guillotina-nuclia 1.0.7

nuclia support for guillotina

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

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

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

Environment variables

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:

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!

1.0.7 (2025-12-18)

• Configuration can be passed in the payload of the request of @NucliaAsk and @NucliaAskStream. [nilbacardit26]

1.0.6 (2025-12-16)

• Adding chat history param in the body @NucliaAsk and @NucliaAskStream [nilbacardit26]

1.0.5 (2025-12-03)

• Adding stateless chat endpoints. [nilbacardit26]

1.0.4 (2025-09-23)

• Changing API Endpoint to progress, and adding API_ENDPOINT env variable to be able to customize it

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]