Start a chat endpoint

Modular Team

max

llama3

openai

MAX provides OpenAI-compatible endpoints for using open source models with the same API interface as OpenAI. This allows you to replace commercial models with alternatives from the MAX Builds site with minimal code changes.

This tutorial shows you how to serve Llama 3.1 locally with the max CLI and interact with it through REST and Python APIs. You'll learn to configure the server and make requests using the OpenAI client libraries as a drop-in replacement.

Set up your environment

Create a Python project to install our APIs and CLI tools.

pip

1. Create a project folder:

   mkdir quickstart && cd quickstart

   mkdir quickstart && cd quickstart

2. Create and activate a virtual environment:

   python3 -m venv .venv \
     && source .venv/bin/activate

   python3 -m venv .venv \
     && source .venv/bin/activate

3. Install the modular Python package:

   Nightly

   pip install modular \
     --index-url https://download.pytorch.org/whl/cpu \
     --extra-index-url https://dl.modular.com/public/max-nightly/python/simple/

   pip install modular \
     --index-url https://download.pytorch.org/whl/cpu \
     --extra-index-url https://dl.modular.com/public/max-nightly/python/simple/

   Stable

   pip install modular \
     --index-url https://download.pytorch.org/whl/cpu

   pip install modular \
     --index-url https://download.pytorch.org/whl/cpu

uv

1. Install uv:

   curl -LsSf https://astral.sh/uv/install.sh | sh

   curl -LsSf https://astral.sh/uv/install.sh | sh

   Then restart your terminal to make uv accessible.

2. Create a project:

   uv init quickstart && cd quickstart

   uv init quickstart && cd quickstart

3. Create and start a virtual environment:

   uv venv && source .venv/bin/activate

   uv venv && source .venv/bin/activate

4. Install the modular Python package:

   Nightly

   uv pip install modular \
     --index-url https://download.pytorch.org/whl/cpu \
     --extra-index-url https://dl.modular.com/public/max-nightly/python/simple/

   uv pip install modular \
     --index-url https://download.pytorch.org/whl/cpu \
     --extra-index-url https://dl.modular.com/public/max-nightly/python/simple/

   Stable

   uv pip install modular \
     --index-url https://download.pytorch.org/whl/cpu

   uv pip install modular \
     --index-url https://download.pytorch.org/whl/cpu

magic

1. Install magic:

   curl -ssL https://magic.modular.com/ | bash

   curl -ssL https://magic.modular.com/ | bash

   Then run the source command that's printed in your terminal.

2. Create a project:

   magic init quickstart --format pyproject && cd quickstart

   magic init quickstart --format pyproject && cd quickstart

3. Install the max-pipelines conda package:

   Nightly

   magic add max-pipelines

   magic add max-pipelines

   Stable

   magic add "max-pipelines==25.3"

   magic add "max-pipelines==25.3"

4. Start the virtual environment:

   magic shell

   magic shell

For a complete list of max CLI commands and options, refer to the max CLI reference.

Serve your model

Use the max serve command to start a local model server with the Llama 3.1 model:

max serve \
  --model-path modularai/Llama-3.1-8B-Instruct-GGUF

max serve \
  --model-path modularai/Llama-3.1-8B-Instruct-GGUF

While this example uses the Llama 3.1 model, you can replace it with any of the models listed in the MAX Builds site.

When searching for a model using the MAX Builds site, ensure that the model type can fit into memory of your machine. You can filter and sort models by hardware type, and size of the model. For more information and to learn how to use the MAX Builds site, see MAX Builds in 60 seconds.

The server is ready when you see a message indicating it's running on http://0.0.0.0:8000:

Server ready on http://0.0.0.0:8000 (Press CTRL+C to quit)

Server ready on http://0.0.0.0:8000 (Press CTRL+C to quit)

For a complete list of max CLI commands and options, refer to the MAX CLI reference.

Interact with the model

After the server is running, you can interact with the model using different methods. The MAX endpoint supports OpenAI REST APIs, so you can send requests from your client using the openai Python API.

cURL

The following curl command sends a simple chat request to the model's chat completions endpoint:

curl http://0.0.0.0:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "modularai/Llama-3.1-8B-Instruct-GGUF",
        "messages": [
            {
            "role": "system",
            "content": "You are a helpful assistant."
            },
            {
            "role": "user",
            "content": "Hello, how are you?"
            }
        ],
        "max_tokens": 100
    }'

curl http://0.0.0.0:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "modularai/Llama-3.1-8B-Instruct-GGUF",
        "messages": [
            {
            "role": "system",
            "content": "You are a helpful assistant."
            },
            {
            "role": "user",
            "content": "Hello, how are you?"
            }
        ],
        "max_tokens": 100
    }'

You should receive a response similar to this:

{
  "id": "18b0abd2d2fd463ea43efe2c147bcac0",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": " I'm doing well, thank you for asking. How can I assist you today?",
        "refusal": "",
        "tool_calls": null,
        "role": "assistant",
        "function_call": null
      },
      "logprobs": {
        "content": [],
        "refusal": []
      }
    }
  ],
  "created": 1743543698,
  "model": "modularai/Llama-3.1-8B-Instruct-GGUF",
  "service_tier": null,
  "system_fingerprint": null,
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 17,
    "prompt_tokens": null,
    "total_tokens": 17
  }
}

{
  "id": "18b0abd2d2fd463ea43efe2c147bcac0",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": " I'm doing well, thank you for asking. How can I assist you today?",
        "refusal": "",
        "tool_calls": null,
        "role": "assistant",
        "function_call": null
      },
      "logprobs": {
        "content": [],
        "refusal": []
      }
    }
  ],
  "created": 1743543698,
  "model": "modularai/Llama-3.1-8B-Instruct-GGUF",
  "service_tier": null,
  "system_fingerprint": null,
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 17,
    "prompt_tokens": null,
    "total_tokens": 17
  }
}

Python

You can also use OpenAI's Python client to interact with the model.

To get started, install the OpenAI Python client:

pip install openai

pip install openai

Then, create a client and make a request to the model:

from openai import OpenAI

client = OpenAI(
    base_url = 'http://0.0.0.0:8000/v1',
    api_key='max-serve', # required, but unused for local deployment
)

response = client.chat.completions.create(
  model="modularai/Llama-3.1-8B-Instruct-GGUF",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"},
    {"role": "assistant", "content": "The LA Dodgers won in 2020."},
    {"role": "user", "content": "Where was it played?"}
  ]
)
print(response.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    base_url = 'http://0.0.0.0:8000/v1',
    api_key='max-serve', # required, but unused for local deployment
)

response = client.chat.completions.create(
  model="modularai/Llama-3.1-8B-Instruct-GGUF",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"},
    {"role": "assistant", "content": "The LA Dodgers won in 2020."},
    {"role": "user", "content": "Where was it played?"}
  ]
)
print(response.choices[0].message.content)

In this example, you're using the OpenAI Python client to interact with the MAX endpoint running on local host 8000. The client object is initialized with the base URL http://0.0.0.0:8000/v1 and the API key max-serve. The api_key is required, but the value is not used and can be set to anything.

When you run this code, the model should respond with information about the 2020 World Series location:

The 2020 World Series was played at Globe Life Field in Arlington, Texas. It was a neutral site due to the COVID-19 pandemic.

The 2020 World Series was played at Globe Life Field in Arlington, Texas. It was a neutral site due to the COVID-19 pandemic.

For complete details on all available API endpoints and options, see the MAX Serve API documentation.

Next steps

Now that you have successfully set up MAX with OpenAI-compatible endpoints, checkout out these other tutorials:

Did this tutorial work for you?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It's missing a step; I don't know what to do

I don't understand the purpose

Other

Submit