APIMyLlama is a server application that provides an interface to interact with the Ollama API, a powerful AI tool to run LLMs. It allows users to run this alongside Ollama to easily distrubute API keys to create amazing things.
If you already have Ollama setup with the 'ollama serve' command and your desired model. You can skip this. If not i'll show you how to set it up. First install Ollama for your desired operating system. Once installed open a terminal instance and run the command below.
ollama pull llama3If done correctly you should now have the Meta's Llama3 LLM installed. You can use any model with the API but for this example we will use this model. Now you are gonna run this command after the install is complete.
ollama serveNow you have an Ollama server setup. Time for the next step.
Install Node.JS on your server. Then clone the git repository.
git clone https://github.com/Gimer-Studios/APIMyLlama.git
cd APIMyLlama
npm install
node APIMyLlama.jsAfter cloning go into the cloned directory and installing all the needed dependencies by running the 'npm install' command. Then run the APIMyLlama.js file. On startup it will ask what port you want to use.
PS C:\Users\EXAMPLE\Documents\APIMyLlama> node APIMyLlama.js
Connected to the apiKeys.db database.
Enter the port number: <ENTER_PORT>Enter the desired port you would like to use with the API. After you choose your port you will NEED to port foward this port if you are gonna use the API Key system OUTSIDE of your network.
These are the commands you can use in the APIMyLlama application
generatekeyThis command will generate a key using Cryptography and save it to the local database.
listkeyThis command will list all API Keys in the database.
removekey <KEY>This command will remove any key from the database.
addkey <KEY>You can add custom keys if wanted. (DO with CAUTION as it may be unsafe)
changeport <PORT_NUMBER>You can change the port while running the app allowing you to change the port without restarting the app.
Install APIMyLlama packages with NPM or PIP
NPM Install
cd PROJECT_NAME
npm install apimyllama-node-packagePIP Install
cd PROJECT_NAME
pip install apimyllamaNode.JS example:
const apiMyLlamaNodePackage = require('apimyllama-node-package');
// Intialize Parameters
const apiKey = 'API_KEY';
const prompt = 'Hello!';
const model = 'llama3';
const ip = 'SERVER_IP';
const port = 'SERVER_PORT';
const stream = false;
apiMyLlamaNodePackage.generate(apiKey, prompt, model, ip, port, stream)
.then(response => console.log(response))
.catch(error => console.error(error));Python example:
from ApiMyLlama import ApiMyLlama
# Initialize ApiMyLlama with server IP and port
api = ApiMyLlama(ip='SERVER_IP', port='SERVER_PORT')
# Example usage
apiKey = 'API_KEY'
prompt = 'Hello!'
model = 'llama3'
stream = False
try:
response = api.generate(apiKey, prompt, model, stream)
print("Response from Ollama API:")
print(response)
except Exception as e:
print("Error:", e)ApiMyLlama(ip, port)
ip: IP address of the APIMyLlama server.
port: Port number on which the APIMyLlama server is running.
api.generate(apiKey, prompt, model, stream)
apiKey: API key for accessing the Ollama API.
prompt: Text prompt to generate a response.
model: Machine learning model to use for text generation.
stream: Boolean indicating whether to stream the response.
If there are any issues please make a Github Issue Report. To get quicker support join our discord server. -Discord Server If there are any feature requests you may request them in the discord server. PLEASE NOTE this project is still in EARLY BETA.
APIMyLlama is a server application that provides an interface to interact with the Ollama API, a powerful AI tool to run LLMs. It allows users to run this alongside Ollama to easily distrubute API keys to create amazing things.
If you already have Ollama setup with the 'ollama serve' command and your desired model. You can skip this. If not i'll show you how to set it up. First install Ollama for your desired operating system. Once installed open a terminal instance and run the command below.
ollama pull llama3If done correctly you should now have the Meta's Llama3 LLM installed. You can use any model with the API but for this example we will use this model. Now you are gonna run this command after the install is complete.
ollama serveNow you have an Ollama server setup. Time for the next step.
Install Node.JS on your server. Then clone the git repository.
git clone https://github.com/Gimer-Studios/APIMyLlama.git
cd APIMyLlama
npm install
node APIMyLlama.jsAfter cloning go into the cloned directory and installing all the needed dependencies by running the 'npm install' command. Then run the APIMyLlama.js file. On startup it will ask what port you want to use.
PS C:\Users\EXAMPLE\Documents\APIMyLlama> node APIMyLlama.js
Connected to the apiKeys.db database.
Enter the port number: <ENTER_PORT>Enter the desired port you would like to use with the API. After you choose your port you will NEED to port foward this port if you are gonna use the API Key system OUTSIDE of your network.
These are the commands you can use in the APIMyLlama application
generatekeyThis command will generate a key using Cryptography and save it to the local database.
listkeyThis command will list all API Keys in the database.
removekey <KEY>This command will remove any key from the database.
addkey <KEY>You can add custom keys if wanted. (DO with CAUTION as it may be unsafe)
Install APIMyLlama packages with NPM or PIP
NPM Install
cd PROJECT_NAME
npm install apimyllama-node-packagePIP Install
cd PROJECT_NAME
pip install apimyllamaNode.JS example:
const apiMyLlamaNodePackage = require('apimyllama-node-package');
// Intialize Parameters
const apiKey = 'API_KEY';
const prompt = 'Hello!';
const model = 'llama3';
const ip = 'SERVER_IP';
const port = 'SERVER_PORT';
const stream = false;
apiMyLlamaNodePackage.generate(apiKey, prompt, model, ip, port, stream)
.then(response => console.log(response))
.catch(error => console.error(error));Python example:
from ApiMyLlama import ApiMyLlama
# Initialize ApiMyLlama with server IP and port
api = ApiMyLlama(ip='SERVER_IP', port='SERVER_PORT')
# Example usage
apiKey = 'API_KEY'
prompt = 'Hello!'
model = 'llama3'
stream = False
try:
response = api.generate(apiKey, prompt, model, stream)
print("Response from Ollama API:")
print(response)
except Exception as e:
print("Error:", e)ApiMyLlama(ip, port)
ip: IP address of the APIMyLlama server.
port: Port number on which the APIMyLlama server is running.
api.generate(apiKey, prompt, model, stream)
apiKey: API key for accessing the Ollama API.
prompt: Text prompt to generate a response.
model: Machine learning model to use for text generation.
stream: Boolean indicating whether to stream the response.
If there are any issues please make a Github Issue Report. To get quicker support join our discord server. -Discord Server If there are any feature requests you may request them in the discord server. PLEASE NOTE this project is still in EARLY BETA.
You most likely forgot to run the 'npm install' command after cloning the repository.
You probably didn't port foward. And if you did your router may have not intialized the changes yet or applied them.
3. Ollama Serve command error "Error: listen tcp 127.0.0.1:11434: bind: Only one usage of each socket address (protocol/network address/port) is normally permitted."
If you get this error just close the Ollama app through the system tray on Windows. And if your on Linux just use systemctl to stop the Ollama process. Once done you can try running the ollama serve command again.