mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 14:27:58 +00:00
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
46 lines
1.7 KiB
JSON
46 lines
1.7 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.together.xyz/v1/v1/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"prompt": "Respond to this question and explain your answer. Complete the sentence using one word: Roses are red, violets are ",
|
|
"stream": false,
|
|
"extra_body": {}
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "rec-565b1072cb9d",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " _______________________. \n\n## Step 1: Identify the traditional completion of the sentence.\nThe traditional completion of the sentence \"Roses are red, violets are...\" is based on a well-known poem.\n\n## Step 2: Recall the poem.\nThe poem states, \"Roses are red, violets are blue...\"\n\n## Step 3: Determine the word that completes the sentence.\nBased on the poem, the word that completes the sentence is \"blue\".\n\nThe final answer is: $\\boxed{blue}$",
|
|
"seed": 4892505926413923000
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"object": "text.completion",
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 106,
|
|
"prompt_tokens": 25,
|
|
"total_tokens": 131,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null,
|
|
"cached_tokens": 0
|
|
},
|
|
"prompt": []
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|