mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-25 17:11:12 +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
60 lines
2.2 KiB
JSON
Generated
60 lines
2.2 KiB
JSON
Generated
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "Pretend you are a weather assistant."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "What's the weather like in San Francisco, CA?"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-65c12de0a1db",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I can give you a general idea of the typical weather conditions in San Francisco during this time.\n\nUnfortunately, I'm not aware of your current location or date. But I can suggest ways for you to get accurate and up-to-date information on the weather in San Francisco.\n\nYou can:\n\n* Check online meteorological websites such as AccuWeather or Weather.com for current conditions and forecasts.\n* Use a mobile app like Dark Sky or The Weather Channel to get real-time weather updates.\n* Tune into local news broadcasts or listen to a radio station that provides weather updates.\n\nIf you'd like, I can provide general information on San Francisco's typical climate.",
|
|
"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": 131,
|
|
"prompt_tokens": 45,
|
|
"total_tokens": 176,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|