When using tools in POST [/chat/completions?api-version=2024-06-01], the logprobs collection is empty ~
If i remove the “tools” array from the input the logprobs is populated.
Could you please add support for logprobs when tools array is set?
{
"logprobs": true,
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Rephrase this text in one sentence: Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be equally well applied to other tasks like clustering or reranking. This makes progress in the field difficult to track, as various models are constantly being proposed without proper evaluation. To solve this problem, we introduce the Massive Text Embedding Benchmark (MTEB). MTEB spans 8 embedding tasks covering a total of 58 datasets and 112 languages. Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks. This suggests that the field has yet to converge on a universal text embedding method and scale it up sufficiently to provide state-of-the-art results on all embedding tasks"
}
],
"temperature": 0.0,
"seed": 10,
"tools": [
{
"type": "function",
"function": {
"name": "super_tool",
"description": "tool solves everything!",
"parameters": {
"type": "object",
"properties": {
"task_description": {
"type": "string",
"description": "The description of task to do"
}
},
"required": ["task_description"],
"additionalProperties": false
}
}
}
]
}
Response:
{
"choices": [
{
"content_filter_results": {},
"finish_reason": "tool_calls",
"index": 0,
"logprobs": {
"content": null
},
"message": {
"content": null,
"role": "assistant",
"tool_calls": [
{
"function": {
"arguments": "{\"task_description\":\"Text embeddings are often evaluated on limited datasets from a single task, making it unclear if state-of-the-art embeddings for semantic textual similarity can be applied to other tasks like clustering or reranking, which complicates tracking progress in the field; to address this, we introduce the Massive Text Embedding Benchmark (MTEB), covering 8 tasks, 58 datasets, and 112 languages, and through benchmarking 33 models, we find no single method excels across all tasks, indicating the need for a universal text embedding method.\"}",
"name": "super_tool"
},
"id": "call_o6KYHMeWsylddddd",
"type": "function"
}
]
}
}
],
"created": 1729712630,
"id": "chatcmpl-ALbYkQXefFF8CmOUdhLvPaO2v888",
"model": "gpt-4o-2024-05-13",
"object": "chat.completion",
"prompt_filter_results": [
{
"prompt_index": 0,
"content_filter_results": {
"hate": {
"filtered": false,
"severity": "safe"
},
"jailbreak": {
"filtered": false,
"detected": false
},
"self_harm": {
"filtered": false,
"severity": "safe"
},
"sexual": {
"filtered": false,
"severity": "safe"
},
"violence": {
"filtered": false,
"severity": "safe"
}
}
}
],
"system_fingerprint": "fp_678dddd",
"usage": {
"completion_tokens": 119,
"prompt_tokens": 245,
"total_tokens": 364
}
}