mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-22 17:46:16 +00:00
ddefd158e9
the integration tests check if all of the metrics we currently support actual are queryable after inference requests this also tests thinks like aggregation, label filtering, etc Signed-off-by: Charlie Doern <cdoern@redhat.com>
39 lines
2.1 KiB
JSON
39 lines
2.1 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/api/generate",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"raw": true,
|
|
"prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nTest metrics generation 1<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
|
|
"options": {
|
|
"temperature": 0.0
|
|
},
|
|
"stream": false
|
|
},
|
|
"endpoint": "/api/generate",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-08-11T15:51:18.170868Z",
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"total_duration": 5240614083,
|
|
"load_duration": 9823416,
|
|
"prompt_eval_count": 21,
|
|
"prompt_eval_duration": 21000000,
|
|
"eval_count": 310,
|
|
"eval_duration": 5209000000,
|
|
"response": "This is the start of a test. I'll provide some sample data and you can try to generate metrics based on it.\n\n**Data:**\n\nLet's say we have a dataset of user interactions with an e-commerce website. The data includes:\n\n| User ID | Product Name | Purchase Date | Quantity | Price |\n| --- | --- | --- | --- | --- |\n| 1 | iPhone 13 | 2022-01-01 | 2 | 999.99 |\n| 1 | MacBook Air | 2022-01-05 | 1 | 1299.99 |\n| 2 | Samsung TV | 2022-01-10 | 3 | 899.99 |\n| 3 | iPhone 13 | 2022-01-15 | 1 | 999.99 |\n| 4 | MacBook Pro | 2022-01-20 | 2 | 1799.99 |\n\n**Task:**\n\nYour task is to generate the following metrics based on this data:\n\n1. Average order value (AOV)\n2. Conversion rate\n3. Average revenue per user (ARPU)\n4. Customer lifetime value (CLV)\n\nPlease provide your answers in a format like this:\n\n| Metric | Value |\n| --- | --- |\n| AOV | 1234.56 |\n| Conversion Rate | 0.25 |\n| ARPU | 1000.00 |\n| CLV | 5000.00 |\n\nGo ahead and generate the metrics!",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|