guillotina_nuclia – Quick Setup
================================
This package lets your Guillotina instance talk to **Nuclia**.
Below is the only thing you have to do: drop the utility in ``app_settings``
and export your credentials.
Install
-------
.. code-block:: bash
pip install guillotina_nuclia
Configure the Nuclia utility
----------------------------
These are the settings regarding nuclia already configured in the package.
You mostly need to set up the next env variables: NUA_KEY, APIKEY, KBID, GENERATIVE_MODEL
.. code-block:: python
import os
app_settings = {
"load_utilities": {
"nuclia": {
# interface that the utility will provide
"provides": "guillotina_nuclia.utility.INucliaUtility",
# dotted path to the factory
"factory": "guillotina_nuclia.utility.NucliaUtility",
# parameters forwarded to the factory
"settings": {
# which LLM model Nuclia will use for generative answers
"generative_model": os.environ.get("GENERATIVE_MODEL", "chatgpt4o"),
# your personal Nuclia key (required)
"nua_key": os.environ.get("NUA_KEY"),
# hard limit for tokens (optional)
"max_tokens": os.environ.get("MAX_TOKENS"),
# Nuclia's API KEY
"apikey": os.environ.get("APIKEY"),
# Knowledge Box ID
"kbid": os.environ.get("KBID", ""),
},
}
}
}
Set the environment variables
-----------------------------
.. list-table:: Environment variables
:header-rows: 1
* - Variable
- Required
- Example value
- Description
* - ``NUA_KEY``
- **Yes**
- ``nua_pk_live_…``
- API token generated in the Nuclia dashboard.
* - ``GENERATIVE_MODEL``
- No
- ``chatgpt4o`` (default)
- LLM used for ``ask`` / ``predict``.
* - ``MAX_TOKENS``
- No
- ``2048``
- Maximum tokens per answer.
Export them before launching Guillotina:
.. code-block:: bash
export NUA_KEY=\"nua_pk_live_your_token_here\"
export KBID=\"Knwoledge box id\"
export API_KEY=\"Nuclia's api key\"
export GENERATIVE_MODEL=\"chatgpt4o\" # optional
export MAX_TOKENS=2048 # optional
Done!
-----
Start Guillotina as usual—``INucliaUtility`` is now available
everywhere and the built-in routes POST (``@NucliaAsk``,
``@NucliaFind``, ``@NucliaPredict``, ``@NucliaSearch``,
``@NucliaAskStream``, etc.) will automatically work.
❤️ Happy coding!
1.0.3 (2025-07-29)
------------------
- Adding retrieval response in @NucliaAskStream
[nilbacardit26]
- Convert all the endpoints from GET to POST. Now the question goes to
the body
[nilbacardit26]
1.0.2 (2025-07-28)
------------------
- Fixing TypeError: can only concatenate str when kbid is not passed
[nilbacardit26]
1.0.1 (2025-07-28)
------------------
- Fixing KBID auth
[nilbacardit26]
- Adding @NucliaAskStream endpoint
[nilbacardit26]
1.0.0 (2025-07-23)
------------------
- Initial release
[nilbacardit26]
Raw data
{
"_id": null,
"home_page": "https://github.com/guillotinaweb/guillotina_nuclia",
"name": "guillotina-nuclia",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "AI async guillotina nuclia",
"author": "Nil Bacardit Vinyals",
"author_email": "n.bacardit@iskra.cat",
"download_url": "https://files.pythonhosted.org/packages/6e/16/92ccce7f0901abe76346d2882841a63d029dbce2efa0acb449af063c4ddd/guillotina_nuclia-1.0.3.tar.gz",
"platform": null,
"description": "guillotina_nuclia \u2013 Quick Setup\n================================\n\nThis package lets your Guillotina instance talk to **Nuclia**.\nBelow is the only thing you have to do: drop the utility in ``app_settings``\nand export your credentials.\n\nInstall\n-------\n\n.. code-block:: bash\n\n pip install guillotina_nuclia\n\nConfigure the Nuclia utility\n----------------------------\n\nThese are the settings regarding nuclia already configured in the package.\nYou mostly need to set up the next env variables: NUA_KEY, APIKEY, KBID, GENERATIVE_MODEL\n\n.. code-block:: python\n\n import os\n\n app_settings = {\n \"load_utilities\": {\n \"nuclia\": {\n # interface that the utility will provide\n \"provides\": \"guillotina_nuclia.utility.INucliaUtility\",\n # dotted path to the factory\n \"factory\": \"guillotina_nuclia.utility.NucliaUtility\",\n # parameters forwarded to the factory\n \"settings\": {\n # which LLM model Nuclia will use for generative answers\n \"generative_model\": os.environ.get(\"GENERATIVE_MODEL\", \"chatgpt4o\"),\n # your personal Nuclia key (required)\n \"nua_key\": os.environ.get(\"NUA_KEY\"),\n # hard limit for tokens (optional)\n \"max_tokens\": os.environ.get(\"MAX_TOKENS\"),\n\t\t # Nuclia's API KEY\n\t\t \"apikey\": os.environ.get(\"APIKEY\"),\n\t\t # Knowledge Box ID\n\t\t \"kbid\": os.environ.get(\"KBID\", \"\"),\n\t\t \n },\n }\n }\n }\n\nSet the environment variables\n-----------------------------\n\n.. list-table:: Environment variables\n :header-rows: 1\n\n * - Variable\n - Required\n - Example value\n - Description\n * - ``NUA_KEY``\n - **Yes**\n - ``nua_pk_live_\u2026``\n - API token generated in the Nuclia dashboard.\n * - ``GENERATIVE_MODEL``\n - No\n - ``chatgpt4o`` (default)\n - LLM used for ``ask`` / ``predict``.\n * - ``MAX_TOKENS``\n - No\n - ``2048``\n - Maximum tokens per answer.\n\nExport them before launching Guillotina:\n\n.. code-block:: bash\n\n export NUA_KEY=\\\"nua_pk_live_your_token_here\\\"\n export KBID=\\\"Knwoledge box id\\\"\n export API_KEY=\\\"Nuclia's api key\\\"\n export GENERATIVE_MODEL=\\\"chatgpt4o\\\" # optional\n export MAX_TOKENS=2048 # optional\n\nDone!\n-----\n\nStart Guillotina as usual\u2014``INucliaUtility`` is now available\neverywhere and the built-in routes POST (``@NucliaAsk``,\n``@NucliaFind``, ``@NucliaPredict``, ``@NucliaSearch``,\n``@NucliaAskStream``, etc.) will automatically work.\n\n\u2764\ufe0f Happy coding!\n\n1.0.3 (2025-07-29)\n------------------\n\n- Adding retrieval response in @NucliaAskStream\n [nilbacardit26]\n- Convert all the endpoints from GET to POST. Now the question goes to\n the body\n [nilbacardit26]\n\n\n1.0.2 (2025-07-28)\n------------------\n\n- Fixing TypeError: can only concatenate str when kbid is not passed\n [nilbacardit26]\n\n\n1.0.1 (2025-07-28)\n------------------\n\n- Fixing KBID auth\n [nilbacardit26]\n- Adding @NucliaAskStream endpoint\n [nilbacardit26]\n\n\n1.0.0 (2025-07-23)\n------------------\n\n- Initial release\n [nilbacardit26]\n",
"bugtrack_url": null,
"license": "GPL version 3",
"summary": "nuclia support for guillotina",
"version": "1.0.3",
"project_urls": {
"Homepage": "https://github.com/guillotinaweb/guillotina_nuclia"
},
"split_keywords": [
"ai",
"async",
"guillotina",
"nuclia"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "d7f3c7c61f0fb9f9ae8a06b93b9f7632e02f1117066e7a1a46c3ef1591e2fb72",
"md5": "eadfb86888b308f4c62db2ddb11a615c",
"sha256": "1b058b28d37273013b27080203241e482915ae0b075aba0a17731bf9270c1f93"
},
"downloads": -1,
"filename": "guillotina_nuclia-1.0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "eadfb86888b308f4c62db2ddb11a615c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 20260,
"upload_time": "2025-07-29T10:23:02",
"upload_time_iso_8601": "2025-07-29T10:23:02.397605Z",
"url": "https://files.pythonhosted.org/packages/d7/f3/c7c61f0fb9f9ae8a06b93b9f7632e02f1117066e7a1a46c3ef1591e2fb72/guillotina_nuclia-1.0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "6e1692ccce7f0901abe76346d2882841a63d029dbce2efa0acb449af063c4ddd",
"md5": "67c0e3e7dd82c133e6ab0645968b39c8",
"sha256": "49ecb9ec68709d6fa53b765d61d84f3c79a6460187a3e670ff8b4024c904d852"
},
"downloads": -1,
"filename": "guillotina_nuclia-1.0.3.tar.gz",
"has_sig": false,
"md5_digest": "67c0e3e7dd82c133e6ab0645968b39c8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 20055,
"upload_time": "2025-07-29T10:23:03",
"upload_time_iso_8601": "2025-07-29T10:23:03.903894Z",
"url": "https://files.pythonhosted.org/packages/6e/16/92ccce7f0901abe76346d2882841a63d029dbce2efa0acb449af063c4ddd/guillotina_nuclia-1.0.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-29 10:23:03",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "guillotinaweb",
"github_project": "guillotina_nuclia",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "guillotina-nuclia"
}
JSON
