Prompt evaluation

# Load env variables and create client
from anthropic import AnthropicVertex
client = AnthropicVertex(region="global", project_id="<YOUR PROJECT ID>")
model = "claude-sonnet-4@20250514"
# Helper functions
def add_user_message(messages, text):
    user_message = {"role": "user", "content": text}
    messages.append(user_message)
def add_assistant_message(messages, text):
    assistant_message = {"role": "assistant", "content": text}
    messages.append(assistant_message)
def chat(messages, system=None, temperature=1.0, stop_sequences=[]):
    params = {
        "model": model,
        "max_tokens": 1000,
        "messages": messages,
        "temperature": temperature,
        "stop_sequences": stop_sequences,
    }
    if system:
        params["system"] = system
    message = client.messages.create(**params)
    return message.content[0].text
import json
def generate_dataset():
    prompt = """
Generate a evaluation dataset for a prompt evaluation. The dataset will be used to evaluate prompts
that generate Python, JSON, or Regex specifically for AWS-related tasks. Generate an array of JSON objects,
each representing task that requires Python, JSON, or a Regex to complete.
Example output:
```json
[
    {
        "task": "Description of task",
    },
    ...additional
]
```
* Focus on tasks that can be solved by writing a single Python function, a single JSON object, or a regular expression.
* Focus on tasks that do not require writing much code
Please generate 3 objects.
"""