Launching an OpenAI-Compatible Server Using Llama 3 Model with llama-cpp-python and Access It from Spring AI

Warning

This article was automatically translated by OpenAI (gpt-4o).It may be edited eventually, but please be aware that it may contain incorrect information at this time.

"Launching an OpenAI-Compatible Server Using Gemma Model with llama-cpp-python and Access It from Spring AI" in the same way, we will try Meta's Llama 3.

Table of Contents

Installing llama-cpp-python
Downloading Llama 3
Starting the OpenAI-Compatible Server

Accessing with curl
Accessing with Spring AI

Installing llama-cpp-python

First, create a virtual environment.

mkdir -p $HOME/work/llm
cd $HOME/work/llm
python3 -m venv .venv
source .venv/bin/activate

Install llama-cpp-python along with the server.

CMAKE_ARGS="-DLLAMA_METAL=on" pip install --force-reinstall --no-cache-dir 'llama-cpp-python[server]'

Note

If you encounter errors on an Apple Silicon Mac, try the setup described at https://github.com/abetlen/llama-cpp-python/blob/main/docs/install/macos.md.

chat_format="llama-3" was supported in the following commit, so use v0.2.64 or higher.

https://github.com/abetlen/llama-cpp-python/commit/8559e8ce88b7c7343004eeccb7333b806034b01c

Downloading Llama 3

sudo mkdir -p /opt/models
sudo chown -R $USER /opt/models

The model used with llama-cpp-python needs to be in GGUF format, so we will use the following model converted to GGUF format.

https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF

Download Meta-Llama-3-8B-Instruct.Q4_K_M.gguf to /opt/models/.

Starting the OpenAI-Compatible Server

Start the server with the following command. You need to specify --chat_format=llama-3.

python3 -m llama_cpp.server --chat_format=llama-3 --model /opt/models/Meta-Llama-3-8B-Instruct.Q4_K_M.gguf --n_gpu_layers 1

You can check the API documentation from the following.

http://localhost:8000/docs

The OpenAI "Create chat completion" API requires the model parameter, but it seems that the model parameter is not necessary for llama-cpp-python.

Accessing with curl

curl -s http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
   "messages": [
      {"role": "user", "content": "Give me a joke."}
   ]
 }' | jq .

A joke was returned.

{
  "id": "chatcmpl-755f1cc0-39e1-408c-b119-11034492b500",
  "object": "chat.completion",
  "created": 1715328366,
  "model": "/opt/models/Meta-Llama-3-8B-Instruct.Q4_K_M.gguf",
  "choices": [
    {
      "index": 0,
      "message": {
        "content": "Here's one:\n\nWhy couldn't the bicycle stand up by itself?\n\n(Wait for it...)\n\nBecause it was two-tired!\n\nHope that made you laugh!",
        "role": "assistant"
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 17,
    "completion_tokens": 32,
    "total_tokens": 49
  }
}

Accessing with Spring AI

Let's access it from an app using Spring AI.
Since it is OpenAI-compatible, you can use the OpenAI Chat Client of Spring AI.

Here is a sample app.

https://github.com/making/hello-spring-ai

git clone https://github.com/making/hello-spring-ai
cd hello-spring-ai
./mvnw clean package -DskipTests=true
java -jar target/hello-spring-ai-0.0.1-SNAPSHOT.jar --spring.ai.openai.base-url=http://localhost:8000 --spring.ai.openai.api-key=dummy

$ curl localhost:8080
Here's one:

Why couldn't the bicycle stand up by itself?

(Wait for it...)

Because it was two-tired!

Hope that made you smile! Do you want to hear another one?

This app itself is for OpenAI, but the advantage of using llama-cpp-python is that you can use Llama-3 just by changing the properties.

If you don't care about compatibility with the OpenAI API and just want to use Llama 3, you can also use Ollama via spring-ai-ollama.

IK.AM