Skip to main content

A Jupyter AI extension.

Project description

jupyter_ai_wekeo

jupyter_ai_wekeo is a Jupyter AI module, a package that registers additional model providers and slash commands for the Jupyter AI extension.

Requirements

  • Python 3.8 - 3.12
  • JupyterLab 4

Install

To install the extension, execute:

pip install jupyter-ai-wekeo

Config

  1. Locate or create the Jupyter AI configuration file jupyter_jupyter_ai_config.py. You can copy it into the Jupyter config folder, which can be discovered with:
jupyter --paths
  1. Edit jupyter_jupyter_ai_config.py to add the server endpoint:
c = get_config()

c.AiExtension.default_language_model = "wekeo-provider:server"
c.AiExtension.allowed_providers = ["wekeo-provider", "openai", "openai-chat"]
c.AiExtension.default_max_chat_history = None

c.AiExtension.model_parameters = {
    "wekeo-provider:server": {
        "endpoint": "<http://wekeo-llm-server-endpoint>/rag"
    }
}
  1. Save the file in the Jupyter config folder so it will be automatically discovered by Jupyter.

Uninstall

To remove the extension, execute:

pip uninstall jupyter-ai-wekeo

Contributing

Development install

cd jupyter-ai-wekeo
pip install -e "."

Development uninstall

pip uninstall jupyter-ai-wekeo

Backend tests

This package uses Pytest for Python testing.

Install test dependencies (needed only once):

cd jupyter-ai-wekeo
pip install -e ".[test]"

To execute them, run:

pytest -vv -r ap --cov jupyter-ai-wekeo

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

jupyter_ai_wekeo-0.1.4.tar.gz (5.5 kB view details)

Uploaded Source

File details

Details for the file jupyter_ai_wekeo-0.1.4.tar.gz.

File metadata

  • Download URL: jupyter_ai_wekeo-0.1.4.tar.gz
  • Upload date:
  • Size: 5.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.19

File hashes

Hashes for jupyter_ai_wekeo-0.1.4.tar.gz
Algorithm Hash digest
SHA256 f0246e21dee722c30c06b2424a3a51ed16c51126cbc7f2b5a74f87330aeb1f4f
MD5 7d8ce3ae9fe719d89b57addd1930ee71
BLAKE2b-256 a391e3f51bf91af398e51c870dcda19d85b0f31420b8963f75bfbcc0f1c716dc

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