mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 03:19:26 +00:00
805abf573f
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>
364 lines
10 KiB
JSON
Generated
364 lines
10 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/responses/test_basic_responses.py::test_include_logprobs_non_streaming[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": "Which planet do humans live on?"
|
|
}
|
|
],
|
|
"logprobs": true,
|
|
"stream": true,
|
|
"stream_options": {
|
|
"include_usage": true
|
|
}
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "gpt-4o"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": [],
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "nhS1O"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "Hum",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": [
|
|
{
|
|
"token": "Hum",
|
|
"bytes": [
|
|
72,
|
|
117,
|
|
109
|
|
],
|
|
"logprob": 0.0,
|
|
"top_logprobs": []
|
|
}
|
|
],
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": ""
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "ans",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": [
|
|
{
|
|
"token": "ans",
|
|
"bytes": [
|
|
97,
|
|
110,
|
|
115
|
|
],
|
|
"logprob": 0.0,
|
|
"top_logprobs": []
|
|
}
|
|
],
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": ""
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " live",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": [
|
|
{
|
|
"token": " live",
|
|
"bytes": [
|
|
32,
|
|
108,
|
|
105,
|
|
118,
|
|
101
|
|
],
|
|
"logprob": -1.2664456789934775e-06,
|
|
"top_logprobs": []
|
|
}
|
|
],
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "t"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " on",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": [
|
|
{
|
|
"token": " on",
|
|
"bytes": [
|
|
32,
|
|
111,
|
|
110
|
|
],
|
|
"logprob": 0.0,
|
|
"top_logprobs": []
|
|
}
|
|
],
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": ""
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " Earth",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": [
|
|
{
|
|
"token": " Earth",
|
|
"bytes": [
|
|
32,
|
|
69,
|
|
97,
|
|
114,
|
|
116,
|
|
104
|
|
],
|
|
"logprob": -0.02083509787917137,
|
|
"top_logprobs": []
|
|
}
|
|
],
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "HqlGFBjvYMrjOfC"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": ".",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"content": [
|
|
{
|
|
"token": ".",
|
|
"bytes": [
|
|
46
|
|
],
|
|
"logprob": -6.869017852295656e-06,
|
|
"top_logprobs": []
|
|
}
|
|
],
|
|
"refusal": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "iHmejH8al8"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "23vTR8FqDi"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-e64dd8ced6be",
|
|
"choices": [],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": {
|
|
"completion_tokens": 6,
|
|
"prompt_tokens": 14,
|
|
"total_tokens": 20,
|
|
"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": ""
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|