mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-15 14:08:00 +00:00
0caef40e0d
# What does this PR do? I found a few issues while adding new metrics for various APIs: currently metrics are only propagated in `chat_completion` and `completion` since most providers use the `openai_..` routes as the default in `llama-stack-client inference chat-completion`, metrics are currently not working as expected. in order to get them working the following had to be done: 1. get the completion as usual 2. use new `openai_` versions of the metric gathering functions which use `.usage` from the `OpenAI..` response types to gather the metrics which are already populated. 3. define a `stream_generator` which counts the tokens and computes the metrics (only for stream=True) 5. add metrics to response NOTE: I could not add metrics to `openai_completion` where stream=True because that ONLY returns an `OpenAICompletion` not an AsyncGenerator that we can manipulate. acquire the lock, and add event to the span as the other `_log_...` methods do some new output: `llama-stack-client inference chat-completion --message hi` <img width="2416" height="425" alt="Screenshot 2025-07-16 at 8 28 20 AM" src="https://github.com/user-attachments/assets/ccdf1643-a184-4ddd-9641-d426c4d51326" /> and in the client: <img width="763" height="319" alt="Screenshot 2025-07-16 at 8 28 32 AM" src="https://github.com/user-attachments/assets/6bceb811-5201-47e9-9e16-8130f0d60007" /> these were not previously being recorded nor were they being printed to the server due to the improper console sink handling --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
56 lines
2 KiB
JSON
56 lines
2 KiB
JSON
{
|
|
"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 1"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "chatcmpl-64",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "You want to test the capabilities of the OpenAI Text-to-Text model (also known as T0).\n\nPlease note that I'll be using a pre-trained model, so my responses might not be entirely customized to your specific prompt or context. That being said, I'll do my best to mimic the behavior of the original model.\n\nWhat would you like to test or ask? Please provide a prompt or question, and I'll respond accordingly.\n\n(Note: if you'd like to run a longer experiment or try out specific models like text completion or code generation, feel free to let me know and we can figure out a way to collaborate.)",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 1754510052,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 129,
|
|
"prompt_tokens": 31,
|
|
"total_tokens": 160,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|