mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-07 18:57:21 +00:00
57 lines
3.6 KiB
JSON
Generated
57 lines
3.6 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/telemetry/test_openai_telemetry.py::test_openai_completion_creates_telemetry[txt=ollama/llama3.2:3b-instruct-fp16]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test OpenAI telemetry creation"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-0de60cd6a6ec",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I'm happy to help you with setting up and testing OpenAI's telemetry creation.\n\nOpenAI provides a feature called \"Telemetry\" which allows developers to collect data about their users' interactions with the model. To test this feature, we need to create a simple application that uses the OpenAI API and sends telemetry data to their servers.\n\nHere's an example code in Python that demonstrates how to create a simple telemetry creator:\n\n```python\nimport os\nfrom openai.api import API\n\n# Initialize the OpenAI API client\napi = API(os.environ['OPENAI_API_KEY'])\n\ndef create_user():\n # Create a new user entity\n user_entity = {\n 'id': 'user-123',\n 'name': 'John Doe',\n 'email': 'john.doe@example.com'\n }\n \n # Send the user creation request to OpenAI\n response = api.users.create(user_entity)\n print(f\"User created: {response}\")\n\ndef create_transaction():\n # Create a new transaction entity\n transaction_entity = {\n 'id': 'tran-123',\n 'user_id': 'user-123',\n 'transaction_type': 'query'\n }\n \n # Send the transaction creation request to OpenAI\n response = api.transactions.create(transaction_entity)\n print(f\"Transaction created: {response}\")\n\ndef send_telemetry_data():\n # Create a new telemetry event entity\n telemetry_event_entity = {\n 'id': 'telem-123',\n 'transaction_id': 'tran-123',\n 'data': '{ \"event\": \"test\", \"user_id\": 1 }'\n }\n \n # Send the telemetry data to OpenAI\n response = api.telemetry.create(telemetry_event_entity)\n print(f\"Telemetry event sent: {response}\")\n\n# Test the telemetry creation\ncreate_user()\ncreate_transaction()\nsend_telemetry_data()\n```\n\nMake sure you replace `OPENAI_API_KEY` with your actual API key. Also, ensure that you have the OpenAI API client library installed by running `pip install openai`.\n\nOnce you've created the test code, run it and observe the behavior of the telemetry creation process.\n\nPlease let me know if you need further modifications or assistance!",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 460,
|
|
"prompt_tokens": 30,
|
|
"total_tokens": 490,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|