llama-stack-mirror/tests/integration/recordings/responses/9c140a29ae09.json
Ashwin Bharambe 27d866795c
feat(ci): add support for running vision inference tests (#2972)
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>
2025-07-31 11:50:42 -07:00

258 lines
9.6 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_boiling_point\",\n \"description\": \"Returns the boiling point of a liquid in Celcius or Fahrenheit.\",\n \"parameters\": {\n \"type\": \"dict\",\n \"required\": [\"liquid_name\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"str\",\n \"description\": \"The name of the liquid\"\n },\n \"celcius\": {\n \"type\": \"bool\",\n \"description\": \"Whether to return the boiling point in Celcius\",\n \"default\": \"True\"\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\nYou MUST use one of the provided functions/tools to answer the user query.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat is the boiling point of the liquid polyjuice in celsius?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n[get_boiling_point(liquid_name=\"polyjuice\", celcius=True)]<|eot_id|><|start_header_id|>ipython<|end_header_id|>\n\n-100<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"options": {
"temperature": 0.0001,
"top_p": 0.9
},
"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": "2025-07-31T17:44:59.929905409Z",
"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": "The",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:00.110734553Z",
"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": " boiling",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:00.290949416Z",
"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": " point",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:00.475960339Z",
"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": " of",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:00.659481498Z",
"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": " poly",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:00.843632147Z",
"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": "ju",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:01.033425275Z",
"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": "ice",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:01.224890954Z",
"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": " is",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:01.412700377Z",
"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": "2025-07-31T17:45:01.602294122Z",
"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": "100",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:01.79213394Z",
"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": "\u00b0C",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-31T17:45:01.982631333Z",
"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": "2025-07-31T17:45:02.172457365Z",
"done": true,
"done_reason": "stop",
"total_duration": 4304742260,
"load_duration": 41766451,
"prompt_eval_count": 415,
"prompt_eval_duration": 2018894885,
"eval_count": 13,
"eval_duration": 2243484258,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}