pip install orquesta-sdk

import time
import cohere
from orquesta_sdk import OrquestaClient, OrquestaClientOptions
from orquesta_sdk.helpers import orquesta_cohere_parameters_mapper
from orquesta_sdk.prompts import OrquestaPromptMetrics


# Initialize Orquesta client
from orquesta_sdk import OrquestaClient, OrquestaClientOptions

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="data_completion", # key of prompt to retrieve
  context={ # the context for the specific prompt variant
    "environments": ["test"]
  },
  variables={  }
)

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

co = cohere.Client('COHERE-API-KEY') # Insert your Cohere API key
completion = co.generate(
    **orquesta_cohere_parameters_mapper(prompt.value),
    model=prompt.value.get("model"),
    prompt=prompt.value.get('prompt'),
)

# 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}')

# Tokenize responses
prompt_tokenization = co.tokenize(prompt.value.get('prompt'))
completion_tokenization = co.tokenize(completion.generations[0].text)

prompt_tokens = len(prompt_tokenization.tokens)
completion_tokens = len(completion_tokenization.tokens)
total_tokens = prompt_tokens + completion_tokens

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

prompt.add_metrics(metrics=metrics)