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.

Duration

11s

Input Tokens

89765

Output Tokens

441

Cost

$0.28

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 function created to identify the user intent in the blogpost 'Agentic customer service chatbot with tools, tracing and evals' is called **`determine_intent`**.

Here is the function signature as shown in the blog:

```python
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
```

This function takes a `messages` parameter (the conversation history) and uses `opper.call` to classify the user's intent into one of three categories: `get_order_status`, `query_products`, or `unsupported`.