mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-22 12:56:17 +00:00
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / generate-matrix (push) Successful in 3s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 3s
API Conformance Tests / check-schema-compatibility (push) Successful in 15s
Python Package Build Test / build (3.12) (push) Successful in 17s
Python Package Build Test / build (3.13) (push) Successful in 18s
Test External API and Providers / test-external (venv) (push) Failing after 28s
Vector IO Integration Tests / test-matrix (push) Failing after 43s
UI Tests / ui-tests (22) (push) Successful in 52s
Unit Tests / unit-tests (3.13) (push) Failing after 1m45s
Unit Tests / unit-tests (3.12) (push) Failing after 1m58s
Pre-commit / pre-commit (22) (push) Successful in 3m9s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4m5s
# Problem As an Application Developer, I want to use the include parameter with the value message.output_text.logprobs, so that I can receive log probabilities for output tokens to assess the model's confidence in its response. # What does this PR do? - Updates the include parameter in various resource definitions - Updates the inline provider to return logprobs when "message.output_text.logprobs" is passed in the include parameter - Converts the logprobs returned by the inference provider from chat completion format to responses format Closes #[4260](https://github.com/llamastack/llama-stack/issues/4260) ## Test Plan - Created a script to explore OpenAI behavior: https://github.com/s-akhtar-baig/llama-stack-examples/blob/main/responses/src/include.py - Added integration tests and new recordings --------- Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
345 lines
9.7 KiB
JSON
Generated
345 lines
9.7 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/responses/test_basic_responses.py::test_include_logprobs_with_function_tools[txt=openai/gpt-4o]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.openai.com/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "gpt-4o",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "What is the weather in Paris?"
|
|
}
|
|
],
|
|
"logprobs": true,
|
|
"stream": true,
|
|
"stream_options": {
|
|
"include_usage": true
|
|
},
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"type": "function",
|
|
"name": "get_weather",
|
|
"description": "Get weather information for a specified location",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"location": {
|
|
"type": "string",
|
|
"description": "The city name (e.g., 'New York', 'London')"
|
|
}
|
|
}
|
|
},
|
|
"strict": null
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "gpt-4o"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-a6c5e729150f",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": "call_8T1tTdWOywKWs4tYSzyflftR",
|
|
"function": {
|
|
"arguments": "",
|
|
"name": "get_weather"
|
|
},
|
|
"type": "function"
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": null,
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_e819e3438b",
|
|
"usage": null,
|
|
"obfuscation": "2U536HpxwFMNHw"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-a6c5e729150f",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "{\"",
|
|
"name": null
|
|
},
|
|
"type": null
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": null,
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_e819e3438b",
|
|
"usage": null,
|
|
"obfuscation": "LDpoCusy"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-a6c5e729150f",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "location",
|
|
"name": null
|
|
},
|
|
"type": null
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": null,
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_e819e3438b",
|
|
"usage": null,
|
|
"obfuscation": "X7q"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-a6c5e729150f",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "\":\"",
|
|
"name": null
|
|
},
|
|
"type": null
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": null,
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_e819e3438b",
|
|
"usage": null,
|
|
"obfuscation": "TMTYo8"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-a6c5e729150f",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "Paris",
|
|
"name": null
|
|
},
|
|
"type": null
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": null,
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_e819e3438b",
|
|
"usage": null,
|
|
"obfuscation": "8EmcxX"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-a6c5e729150f",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "\"}",
|
|
"name": null
|
|
},
|
|
"type": null
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": null,
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_e819e3438b",
|
|
"usage": null,
|
|
"obfuscation": "cnMSe1WI"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-a6c5e729150f",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_e819e3438b",
|
|
"usage": null,
|
|
"obfuscation": "fs5p"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-a6c5e729150f",
|
|
"choices": [],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_e819e3438b",
|
|
"usage": {
|
|
"completion_tokens": 14,
|
|
"prompt_tokens": 67,
|
|
"total_tokens": 81,
|
|
"completion_tokens_details": {
|
|
"accepted_prediction_tokens": 0,
|
|
"audio_tokens": 0,
|
|
"reasoning_tokens": 0,
|
|
"rejected_prediction_tokens": 0
|
|
},
|
|
"prompt_tokens_details": {
|
|
"audio_tokens": 0,
|
|
"cached_tokens": 0
|
|
}
|
|
},
|
|
"obfuscation": "xFLK91cW1si1hsA"
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|