mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 14:43:48 +00:00
045a0c1d57
Uses test_id in request hashes and test-scoped subdirectories to prevent cross-test contamination. Model list endpoints exclude test_id to enable merging recordings from different servers. Additionally, this PR adds a `record-if-missing` mode (which we will use instead of `record` which records everything) which is very useful. 🤖 Co-authored with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude <noreply@anthropic.com>
58 lines
1.9 KiB
JSON
58 lines
1.9 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test trace openai with temperature 1"
|
|
}
|
|
],
|
|
"max_tokens": 100,
|
|
"stream": false,
|
|
"temperature": 0.7
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-e2c9b07709fe",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "To test the prompt understanding of OpenAI's text generation capabilities, I'll simulate a conversation. \n\nYou mentioned testing the model with a temperature setting of 1. The temperature parameter in OpenAI's text models controls the diversity and coherence of generated text.\n\nA temperature of 1 is considered \"colder\" than usual, meaning the model will generate more coherent but potentially less diverse text compared to higher temperatures (e.g., 0.5 or 0.7).\n\nPlease provide a prompt for",
|
|
"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": 100,
|
|
"prompt_tokens": 33,
|
|
"total_tokens": 133,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|