"4. Message may be blocked if they violate the safety checks of the LLM. In this case, the model will return an empty response."
"4. Message may be blocked if they violate the safety checks of the LLM. In this case, the model will return an empty response."
]
]
},
},
{
"cell_type": "markdown",
"id": "54793b9e",
"metadata": {},
"source": [
"### Safety Settings\n",
"\n",
"Gemini models have default safety settings that can be overridden. If you are receiving lots of \"Safety Warnings\" from your models, you can try tweaking the `safety_settings` attribute of the model. For example, to turn off safety blocking for dangerous content, you can construct your LLM as follows:"
"For an enumeration of the categories and thresholds available, see Google's [safety setting types](https://ai.google.dev/api/python/google/generativeai/types/SafetySettingDict)."
]
},
},
{
{
"cell_type": "markdown",
"cell_type": "markdown",
"id": "92b5aca5",
"id": "92b5aca5",
"metadata": {},
"metadata": {},
"source": [
"source": [
"## Additional Configuraation\n",
"## Additional Configuration\n",
"\n",
"\n",
"You can pass the following parameters to ChatGoogleGenerativeAI in order to customize the SDK's behavior:\n",
"You can pass the following parameters to ChatGoogleGenerativeAI in order to customize the SDK's behavior:\n",
"Gemini models have default safety settings that can be overridden. If you are receiving lots of \"Safety Warnings\" from your models, you can try tweaking the `safety_settings` attribute of the model. For example, to turn off safety blocking for dangerous content, you can construct your LLM as follows:"
"For an enumeration of the categories and thresholds available, see Google's [safety setting types](https://ai.google.dev/api/python/google/generativeai/types/SafetySettingDict)."