Skip to main content

PAIG

PAIG offers tools designed to enhance the security and compliance of your AI applications. Whether you're using chatbots internally, incorporating AI services into your products, or utilizing automated tools to process tasks like customer support tickets or feedback, PAIG ensures that you maintain the highest standards of security and adherence to compliance. It's tailored for businesses that value a robust yet straight forward approach to AI application governance

Contents

Installation

PAIG is a python library which can be installed using pip.

pip install paig-server
python -m spacy download en_core_web_lg

Usage

PAIG can be used in following ways:

  1. Run as a service:
    You can simply run the PAIG as a service by running following command:

    paig run
    

    To get the help for the command and see all available [OPTIONS], you can run the following command:

    paig --help
    

    Example:

    paig run --port 4545 --host 0.0.0.0 --background true
    
  2. Run as an Embedded Service:
    You can run PAIG in background by importing the library in your Python code. Please run the help command to see all available options you can pass while calling the launch_app method.

    from paig import launcher
    # Start the PIAG
    session = launcher.launch_app()
    # To get active sessions
    active_session = launcher.get_active_session()
    print(active_session)
    # To view the PIAG in the browser/Iframe
    print(active_session.url)
    # To view the PIAG in the Iframe
    active_session.view()
    # To stop the PIAG
    launcher.close_app()
    

PAIG Server Background Mode

PAIG can be run in the background mode by setting the background flag to true.

  1. To Start the PAIG in the background mode:
paig run --background true

Note: Please use help command to see all available options you can pass on command line.

paig --help
  1. To Stop the PAIG Server:
paig stop
  1. To Check the status of the PAIG Server:
paig status

Optional Configuration

PAIG provides overlay configuration. You can provide the custom configuration in the following ways:

  1. Create a new directory in the present working directory of the project with the name custom-conf.

  2. Create a new custom configuration file named <env>_config.yaml(e.g. dev_config.yaml) in the custom-conf folder which will override default_config.yaml.

  3. In a custom configuration file, the user should provide new configuration key values or override the existing configuration.
    Example: custom-conf/dev_config.yaml

    database:
      url: "sqlite+aiosqlite:///db/database.db"
    
    security:
      basic_auth:
        secret: "<your_secret>"
    

Metadata

Release files for paig-server 0.0.11

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for paig-server 0.0.11
File Interpreter ABI Platform Actions
paig_server-0.0.11-py3-none-any.whl Python 3 none any Details for paig_server-0.0.11-py3-none-any.whl

Release files / paig_server-0.0.11-py3-none-any.whl

Download URL paig_server-0.0.11-py3-none-any.whl
Size 4.2 MB
Tags Python 3
SHA-256 checksum
How to use checksums
dacd4b323d7a40accc57b2efd2b7bd310a2e8f90cd7611874a84eed0ddd66d05
BLAKE2b-256 checksum
How to use checksums
3a14d86797dcf76498822a16b28d79217da5bd49484ca10b3547e9adc1234c82
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.18

Security for paig-server 0.0.11

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page