mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-16 06:27:58 +00:00
59 lines
3.5 KiB
JSON
59 lines
3.5 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\nYou are a helpful assistant. You have access to functions, but you should only use them if they are required.\nYou are an expert in composing functions. You are given a question and a set of possible functions.\nBased on the question, you may or may not need to make one function/tool call to achieve the purpose.\n\nIf you decide to invoke any of the function(s), you MUST put it in the format of [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]\nIf you decide to invoke a function, you SHOULD NOT include any other text in the response. besides the function call in the above format.\nFor a boolean parameter, be sure to use `True` or `False` (capitalized) for the value.\n\n\nHere is a list of functions in JSON format that you can invoke.\n\n[\n {\n \"name\": \"get_object_namespace_list\",\n \"description\": \"Get the list of objects in a namespace\",\n \"parameters\": {\n \"type\": \"dict\",\n \"required\": [\"kind\", \"namespace\"],\n \"properties\": {\n \"kind\": {\n \"type\": \"string\",\n \"description\": \"the type of object\"\n },\n \"namespace\": {\n \"type\": \"string\",\n \"description\": \"the name of the namespace\"\n }\n }\n }\n }\n]\n\nYou can answer general questions or invoke tools when necessary.\nIn addition to tool calls, you should also augment your responses by using the tool outputs.\nYou are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat pods are in the namespace openshift-lightspeed?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n[get_object_namespace_list(kind=\"pod\", namespace=\"openshift-lightspeed\")]<|eot_id|><|start_header_id|>ipython<|end_header_id|>\n\nthe objects are pod1, pod2, pod3<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
|
|
"options": {
|
|
"temperature": 0.0
|
|
},
|
|
"stream": true
|
|
},
|
|
"endpoint": "/api/generate",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-08-01T20:57:11.920796Z",
|
|
"done": false,
|
|
"done_reason": null,
|
|
"total_duration": null,
|
|
"load_duration": null,
|
|
"prompt_eval_count": null,
|
|
"prompt_eval_duration": null,
|
|
"eval_count": null,
|
|
"eval_duration": null,
|
|
"response": "[]",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-08-01T20:57:11.963674Z",
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"total_duration": 837987583,
|
|
"load_duration": 158475167,
|
|
"prompt_eval_count": 386,
|
|
"prompt_eval_duration": 617000000,
|
|
"eval_count": 2,
|
|
"eval_duration": 60000000,
|
|
"response": "",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|