mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
27d866795c
This PR significantly refactors the Integration Tests workflow. The main goal behind the PR was to enable recording of vision tests which were never run as part of our CI ever before. During debugging, I ended up making several other changes refactoring and hopefully increasing the robustness of the workflow. After doing the experiments, I have updated the trigger event to be `pull_request_target` so this workflow can get write permissions by default but it will run with source code from the base (main) branch in the source repository only. If you do change the workflow, you'd need to experiment using the `workflow_dispatch` triggers. This should not be news to anyone using Github Actions (except me!) It is likely to be a little rocky though while I learn more about GitHub Actions, etc. Please be patient :) --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
221 lines
8 KiB
JSON
221 lines
8 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_weather\",\n \"description\": \"Get the current weather\",\n \"parameters\": {\n \"type\": \"dict\",\n \"required\": [\"location\"],\n \"properties\": {\n \"location\": {\n \"type\": \"string\",\n \"description\": \"The city and state (both required), e.g. San Francisco, CA.\"\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.\nPretend you are a weather assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat's the weather like in San Francisco?<|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": "2025-07-31T17:54:04.749672905Z",
|
|
"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": "2025-07-31T17:54:04.935716874Z",
|
|
"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": "get",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-07-31T17:54:05.124992167Z",
|
|
"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": "_weather",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-07-31T17:54:05.313306567Z",
|
|
"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": "(location",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-07-31T17:54:05.496860421Z",
|
|
"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": "2025-07-31T17:54:05.682903521Z",
|
|
"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": "San",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-07-31T17:54:05.868324667Z",
|
|
"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": " Francisco",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-07-31T17:54:06.061112692Z",
|
|
"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": "2025-07-31T17:54:06.268369491Z",
|
|
"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": " CA",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-07-31T17:54:06.47768613Z",
|
|
"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": "2025-07-31T17:54:06.671958182Z",
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"total_duration": 2151822386,
|
|
"load_duration": 44157323,
|
|
"prompt_eval_count": 324,
|
|
"prompt_eval_duration": 183972482,
|
|
"eval_count": 11,
|
|
"eval_duration": 1923143597,
|
|
"response": "",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|