Skip to main content

Intelligence/AI services for the Lifsys Enterprise

Project description

Intellisys

Intellisys is a Python library that provides intelligence/AI services for the Lifsys Enterprise. It offers a unified interface to interact with various AI models and services, including OpenAI, Anthropic, Google, and more.

Installation

You can install Intellisys using pip:

pip install intellisys

For the latest development version, you can install directly from GitHub:

pip install git+https://github.com/lifsys/intellisys.git

Requirements

  • Python 3.6 or higher
  • A 1Password Connect server (for API key management)
  • Environment variables:
    • OP_CONNECT_TOKEN: Your 1Password Connect token
    • OP_CONNECT_HOST: The URL of your 1Password Connect server

Note: If no local 1Password Connect server is available, the library will fail to retrieve API keys.

Features

  • Support for multiple AI models (OpenAI, Anthropic, Google, TogetherAI, Groq, MistralAI)
  • Secure API key management using 1Password Connect
  • JSON formatting and template rendering
  • Asynchronous assistant interactions
  • Template-based API calls

Usage

Here's a quick example of how to use Intellisys:

from intellisys import get_completion_api

# Make sure OP_CONNECT_TOKEN and OP_CONNECT_HOST are set in your environment

response = get_completion_api("Hello, how are you?", "gpt-4")
print(response)

Advanced Usage

from intellisys import template_api_json, get_assistant

# Using a template for API calls
render_data = {"user_name": "Alice"}
system_message = "You are a helpful assistant. Greet {{user_name}}."
response = template_api_json("gpt-4", render_data, system_message, "friendly_assistant")
print(response)

# Using an OpenAI assistant
assistant_id = "your_assistant_id"
reference = "What's the weather like today?"
responses = get_assistant(reference, assistant_id)
for response in responses:
    print(response)

Supported Models

Intellisys supports a variety of AI models:

  • OpenAI: gpt-4o-mini, gpt-4, gpt-4o
  • Anthropic: claude-3.5
  • Google: gemini-flash
  • TogetherAI: llama-3-70b, llama-3.1-large
  • Groq: groq-llama, groq-fast
  • MistralAI: mistral-large

API Reference

For detailed information on available functions and their usage, please refer to the docstrings in the source code.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Changelog

For a detailed list of changes and version history, please refer to the CHANGELOG.md file.

About Lifsys, Inc

Lifsys, Inc is an AI company dedicated to developing solutions for the future. For more information, visit www.lifsys.com.

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

intellisys-0.1.8.tar.gz (11.3 kB view details)

Uploaded Source

Built Distribution

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

intellisys-0.1.8-py3-none-any.whl (9.5 kB view details)

Uploaded Python 3

File details

Details for the file intellisys-0.1.8.tar.gz.

File metadata

  • Download URL: intellisys-0.1.8.tar.gz
  • Upload date:
  • Size: 11.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.0

File hashes

Hashes for intellisys-0.1.8.tar.gz
Algorithm Hash digest
SHA256 eb730c186c9c37393e18e0a5289abd7992d42e7604a3ce8d5a6ea075d24547a7
MD5 6f3f6b76afd4a9924e2989a729cd6fe2
BLAKE2b-256 c9f1bd0072789b321b28d9fc0f526cc1a7f9a6002927cf222415fbc87117d37a

See more details on using hashes here.

File details

Details for the file intellisys-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: intellisys-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 9.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.0

File hashes

Hashes for intellisys-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 a95dcf05a6f46834b2ab357d6d34225d5ab140b515bb0f7543a583bc1a19f65a
MD5 abd7954416bcd855adc4e12e50cd0736
BLAKE2b-256 b9557250238e5f8f4b444ad88f98db63ef0f093582d643ae937af0100d08d4c3

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