mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 22:33:48 +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
176 lines
5 KiB
JSON
176 lines
5 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.together.xyz/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "What's the weather in Tokyo? Use the get_weather function to get the weather."
|
|
}
|
|
],
|
|
"stream": true,
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "get_weather",
|
|
"description": "Get the weather in a given city",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"city": {
|
|
"type": "string",
|
|
"description": "The city to get the weather for"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-894fdacb1cfa",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-894fdacb1cfa",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": "call_jy63yt7kp8hfof3sy4pim94o",
|
|
"function": {
|
|
"arguments": "",
|
|
"name": "get_weather"
|
|
},
|
|
"type": "function"
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-894fdacb1cfa",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "{\"city\":\"Tokyo\"}",
|
|
"name": null
|
|
},
|
|
"type": null
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-894fdacb1cfa",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null,
|
|
"token_id": 128008
|
|
},
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "",
|
|
"seed": 1489065696184500700
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 24,
|
|
"prompt_tokens": 193,
|
|
"total_tokens": 217,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null,
|
|
"cached_tokens": 0
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|