mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
c3d3a0b833
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 4s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 7s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (push) Failing after 7s
Python Package Build Test / build (3.13) (push) Failing after 8s
Python Package Build Test / build (3.12) (push) Failing after 8s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Unit Tests / unit-tests (3.12) (push) Failing after 14s
UI Tests / ui-tests (22) (push) Successful in 1m7s
Pre-commit / pre-commit (push) Successful in 2m34s
One needed to specify record-replay related environment variables for running integration tests. We could not use defaults because integration tests could be run against Ollama instances which could be running different models. For example, text vs vision tests needed separate instances of Ollama because a single instance typically cannot serve both of these models if you assume the standard CI worker configuration on Github. As a result, `client.list()` as returned by the Ollama client would be different between these runs and we'd end up overwriting responses. This PR "solves" it by adding a small amount of complexity -- we store model list responses specially, keyed by the hashes of the models they return. At replay time, we merge all of them and pretend that we have the union of all models available. ## Test Plan Re-recorded all the tests using `scripts/integration-tests.sh --inference-mode record`, including the vision tests.
167 lines
7.3 KiB
JSON
167 lines
7.3 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\": \"greet_everyone\",\n \"description\": \"\",\n \"parameters\": {\n \"type\": \"dict\",\n \"required\": [\"url\"],\n \"properties\": {\n \"url\": {\n \"type\": \"string\",\n \"description\": \"\"\n }\n }\n }\n },\n {\n \"name\": \"get_boiling_point\",\n \"description\": \"\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n \",\n \"parameters\": {\n \"type\": \"dict\",\n \"required\": [\"liquid_name\", \"celsius\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\"\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\nSay hi to the world. Use tools to do so.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n[greet_everyone(url=\"world\")]<|eot_id|><|start_header_id|>ipython<|end_header_id|>\n\nHello, world!<|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": "2025-09-03T17:34:22.916043Z",
|
|
"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": "How",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-09-03T17:34:22.957379Z",
|
|
"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": " can",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-09-03T17:34:23.00029Z",
|
|
"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": " I",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-09-03T17:34:23.043332Z",
|
|
"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": " assist",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-09-03T17:34:23.085324Z",
|
|
"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": " you",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-09-03T17:34:23.128181Z",
|
|
"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": " further",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-09-03T17:34:23.172026Z",
|
|
"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": "2025-09-03T17:34:23.216706Z",
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"total_duration": 516060000,
|
|
"load_duration": 127260334,
|
|
"prompt_eval_count": 479,
|
|
"prompt_eval_duration": 87107292,
|
|
"eval_count": 8,
|
|
"eval_duration": 299381042,
|
|
"response": "",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|