mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-22 20:40:00 +00:00
record tool_runtime tests
This commit is contained in:
Ashwin Bharambe
parent
579ff826f7
commit
136451feee
8 changed files with 782 additions and 9 deletions
Binary file not shown.
167
tests/integration/recordings/responses/0ff78129bb3a.json
Normal file
167
tests/integration/recordings/responses/0ff78129bb3a.json
Normal file
|
|
@ -0,0 +1,167 @@
|
||||||
|
{
|
||||||
|
"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\": \"\nReturns 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": "2025-07-29T23:26:18.143606Z",
|
||||||
|
"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": "2025-07-29T23:26:18.186151Z",
|
||||||
|
"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": "2025-07-29T23:26:18.229036Z",
|
||||||
|
"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": "2025-07-29T23:26:18.271516Z",
|
||||||
|
"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": "2025-07-29T23:26:18.316272Z",
|
||||||
|
"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": "2025-07-29T23:26:18.361005Z",
|
||||||
|
"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": "2025-07-29T23:26:18.404689Z",
|
||||||
|
"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": "2025-07-29T23:26:18.447699Z",
|
||||||
|
"done": true,
|
||||||
|
"done_reason": "stop",
|
||||||
|
"total_duration": 456939083,
|
||||||
|
"load_duration": 79653292,
|
||||||
|
"prompt_eval_count": 471,
|
||||||
|
"prompt_eval_duration": 71724667,
|
||||||
|
"eval_count": 8,
|
||||||
|
"eval_duration": 304859000,
|
||||||
|
"response": "",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"is_streaming": true
|
||||||
|
}
|
||||||
|
}
|
||||||
185
tests/integration/recordings/responses/4597743bcd2a.json
Normal file
185
tests/integration/recordings/responses/4597743bcd2a.json
Normal file
|
|
@ -0,0 +1,185 @@
|
||||||
|
{
|
||||||
|
"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\": \"\nReturns 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",
|
||||||
|
"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": "2025-07-29T23:26:17.476678Z",
|
||||||
|
"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": "[g",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:17.520346Z",
|
||||||
|
"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": "reet",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:17.563375Z",
|
||||||
|
"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": "_every",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:17.606256Z",
|
||||||
|
"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": "one",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:17.649215Z",
|
||||||
|
"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": "(url",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:17.692049Z",
|
||||||
|
"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": "2025-07-29T23:26:17.734316Z",
|
||||||
|
"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": "world",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:17.776615Z",
|
||||||
|
"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": "2025-07-29T23:26:17.819266Z",
|
||||||
|
"done": true,
|
||||||
|
"done_reason": "stop",
|
||||||
|
"total_duration": 5629478417,
|
||||||
|
"load_duration": 4092162625,
|
||||||
|
"prompt_eval_count": 448,
|
||||||
|
"prompt_eval_duration": 1191158583,
|
||||||
|
"eval_count": 9,
|
||||||
|
"eval_duration": 343915792,
|
||||||
|
"response": "",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"is_streaming": true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
@ -14,7 +14,7 @@
|
||||||
"models": [
|
"models": [
|
||||||
{
|
{
|
||||||
"model": "nomic-embed-text:latest",
|
"model": "nomic-embed-text:latest",
|
||||||
"modified_at": "2025-07-29T14:55:45.755906-07:00",
|
"modified_at": "2025-07-29T16:26:10.815830-07:00",
|
||||||
"digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f",
|
"digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f",
|
||||||
"size": 274302450,
|
"size": 274302450,
|
||||||
"details": {
|
"details": {
|
||||||
|
|
|
||||||
347
tests/integration/recordings/responses/c7582fa7c2c4.json
Normal file
347
tests/integration/recordings/responses/c7582fa7c2c4.json
Normal file
|
|
@ -0,0 +1,347 @@
|
||||||
|
{
|
||||||
|
"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\": \"\nReturns 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\nHow can I assist you further?<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat is the boiling point of polyjuice? Use tools to answer.<|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": "2025-07-29T23:26:18.64197Z",
|
||||||
|
"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": "2025-07-29T23:26:18.687885Z",
|
||||||
|
"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": "2025-07-29T23:26:18.73112Z",
|
||||||
|
"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": "_bo",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:18.774191Z",
|
||||||
|
"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": "iling",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:18.816695Z",
|
||||||
|
"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": "2025-07-29T23:26:18.859121Z",
|
||||||
|
"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": "2025-07-29T23:26:18.901585Z",
|
||||||
|
"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": "liquid",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:18.943788Z",
|
||||||
|
"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": "_name",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:18.986429Z",
|
||||||
|
"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": "2025-07-29T23:26:19.029894Z",
|
||||||
|
"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": "2025-07-29T23:26:19.073113Z",
|
||||||
|
"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": "2025-07-29T23:26:19.116671Z",
|
||||||
|
"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": "2025-07-29T23:26:19.159456Z",
|
||||||
|
"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": "2025-07-29T23:26:19.203354Z",
|
||||||
|
"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": " c",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:19.246192Z",
|
||||||
|
"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": "elsius",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:19.290499Z",
|
||||||
|
"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": "=True",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:3b-instruct-fp16",
|
||||||
|
"created_at": "2025-07-29T23:26:19.334562Z",
|
||||||
|
"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": "2025-07-29T23:26:19.380415Z",
|
||||||
|
"done": true,
|
||||||
|
"done_reason": "stop",
|
||||||
|
"total_duration": 881889250,
|
||||||
|
"load_duration": 69966916,
|
||||||
|
"prompt_eval_count": 503,
|
||||||
|
"prompt_eval_duration": 70368167,
|
||||||
|
"eval_count": 18,
|
||||||
|
"eval_duration": 740885458,
|
||||||
|
"response": "",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"is_streaming": true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
@ -11,7 +11,26 @@
|
||||||
"body": {
|
"body": {
|
||||||
"__type__": "ollama._types.ProcessResponse",
|
"__type__": "ollama._types.ProcessResponse",
|
||||||
"__data__": {
|
"__data__": {
|
||||||
"models": []
|
"models": [
|
||||||
|
{
|
||||||
|
"model": "llama3.2:1b",
|
||||||
|
"name": "llama3.2:1b",
|
||||||
|
"digest": "baf6a787fdffd633537aa2eb51cfd54cb93ff08e28040095462bb63daf552878",
|
||||||
|
"expires_at": "2025-07-29T16:28:09.564177-07:00",
|
||||||
|
"size": 2770397184,
|
||||||
|
"size_vram": 2770397184,
|
||||||
|
"details": {
|
||||||
|
"parent_model": "",
|
||||||
|
"format": "gguf",
|
||||||
|
"family": "llama",
|
||||||
|
"families": [
|
||||||
|
"llama"
|
||||||
|
],
|
||||||
|
"parameter_size": "1.2B",
|
||||||
|
"quantization_level": "Q8_0"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
]
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"is_streaming": false
|
"is_streaming": false
|
||||||
|
|
|
||||||
59
tests/integration/recordings/responses/f3c3afbd9b7e.json
Normal file
59
tests/integration/recordings/responses/f3c3afbd9b7e.json
Normal file
|
|
@ -0,0 +1,59 @@
|
||||||
|
{
|
||||||
|
"request": {
|
||||||
|
"method": "POST",
|
||||||
|
"url": "http://localhost:11434/api/generate",
|
||||||
|
"headers": {},
|
||||||
|
"body": {
|
||||||
|
"model": "llama3.2:1b",
|
||||||
|
"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\": \"\nReturns 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",
|
||||||
|
"options": {
|
||||||
|
"temperature": 0.0
|
||||||
|
},
|
||||||
|
"stream": true
|
||||||
|
},
|
||||||
|
"endpoint": "/api/generate",
|
||||||
|
"model": "llama3.2:1b"
|
||||||
|
},
|
||||||
|
"response": {
|
||||||
|
"body": [
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:1b",
|
||||||
|
"created_at": "2025-07-29T23:23:09.553247Z",
|
||||||
|
"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": "Hi",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"__type__": "ollama._types.GenerateResponse",
|
||||||
|
"__data__": {
|
||||||
|
"model": "llama3.2:1b",
|
||||||
|
"created_at": "2025-07-29T23:23:09.564069Z",
|
||||||
|
"done": true,
|
||||||
|
"done_reason": "stop",
|
||||||
|
"total_duration": 2125493250,
|
||||||
|
"load_duration": 1610279708,
|
||||||
|
"prompt_eval_count": 448,
|
||||||
|
"prompt_eval_duration": 502413125,
|
||||||
|
"eval_count": 2,
|
||||||
|
"eval_duration": 11573709,
|
||||||
|
"response": "",
|
||||||
|
"thinking": null,
|
||||||
|
"context": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"is_streaming": true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
@ -24,7 +24,7 @@ def mcp_server():
|
||||||
yield mcp_server_info
|
yield mcp_server_info
|
||||||
|
|
||||||
|
|
||||||
def test_mcp_invocation(llama_stack_client, mcp_server):
|
def test_mcp_invocation(llama_stack_client, text_model_id, mcp_server):
|
||||||
if not isinstance(llama_stack_client, LlamaStackAsLibraryClient):
|
if not isinstance(llama_stack_client, LlamaStackAsLibraryClient):
|
||||||
pytest.skip("The local MCP server only reliably reachable from library client.")
|
pytest.skip("The local MCP server only reliably reachable from library client.")
|
||||||
|
|
||||||
|
|
@ -69,14 +69,10 @@ def test_mcp_invocation(llama_stack_client, mcp_server):
|
||||||
assert content[0].type == "text"
|
assert content[0].type == "text"
|
||||||
assert content[0].text == "Hello, world!"
|
assert content[0].text == "Hello, world!"
|
||||||
|
|
||||||
models = [
|
print(f"Using model: {text_model_id}")
|
||||||
m for m in llama_stack_client.models.list() if m.model_type == ModelType.llm and "guard" not in m.identifier
|
|
||||||
]
|
|
||||||
model_id = models[0].identifier
|
|
||||||
print(f"Using model: {model_id}")
|
|
||||||
agent = Agent(
|
agent = Agent(
|
||||||
client=llama_stack_client,
|
client=llama_stack_client,
|
||||||
model=model_id,
|
model=text_model_id,
|
||||||
instructions="You are a helpful assistant.",
|
instructions="You are a helpful assistant.",
|
||||||
tools=[test_toolgroup_id],
|
tools=[test_toolgroup_id],
|
||||||
)
|
)
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue