mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-27 16:30:25 +00:00
e461246eed
ensure openai completion routes produce metrics in the existing telemetry suite Signed-off-by: Charlie Doern <cdoern@redhat.com>
58 lines
1.9 KiB
JSON
58 lines
1.9 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test trace openai with temperature 0"
|
|
}
|
|
],
|
|
"max_tokens": 100,
|
|
"stream": false,
|
|
"temperature": 0.7
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "chatcmpl-339",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I can guide you through the process, but please note that this is not an official OpenAI API call. OpenAI's API terms and conditions prohibit using their models for malicious purposes.\n\nTo test a model like \"text-temperature\" with a temperature of 0 (i.e., no noise or randomness), we'll need to use a third-party library that connects to the OpenAI API. One such library is `transformers`.\n\nFirst, you need to install the `transformers` and `",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 1754510065,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 100,
|
|
"prompt_tokens": 33,
|
|
"total_tokens": 133,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|