mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-15 19:43:05 +00:00
6f1afabcdc
IDs are now deterministic hashes based on request content, and timestamps are normalized to constants, eliminating spurious changes when re-recording tests.
56 lines
1.8 KiB
JSON
56 lines
1.8 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 2"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-dc8120cf0774",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I'm happy to help with your question or task. Please go ahead and ask me anything, and I'll do my best to assist you.\n\nNote: I'll be using the latest version of my knowledge cutoff, which is December 2023.\n\nAlso, please keep in mind that I'm a large language model, I can provide information on a broad range of topics, including science, history, technology, culture, and more. However, my ability to understand and respond to specific questions or requests may be limited by the data I've been trained on.",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 113,
|
|
"prompt_tokens": 30,
|
|
"total_tokens": 143,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|