> ## Documentation Index
> Fetch the complete documentation index at: https://docs.athina.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Completions

> _If you're using OpenAI completions in Python, you can get set up in just **2 minutes**_

#### Supported Models[](#supported-models)

* `text-davinci-003`

<Tabs>
  <Tab title="API Request">
    ### Log via API Request

    See instructions [here](/api-reference/logging/log-via-api-request).
  </Tab>

  <Tab title="Python (Streaming)">
    #### Install the Python SDK

    Run `pip install athina-logger`

    #### Log via Python SDK

    ```python
    from openai import OpenAI
    from athina_logger.log_stream_inference.openai_completion_stream import LogOpenAiCompletionStreamInference
    from athina_logger.api_key import AthinaApiKey
    from athina_logger.exception.custom_exception import CustomException

    client = OpenAI(api_key=os.getenv('OPENAI_API_KEY'))
    AthinaApiKey.set_api_key('ATHINA_API_KEY')

    # Using python openai SDK
    def stream_openai_completion_response(user_query, prompt):
    	response = client.completions.create(
    		model='text-davinci-003',
    		prompt=prompt,
    		stream=True,
    	)
    	logger = LogOpenAiCompletionStreamInference(
    		prompt=prompt,
    		language_model_id="text-davinci-003",
    		prompt_slug="customer_query",
    		context=context, # OPTIONAL
    		response_time=response_time_ms, # OPTIONAL
    		customer_id="stripe", # OPTIONAL
    		customer_user_id="shiv@athina.ai", # OPTIONAL
    		session_id="c45g-1234-s6g4-43d3", # OPTIONAL
    		user_query=user_query, # OPTIONAL
    		environment="production", # OPTIONAL
    		external_reference_id="5e838eaf-7dd0-4b6f-a32c-26110dd54e58", # OPTIONAL; If passed, should be unique across all inference calls
    		custom_attributes={
                "name": "John Doe"
            } # OPTIONAL;
    	)

    	# Here are 2 ways to log openai chat streams
    	# OPTION 1
    	try:
    		for chunk in response:
    			logger.collect_stream_inference_by_chunk(chunk)
    		logger.log_stream_inference()
    	except Exception as e:
    		if isinstance(e, CustomException):
    			print(e.status_code)
    			print(e.message)
    		else:
    			print(e)


    	# OPTION 2
    	try:
    		logger.collect_stream_inference(response)
    		logger.log_stream_inference()
    	except Exception as e:
    		if isinstance(e, CustomException):
    			print(e.status_code)
    			print(e.message)
    		else:
    			print(e)

    # Using OpenAI API call and SSE
    def stream_openai_completion_response_with_openai_api(user_query, prompt):
    	reqUrl = 'https://api.openai.com/v1/completions'
    	reqHeaders = {
    		'Accept': 'text/event-stream',
    		'Authorization': 'Bearer ' + 'OPENAI_API_KEY'
    	}
    	reqBody = {
    		"model": "text-davinci-003",
    		"prompt": prompt,
    		"stream": True,
    	}
    	request = requests.post(reqUrl, stream=True,
    							headers=reqHeaders, json=reqBody)
    	logger = LogOpenAiCompletionStreamInference(
    		prompt=prompt,
    		language_model_id="text-davinci-003",
    		prompt_slug="customer_query",
    		context=context, # OPTIONAL
    		response_time=response_time_ms, # OPTIONAL
    		customer_id="stripe", # OPTIONAL
    		customer_user_id="shiv@athina.ai", # OPTIONAL
    		session_id="c45g-1234-s6g4-43d3", # OPTIONAL
    		user_query=user_query, # OPTIONAL
    		environment="production", # OPTIONAL
    		external_reference_id="5e838eaf-7dd0-4b6f-a32c-26110dd54e58", # OPTIONAL; If passed, should be unique across all inference calls
    		custom_attributes={
                "name": "John Doe"
            } # OPTIONAL;
    	)
    	client = sseclient.SSEClient(request)
    	try:
    		for event in client.events():
    			if event.data != '[DONE]':
    				logger.collect_stream_inference_by_chunk(json.loads(event.data))
    		logger.log_stream_inference()
    	except Exception as e:
    		if isinstance(e, CustomException):
    			print(e.status_code)
    			print(e.message)
    		else:
    			print(e)

    ```
  </Tab>
</Tabs>

## Not using Python?[](#not-using-python)

Reach out to us at [hello@athina.ai](mailto:hello@athina.ai) - we're happy to add support for other stacks as well if we hear from you.