pip install orquesta-sdk

import os
import time
import openai
from orquesta_sdk import OrquestaClient, OrquestaClientOptions
from orquesta_sdk.helpers import orquesta_openai_parameters_mapper
from orquesta_sdk.prompts import OrquestaPromptMetrics

openai.api_key = "<OPENAI_API_KEY>"

# Initialize Orquesta client
api_key = "<ORQUESTA_API_KEY>"
options = OrquestaClientOptions(
    api_key=api_key,
    ttl=3600
)

client = OrquestaClient(options)

# Query the prompt from Orquesta
prompt = client.prompts.query(
  key="customer-support-chat",
  context={
    "environments": ["test"],
    "country": ["BEL", "NLD"],
    "locale": ["en"],
    "user-segment": ["b2c"]
  },
  variables={ "customer_name": "John" },
  metadata={"user_id":45515}
)

if prompt.has_error:
    print("There was an error while fetching the prompt")

# Start time of the completion request
start_time = time.time()
print(f'Start time: {start_time}')

completion = openai.ChatCompletion.create(
    **orquesta_openai_parameters_mapper(prompt.value),
    model=prompt.value.get("model"),
    messages=prompt.value.get("messages"),
)

# End time of the completion request
end_time = time.time()
print(f'End time: {end_time}')

# Calculate the difference (latency) in milliseconds
latency = (end_time - start_time) * 1000
print(f'Latency is: {latency}')

# Report the metrics back to Orquesta
metrics = OrquestaPromptMetrics(
    economics={
        "total_tokens": completion.usage.get("total_tokens"),
        "completion_tokens": completion.usage.get("completion_tokens"),
        "prompt_tokens": completion.usage.get("prompt_tokens"),
    },
    llm_response=completion.choices[0].message.content,
    latency=latency,
    metadata={
        "finish_reason": completion.choices[0].finish_reason,
    },
)

prompt.add_metrics(metrics=metrics)