argo-proxy 2.5.1a0

Proxy server to Argo API, OpenAI format compatible

argo-openai-proxy

This project is a proxy application that forwards requests to an ARGO API and optionally converts the responses to be compatible with OpenAI's API format. It can be used in conjunction with autossh-tunnel-dockerized or other secure connection tools.

TL;DR

pip install argo-proxy # install the package
argo-proxy # run the proxy

NOTICE OF USAGE

The machine or server making API calls to Argo must be connected to the Argonne internal network or through a VPN on an Argonne-managed computer if you are working off-site. Your instance of the argo proxy should always be on-premise at an Argonne machine. The software is provided "as is," without any warranties. By using this software, you accept that the authors, contributors, and affiliated organizations will not be liable for any damages or issues arising from its use. You are solely responsible for ensuring the software meets your requirements.

• Notice of Usage
• Deployment
  • Prerequisites
  • Configuration File
  • Running the Application
  • First-Time Setup
  • Configuration Options Reference
• Usage
  • Endpoints
    • OpenAI Compatible
    • Not OpenAI Compatible
    • Timeout Override
  • Models
    • Chat Models
    • Embedding Models
  • Examples
    • Chat Completion Example
    • Embedding Example
    • o1 Chat Example
    • OpenAI Client Example
• Folder Structure
• Bug Reports and Contributions

Deployment

Prerequisites

• Python 3.10+ is required
  recommend to use conda/mamba or pipx etc to manage exclusive environment
  Conda/Mamba Download and install from: https://conda-forge.org/download/

• Install dependencies:

  pip install argo-proxy
  

  or, if you decide to use dev version (make sure you are at the root of the repo cloned):

  pip install .
  

Configuration File

If you don't want to bother manually configure it, the First-Time Setup will automatically create it for you.

The application uses config.yaml for configuration. Here's an example:

port: 44497
host: 0.0.0.0
argo_url: "https://apps-dev.inside.anl.gov/argoapi/api/v1/resource/chat/"
argo_stream_url: "https://apps-dev.inside.anl.gov/argoapi/api/v1/resource/streamchat/"
argo_embedding_url: "https://apps.inside.anl.gov/argoapi/api/v1/resource/embed/"
user: "your_username" # set during first-time setup
verbose: true # can be changed during setup
num_workers: 5
timeout: 600 # in seconds

Running the Application

To start the application:

argo-proxy [config_path]

• Without arguments: search for config.yaml under ~/.config/argoproxy/, ~/.argoproxy/, or current directory

• With path: uses specified config file

  argo-proxy /path/to/config.yaml
  

First-Time Setup

When running without an existing config file:

1. The script offers to create config.yaml from config.sample.yaml
2. Automatically selects a random available port (can be overridden)
3. Prompts for:
   • Your username (sets user field)
   • Verbose mode preference (sets verbose field)
4. Validates connectivity to configured URLs
5. Shows the generated config in a formatted display for review before proceeding

Example session:

$ argo-proxy 
No valid configuration found.
Would you like to create it from config.sample.yaml? [Y/n]: 
Creating new configuration...
Use port [52226]? [Y/n/<port>]: 
Enter your username: your_username
Enable verbose mode? [Y/n] 
Set timeout to [600] seconds? [Y/n/<timeout>] 
Created new configuration at: /home/your_username/.config/argoproxy/config.yaml
Using port 52226...
Validating URL connectivity...
Current configuration:
--------------------------------------
{
    "host": "0.0.0.0",
    "port": 52226,
    "user": "your_username",
    "argo_url": "https://apps-dev.inside.anl.gov/argoapi/api/v1/resource/chat/",
    "argo_stream_url": "https://apps-dev.inside.anl.gov/argoapi/api/v1/resource/streamchat/",
    "argo_embedding_url": "https://apps.inside.anl.gov/argoapi/api/v1/resource/embed/",
    "verbose": true,
    "num_workers": 5,
    "timeout": 600
}
--------------------------------------
# ... proxy server starting info display ...

Configuration Options Reference

Option	Description	Default
host	Host address to bind the server to	0.0.0.0
port	Application port (random available port selected by default)	randomly assigned
argo_url	ARGO chat API URL	Dev URL (for now)
argo_stream_url	ARGO stream API URL	Dev URL (for now)
argo_embedding_url	ARGO embedding API URL	Prod URL
user	Your username	(Set during setup)
verbose	Debug logging	true
num_workers	Worker processes	5
timeout	Request timeout (seconds)	600

argo-proxy Cli Available Options

$ argo-proxy -h
usage: argo-proxy [-h] [--show] [--host HOST] [--port PORT] [--num-worker NUM_WORKER]
                  [--verbose | --quiet] [--version]
                  [config]

Argo Proxy CLI

positional arguments:
  config                Path to the configuration file

options:
  -h, --help            show this help message and exit
  --show, -s            Show the current configuration during launch
  --host HOST, -H HOST  Host address to bind the server to
  --port PORT, -p PORT  Port number to bind the server to
  --num-worker NUM_WORKER, -n NUM_WORKER
                        Number of worker processes to run
  --verbose, -v         Enable verbose logging, override if `verbose` set False in config
  --quiet, -q           Disable verbose logging, override if `verbose` set True in config
  --version, -V         Show the version and exit.

Usage

Endpoints

OpenAI Compatible

These endpoints convert responses from the ARGO API to be compatible with OpenAI's format:

• /v1/chat/completions: Converts ARGO chat/completions responses to OpenAI-compatible format.
• /v1/completions: Legacy API for conversions to OpenAI format.
• /v1/embeddings: Accesses ARGO Embedding API with response conversion.
• /v1/models: Lists available models in OpenAI-compatible format.

Not OpenAI Compatible

These endpoints interact directly with the ARGO API and do not convert responses to OpenAI's format:

• /v1/chat: Proxies requests to the ARGO API without conversion.
• /v1/status: Responds with a simple "hello" from GPT-4o, knowing it is alive.

Timeout Override

You can override the default timeout with a timeout parameter in your request.

Details of how to make such override in different query flavors: Timeout Override Examples

Models

Chat Models

Original ARGO Model Name	Argo Proxy Name
gpt35	argo:gpt-3.5-turbo
gpt35large	argo:gpt-3.5-turbo-16k
gpt4	argo:gpt-4
gpt4large	argo:gpt-4-32k
gpt4turbo	argo:gpt-4-turbo-preview
gpt4o	argo:gpt-4o
gpt4olatest	argo:gpt-4o-latest
gpto1preview	argo:gpt-o1-preview, argo:o1-preview
gpto1mini	argo:gpt-o1-mini , argo:o1-mini
gpto3mini	argo:gpt-o3-mini , argo:o3-mini
gpto1	argo:gpt-o1 , argo:o1

Embedding Models

Original ARGO Model Name	Argo Proxy Name
ada002	argo:text-embedding-ada-002
v3small	argo:text-embedding-3-small
v3large	argo:text-embedding-3-large

Examples

Chat Completion Example

For an example of how to use the /v1/chat/completions, /v1/completions, /v1/chat endpoint, see the followings:

• chat_completions_example.py
• chat_completions_example_stream.py
• completions_example.py
• completions_example_stream.py
• chat_example.py
• chat_example_stream.py

Embedding Example

• embedding_example.py

o1 Chat Example

• o1_chat_example.py

OpenAI Client Example

• openai_o3_chat_example.py

Folder Structure

The following is an overview of the project's directory structure:

$ tree -I "__pycache__|*.egg-info|dist|dev_scripts|config.yaml"
.
├── config.sample.yaml
├── examples
│   ├── chat_completions_example.py
│   ├── chat_completions_example_stream.py
│   ├── chat_example.py
│   ├── chat_example_stream.py
│   ├── completions_example.py
│   ├── completions_example_stream.py
│   ├── embedding_example.py
│   ├── o1_chat_example.py
│   └── o3_chat_example_pyclient.py
├── LICENSE
├── Makefile
├── pyproject.toml
├── README.md
├── run_app.sh
├── src
│   └── argoproxy
│       ├── app.py
│       ├── chat.py
│       ├── cli.py
│       ├── completions.py
│       ├── config.py
│       ├── constants.py
│       ├── embed.py
│       ├── extras.py
│       ├── __init__.py
│       ├── py.typed
│       └── utils.py
└── timeout_examples.md

4 directories, 27 files

Bug Reports and Contributions

This project was developed in my spare time. Bugs and issues may exist. If you encounter any or have suggestions for improvements, please open an issue or submit a pull request. Your contributions are highly appreciated!