You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Function calling allows you to connect models like locally trained Models to external tools and systems. This is useful for many things such as empowering AI assistants with capabilities or building deep integrations between your applications and the models.
Can we do this using the existing code of LLM.swift?
if not then can we able to integrate this feature?
my functionality is locally added LLM model in device that gives me output in the form of structure JSON.
Sample Function { "name": "get_delivery_date", "description": "Get the delivery date for a customer's order. Call this whenever you need to know the delivery date, for example when a customer asks 'Where is my package'", "parameters": { "type": "object", "properties": { "order_id": { "type": "string", "description": "The customer's order ID.", }, }, "required": ["order_id"], "additionalProperties": false, } }
The text was updated successfully, but these errors were encountered:
Function calling allows you to connect models like locally trained Models to external tools and systems. This is useful for many things such as empowering AI assistants with capabilities or building deep integrations between your applications and the models.
Can we do this using the existing code of LLM.swift?
if not then can we able to integrate this feature?
my functionality is locally added LLM model in device that gives me output in the form of structure JSON.
Sample Function
{ "name": "get_delivery_date", "description": "Get the delivery date for a customer's order. Call this whenever you need to know the delivery date, for example when a customer asks 'Where is my package'", "parameters": { "type": "object", "properties": { "order_id": { "type": "string", "description": "The customer's order ID.", }, }, "required": ["order_id"], "additionalProperties": false, } }
The text was updated successfully, but these errors were encountered: