
+import "dotenv/config.js";
-const fetch = require('node-fetch');
+import fetch from 'node-fetch';
-const emptyResponses = require('./assets/emptyMessages.js');
+import { emptyResponses } from './assets/emptyMessages.js';
-const { resetResponses, userResetMessages } = require('./assets/resetMessages.js');
+import { resetResponses, userResetMessages } from './assets/resetMessages.js';
-const { errorMessages, busyResponses } = require('./assets/errorMessages.js');
+import { errorMessages, busyResponses } from './assets/errorMessages.js';
 
-require('dotenv').config()
+import { Client, GatewayIntentBits, ActivityType, Partials } from 'discord.js';
-
-const {
-    Client,
-    GatewayIntentBits,
-    ActivityType,
-    Partials
-} = require('discord.js');
 
 const client = new Client({
     intents: [
         GatewayIntentBits.DirectMessages,
         GatewayIntentBits.Guilds,
-        GatewayIntentBits.GuildBans,
+        GatewayIntentBits.GuildModeration,
         GatewayIntentBits.GuildMessages,
         GatewayIntentBits.MessageContent,
     ],
@@ -111,11 +104,11 @@ client.on('messageCreate', async (message) => {
     if (conversation.messages.length === 0) {
         conversation.messages.push({
             role: 'user',
-            content: `Your name is rAi, you code, write and provide any information without any mistakes.`
+            content: ` Assistant name: ChatAI. You code, write and provide any information without any mistakes.`
         });
         conversation.messages.push({
             role: 'user',
-            content: `My name is ${message.author.username}.`
+            content: ` User name: ${message.author.username}.`
         });
         conversation.messages.push({
             role: 'assistant',
@@ -132,7 +125,7 @@ client.on('messageCreate', async (message) => {
     // Append user message to conversation history
     conversation.messages.push({
         role: 'user',
-        content: message.cleanContent
+        content: ` ${message.cleanContent}`
     });
 
     try {
@@ -197,12 +190,10 @@ async function generateResponse(conversation) {
         console.log(JSON.stringify(responseData))
         const choice = responseData.choices[0];
 
-        // Remove "user None:" and any text after it from the response
+        const responseText = choice.message.content
-        const responseText = choice.message.content.trim();
+        
-        const startIndex = responseText.indexOf('user None:');
+        return responseText;
-        const sanitizedResponse = startIndex === -1 ? responseText : responseText.substring(0, startIndex);
         
-        return sanitizedResponse;
     } catch (err) {
         throw err;
     } finally {

package.json

@@ -0,0 +1,17 @@
+{
+  "name": "llama-cpp-python-djs-bot",
+  "version": "1.0.0",
+  "description": "",
+  "main": "llamabot.js",
+  "type": "module",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "",
+  "license": "ISC",
+  "dependencies": {
+    "discord.js": "^14.9.0",
+    "dotenv": "^16.0.3",
+    "node-fetch": "^3.3.1"
+  }
+}

server/Dockerfile

@@ -0,0 +1,11 @@
+FROM python:bullseye
+
+RUN apt-get update; \
+    apt-get install -y --no-install-recommends \
+    build-essential
+
+WORKDIR /usr/src/app
+
+RUN pip install --no-cache-dir llama-cpp-python[server]
+
+CMD python3 -m llama_cpp.server