update readme

README.md

@@ -32,6 +32,19 @@ 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.
 
+# Backend REQUIIRED
+
+The HTTP Server from https://abetlen.github.io/llama-cpp-python/ is required to use this bot.
+
+llama-cpp-python offers a web server which aims to act as a drop-in replacement for the OpenAI API. This allows you to use llama.cpp compatible models with any OpenAI compatible client (language libraries, services, etc).
+
+To install the server package and get started:
+
+pip install llama-cpp-python[server]
+export MODEL=./models/your_model.py
+python3 -m llama_cpp.server
+Navigate to http://localhost:8000/docs to see the OpenAPI documentation.
+
 # Usage
 
 1) Use ```npm i ```

llamabot.js

@@ -111,15 +111,15 @@ client.on('messageCreate', async (message) => {
     if (conversation.messages.length === 0) {
         conversation.messages.push({
             role: 'user',
-            content: `You are rAi, the most helpful writing AI, you code, write and provide information without any mistakes.`
+            content: `Your name is rAi, you code, write and provide any information without any mistakes.`
         });
         conversation.messages.push({
             role: 'user',
-            content: `My name is ${message.author.username}. \nIf you address me, tag me using @${message.author.username}`
+            content: `My name is ${message.author.username}.`
         });
         conversation.messages.push({
             role: 'assistant',
-            content: `Hello, ${message.author.username}, I am here to answer any question you have, how may I help you?`
+            content: `Hello, ${message.author.username}, how may I help you?`
         });
     }