Context Reasoning

Context understanding and reasoning tasks test accurate answers grounded in provided context. This capability is essential for knowledge-base support bots, policy lookup systems, and internal knowledge Q&A applications. Models are evaluated on their ability to provide accurate answers that are properly grounded in the given context rather than hallucinating information.

100
Duration
27s
Input Tokens
78964
Output Tokens
252
Cost
$0.00
Context
Input
In the blogpost 'Agentic customer service chatbot with tools, tracing and evals' a python function is created to identify the user intent. What is the name of this function? def name_of_function(messages)
Expected output
determine_intent
Model output
The name of the function created to identify the user intent in the blog post 'Agentic customer service chatbot with tools, tracing and evals' is determine_intent. The Python definition is:
def determine_intent(messages):
    intent, _ = opper.call(
        name="determine_intent",
        instructions="Analyze the user message and determine their intent. Supported intents are get_order_status and query products.",
        input={"messages": messages},
        output_type=IntentClassification
    )
    return intent