mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-21 08:03:09 +00:00
943558af36
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 10s
Python Package Build Test / build (3.13) (push) Failing after 10s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 14s
Unit Tests / unit-tests (3.13) (push) Failing after 11s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 20s
Unit Tests / unit-tests (3.12) (push) Failing after 16s
Test External API and Providers / test-external (venv) (push) Failing after 28s
Vector IO Integration Tests / test-matrix (push) Failing after 30s
API Conformance Tests / check-schema-compatibility (push) Successful in 38s
UI Tests / ui-tests (22) (push) Successful in 1m32s
Pre-commit / pre-commit (push) Successful in 3m16s
# What does this PR do? Adds a test and a standardized way to build future tests out for telemetry in llama stack. Contributes to https://github.com/llamastack/llama-stack/issues/3806 ## Test Plan This is the test plan 😎
59 lines
2 KiB
JSON
Generated
59 lines
2 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/telemetry/test_completions.py::test_telemetry_format_completeness[txt=llama3.2:3b-instruct-fp16]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test trace openai with temperature 0.7"
|
|
}
|
|
],
|
|
"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-dba5042d6691",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "To test the \"trace\" functionality of OpenAI's GPT-4 model at a temperature of 0.7, you can follow these steps:\n\n1. First, make sure you have an account with OpenAI and have been granted access to their API.\n\n2. You will need to install the `transformers` library, which is the official library for working with Transformers models like GPT-4:\n\n ```bash\npip install transformers\n```\n\n3. Next, import the necessary",
|
|
"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": 35,
|
|
"total_tokens": 135,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|