Containerize bot and server in one stack.

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!

default.env

@@ -1,5 +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
+DATA_DIR = /home/USERNAME/weights

docker-compose.yml

@@ -11,7 +11,7 @@ services:
       - ${DATA_DIR}/weights:/usr/src/app/models
     environment:
       - HOST=llama-python-server
-      - MODEL=./models/gpt4-x-alpaca-13b-native-4bit-128g.bin
+      - MODEL=./models/30B.bin
   llama-python-djs-bot:
     container_name: llama-python-djs-bot
     restart: unless-stopped
@@ -23,4 +23,5 @@ services:
       - THE_TOKEN
       - CHANNEL_IDS
       - ROOT_IP=llama-python-server
-      - ROOT_PORT=8000
+      - ROOT_PORT=8000
+      - CACHE=1

llamabot.js

@@ -104,15 +104,15 @@ 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',
-            content: `Hello, ${message.author.username}, how may I help you?`
+            content: ` Hello, ${message.author.username}, how may I help you?`
         });
     }
 
@@ -125,7 +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 {
@@ -190,12 +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.trim();
-        const startIndex = responseText.indexOf('user None:');
-        const sanitizedResponse = startIndex === -1 ? responseText : responseText.substring(0, startIndex);
-
-        return sanitizedResponse;
+        const responseText = choice.message.content
+        
+        return responseText;
+        
     } catch (err) {
         throw err;
     } finally {