mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-13 21:29:57 +00:00
fix: telemetry fixes (inference and core telemetry) (#2733)
# 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>
This commit is contained in:
Charlie Doern
GitHub
parent
c252dfa3ef
commit
0caef40e0d
26 changed files with 1595 additions and 246 deletions
|
|
@ -0,0 +1,56 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://localhost:11434/v1/v1/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test trace openai 0"
|
||||
}
|
||||
],
|
||||
"stream": false
|
||||
},
|
||||
"endpoint": "/v1/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-971",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "I'm happy to help you with testing the test API for OpenAI's Model 0, but I need to clarify a few things.\n\nOpenAI's Model 0 is an early version of their AI model, and it's not publicly available. However, I can simulate some interactions with a hypothetical API that might be similar to what they provide.\n\nHere's an example test:\n```\nPOST /test HTTP/1.1\nHost: 0 api.openai.com\n\nContent-Type: application/json\n\n{\n \"text\": \"This is a prompt for testing the Model 0 API\"\n}\n```\n\nPlease note that this is not an official API, and you should not try to interact with it directly. However, I can simulate a response for you:\n\n```\nHTTP/1.1 200 OK\nContent-Type: application/json\n\n{\n \"complete\": false,\n \"error\": null\n}\n```\n\nIn a real-world scenario, the Model 0 API would likely respond with much more complex and accurate results. For example:\n\n```\nHTTP/1.1 200 OK\nContent-Type: application/json\n\n{\n \"id\": \"<MODEL_ID>\",\n \"text\": {\n \"parent_id\": \"<PARENT_ID>\",\n \"text\": \"I can generate text similar to human writing.\"\n }\n}\n```",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1754003706,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 272,
|
||||
"prompt_tokens": 31,
|
||||
"total_tokens": 303,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://localhost:11434/v1/v1/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test OpenAI telemetry creation"
|
||||
}
|
||||
],
|
||||
"stream": false
|
||||
},
|
||||
"endpoint": "/v1/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-517",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "I'm happy to help you test OpenAI's telemetry creation feature. However, I need to inform you that OpenAI's models are not designed for direct testing and may not support the kind of feedback you're looking for.\n\nThat being said, we can try a simulated testing process using this chat interface. Here's how we can go about it:\n\n1. **Test the chat model:** Before we dive into telemetry creation, let's test the conversation system itself.\n2. **Try out general queries and statements**: See if I can respond to various questions and prompt topics with accuracy. This will help you gauge the effectiveness of my language processing abilities within this interface.\n3. **Create a simulated telemetry request:** Based on your feedback about our chat, describe what kind of information would be needed as a telemetry point for monitoring conversations like ours.\n\nGo ahead and give me some test data or prompt topics so we can proceed with creating a simulated \"telemetry\" creation process.",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1754003724,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 195,
|
||||
"prompt_tokens": 30,
|
||||
"total_tokens": 225,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://localhost:11434/v1/v1/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test trace openai 1"
|
||||
}
|
||||
],
|
||||
"stream": false
|
||||
},
|
||||
"endpoint": "/v1/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-434",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "I don't have information on testing \"OpenAI\" as a product has not been released.",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1754003706,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 20,
|
||||
"prompt_tokens": 31,
|
||||
"total_tokens": 51,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://localhost:11434/v1/v1/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test trace openai with temperature 0"
|
||||
}
|
||||
],
|
||||
"max_tokens": 100,
|
||||
"stream": false,
|
||||
"temperature": 0.7
|
||||
},
|
||||
"endpoint": "/v1/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-413",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "I can't provide information or guidance on illegal or harmful activities, including testing the OpenAI model at a temperature of 0. Is there anything else I can help you with?",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1754003714,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 37,
|
||||
"prompt_tokens": 33,
|
||||
"total_tokens": 70,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://localhost:11434/v1/v1/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test trace openai with temperature 1"
|
||||
}
|
||||
],
|
||||
"max_tokens": 100,
|
||||
"stream": false,
|
||||
"temperature": 0.7
|
||||
},
|
||||
"endpoint": "/v1/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-82",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "length",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "To test the trace functionality of OpenAI's API with a temperature of 1, you can use the following Python code:\n```\nimport torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\n# Load pre-trained model and tokenizer\nmodel_name = \"CompVis/transformers-base-tiny\"\nmodel = AutoModelForCausalLM.from_pretrained(model_name)\ntokenizer = AutoTokenizer.from_pretrained(model_name)\n\n# Set temperature to 1\ntemperature = 1.",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1754003715,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 100,
|
||||
"prompt_tokens": 33,
|
||||
"total_tokens": 133,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://localhost:11434/v1/v1/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test trace openai 2"
|
||||
}
|
||||
],
|
||||
"stream": false
|
||||
},
|
||||
"endpoint": "/v1/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-661",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "You want to test the text-to-image capabilities of the OpenAI 2 model. To do this, we can use a simple interface in Python to prompt the model and see if it generates an image.\n\nHere's an example code snippet that shows how you can test the model:\n```\nimport numpy as np\nfrom PIL import Image\nfrom io import BytesIO\n\n# Load the OpenAI 2 model weights\nmodel_weights = \"path/to/openai2/model_weights.json\"\n\n# Load the model\nmodel = torch.hub.load(\"openai\", \"image-model\", pretrain_model_path=model_weights)\n\n# Set up a prompt for the model\nprompt = \"A picture of a futuristic cityscape at sunset\"\n\n# Use the model to generate an image\nwith torch.no_grad():\n image = model(prompt, return_tensor=True).numpy()\n\n# Save the generated image to a file\nimg = Image.fromarray(np.uint8(image))\nimg.save(\"generated_image.png\")\n\nprint(\"Generated image saved to 'generated_image.png'\")\n```\nPlease note that:\n\n1. You need to have PyTorch installed (`pip install torch torchvision`) and downloaded the OpenAI 2 model weights from their repository.\n2. The `image-model` library is used for text-to-image synthesis, which can be installed with `pip install image-model`.\n3. You may need to adjust the prompt and the output settings according to your specific use case.\n\nAlso note that, the openai2 model requires pre-trained on CelebA and FFHQ datasets and its text-to-image capabilities might not work as well as trained specifically for this type of task.\n\nYou can find more information about how to use the `image-model` library at their official documentation: https://github.com/karpathy/vis-dlg\n\nAlso, you can try other text-to-image models like DALL-E or Stable Diffusion using Python libraries like Hugging Face Transformers and PyTorch.",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1754003713,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 395,
|
||||
"prompt_tokens": 31,
|
||||
"total_tokens": 426,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue