mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 06:37:58 +00:00
3f36bfaeaa
IDs are now deterministic hashes based on request content, and timestamps are normalized to constants, eliminating spurious changes when re-recording tests. ## Changes - Updated `inference_recorder.py` to normalize IDs and timestamps during recording - Added `scripts/normalize_recordings.py` utility to re-normalize existing recordings - Created documentation in `tests/integration/recordings/README.md` - Normalized 350 existing recording files
56 lines
2.3 KiB
JSON
56 lines
2.3 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 0"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-4de6877d86fa",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I don't have any information about an \"OpenAI test 0\". It's possible that you may be referring to a specific experiment or task being performed by OpenAI, but without more context, I can only speculate.\n\nHowever, I can tell you that OpenAI is a research organization that has been involved in various projects and tests related to artificial intelligence. If you could provide more context or clarify what you're referring to, I may be able to help further.\n\nIf you're looking for general information about OpenAI, I can try to provide some background on the organization:\n\nOpenAI is a non-profit research organization that was founded in 2015 with the goal of developing and applying advanced artificial intelligence to benefit humanity. The organization has made significant contributions to the field of AI, including the development of the popular language model, ChatGPT.\n\nIf you could provide more context or clarify what you're looking for, I'll do my best to assist you.",
|
|
"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": 194,
|
|
"prompt_tokens": 30,
|
|
"total_tokens": 224,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|