mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-22 10:36:18 +00:00
ddefd158e9
the integration tests check if all of the metrics we currently support actual are queryable after inference requests this also tests thinks like aggregation, label filtering, etc Signed-off-by: Charlie Doern <cdoern@redhat.com>
56 lines
1.5 KiB
JSON
56 lines
1.5 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "OpenAI test 1"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "chatcmpl-726",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I'm ready to help with the test. What language would you like to use? Would you like to have a conversation, ask questions, or take a specific type of task?",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 1755891519,
|
|
"model": "llama3.2:3b",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 37,
|
|
"prompt_tokens": 30,
|
|
"total_tokens": 67,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|