Skip to main content

Async Python client for Autobyteus LLM API

Project description

Autobyteus LLM Client

Async Python client for Autobyteus LLM API with HTTPS support.

Installation

pip install autobyteus_llm_client

Certificate Setup

  1. Create certificates directory:
mkdir -p certificates
  1. Copy the server's certificate:
cp path/to/server/certificates/cert.pem certificates/
  1. Get certificate fingerprint (optional but recommended):
openssl x509 -in certificates/cert.pem -fingerprint -sha256 -noout

Configuration

Set environment variables:

# Required
export AUTOBYTEUS_API_KEY='your-api-key'

# Optional (defaults shown)
export AUTOBYTEUS_LLM_SERVER_URL='https://api.autobyteus.com:8443'
export AUTOBYTEUS_CERT_FINGERPRINT='your-certificate-fingerprint'  # Optional but recommended

Usage

from autobyteus_llm_client import AutobyteusClient

async def main():
    # Initialize client (automatically uses certificate from certificates/cert.pem)
    client = AutobyteusClient()
    
    try:
        # Get available models
        models = await client.get_available_models()
        print(f"Available models: {models}")
        
        # Send a message
        response = await client.send_message(
            conversation_id="conv123",
            model_name="gpt-4",
            user_message="Hello!"
        )
        print(f"Response: {response}")
        
    finally:
        await client.close()

Security Features

  1. Certificate Verification

    • Automatic certificate validation
    • Certificate expiration checking
    • Optional fingerprint verification
    • Path validation and security checks
  2. SSL/TLS Security

    • HTTPS communication
    • Certificate-based authentication
    • Secure default configuration

Development

Requirements

  • Python 3.8 or higher
  • httpx
  • cryptography

Installing Development Dependencies

pip install -e ".[test]"

Running Tests

pytest

Building and Publishing

Build Package

python -m build

Publish to Test PyPI

python -m twine upload --repository testpypi dist/*

Publish to Production PyPI

python -m twine upload dist/*

Troubleshooting

  1. Certificate Issues

    • Verify certificate location (should be in certificates/cert.pem)
    • Check certificate expiration
    • Verify fingerprint if enabled
  2. Connection Issues

    • Verify server URL and port
    • Check certificate validity
    • Ensure API key is set correctly

License

This project is licensed under the MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

autobyteus_llm_client-1.1.0.tar.gz (10.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

autobyteus_llm_client-1.1.0-py3-none-any.whl (11.6 kB view details)

Uploaded Python 3

File details

Details for the file autobyteus_llm_client-1.1.0.tar.gz.

File metadata

  • Download URL: autobyteus_llm_client-1.1.0.tar.gz
  • Upload date:
  • Size: 10.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.12

File hashes

Hashes for autobyteus_llm_client-1.1.0.tar.gz
Algorithm Hash digest
SHA256 57888cb567e343512179b8f5e630570cdb647547b335fc8542975eb458b81a01
MD5 8b2878ca68e1b53832b4e123c50ebded
BLAKE2b-256 9a70801a3778b975e68efd0820e390a272ef88b707576dd4d7051704e6e16f2f

See more details on using hashes here.

File details

Details for the file autobyteus_llm_client-1.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for autobyteus_llm_client-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e8817824704f0f239d02165d7eb5f1bda7e85ffff5e46a09dafd6e8b304c8c19
MD5 f839f8ddcea2ba282db3aea4b0ab7257
BLAKE2b-256 5d7b95a818eb13d2a3a8d57b4abf01a30c18e6e284381f4228669542c8a01eef

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page