{
  "task": "task_1_plan_generation",
  "prompt_type": "oneshot",
  "domain": "blocksworld",
  "instances": [
    {
      "instance_id": 2,
      "example_instance_ids": [
        1
      ],
      "query": "I am playing with a set of blocks where I need to arrange the blocks into stacks. Here are the actions I can do\n\nPick up a block\nUnstack a block from on top of another block\nPut down a block\nStack a block on top of another block\n\nI have the following restrictions on my actions:\nI can only pick up or unstack one block at a time.\nI can only pick up or unstack a block if my hand is empty.\nI can only pick up a block if the block is on the table and the block is clear. A block is clear if the block has no other blocks on top of it and if the block is not picked up.\nI can only unstack a block from on top of another block if the block I am unstacking was really on top of the other block.\nI can only unstack a block from on top of another block if the block I am unstacking is clear.\nOnce I pick up or unstack a block, I am holding the block.\nI can only put down a block that I am holding.\nI can only stack a block on top of another block if I am holding the block being stacked.\nI can only stack a block on top of another block if the block onto which I am stacking the block is clear.\nOnce I put down or stack a block, my hand becomes empty.\nOnce you stack a block on top of a second block, the second block is no longer clear.\n\n[STATEMENT]\nAs initial conditions I have that, the red block is clear, the blue block is clear, the yellow block is clear, the hand is empty, the blue block is on top of the orange block, the red block is on the table, the orange block is on the table and the yellow block is on the table.\nMy goal is to have that the orange block is on top of the blue block.\n\nMy plan is as follows:\n\n[PLAN]\nunstack the blue block from on top of the orange block\nput down the blue block\npick up the orange block\nstack the orange block on top of the blue block\n[PLAN END]\n\n[STATEMENT]\nAs initial conditions I have that, the red block is clear, the yellow block is clear, the hand is empty, the red block is on top of the blue block, the yellow block is on top of the orange block, the blue block is on the table and the orange block is on the table.\nMy goal is to have that the orange block is on top of the red block.\n\nMy plan is as follows:\n\n[PLAN]",
      "ground_truth_plan": "(unstack yellow orange)\n(put-down yellow)\n(pick-up orange)\n(stack orange red)\n"
    },
    {
      "instance_id": 3,
      "example_instance_ids": [
        2
      ],
      "query": "I am playing with a set of blocks where I need to arrange the blocks into stacks. Here are the actions I can do\n\nPick up a block\nUnstack a block from on top of another block\nPut down a block\nStack a block on top of another block\n\nI have the following restrictions on my actions:\nI can only pick up or unstack one block at a time.\nI can only pick up or unstack a block if my hand is empty.\nI can only pick up a block if the block is on the table and the block is clear. A block is clear if the block has no other blocks on top of it and if the block is not picked up.\nI can only unstack a block from on top of another block if the block I am unstacking was really on top of the other block.\nI can only unstack a block from on top of another block if the block I am unstacking is clear.\nOnce I pick up or unstack a block, I am holding the block.\nI can only put down a block that I am holding.\nI can only stack a block on top of another block if I am holding the block being stacked.\nI can only stack a block on top of another block if the block onto which I am stacking the block is clear.\nOnce I put down or stack a block, my hand becomes empty.\nOnce you stack a block on top of a second block, the second block is no longer clear.\n\n[STATEMENT]\nAs initial conditions I have that, the red block is clear, the yellow block is clear, the hand is empty, the red block is on top of the blue block, the yellow block is on top of the orange block, the blue block is on the table and the orange block is on the table.\nMy goal is to have that the orange block is on top of the red block.\n\nMy plan is as follows:\n\n[PLAN]\nunstack the yellow block from on top of the orange block\nput down the yellow block\npick up the orange block\nstack the orange block on top of the red block\n[PLAN END]\n\n[STATEMENT]\nAs initial conditions I have that, the blue block is clear, the hand is empty, the blue block is on top of the orange block, the orange block is on top of the yellow block, the yellow block is on top of the red block and the red block is on the table.\nMy goal is to have that the red block is on top of the orange block and the yellow block is on top of the red block.\n\nMy plan is as follows:\n\n[PLAN]",
            "ground_truth_plan": "(unstack blue orange)\n(put-down blue)\n(unstack orange yellow)\n(put-down orange)\n(unstack yellow red)\n(stack yellow blue)\n(pick-up red)\n(stack red orange)\n(unstack yellow blue)\n(stack yellow red)\n"
        },
        ...
    ]
}

{
    "id":"modelscope_merge_api_527",
    "conversations":[
        {
            "from":"system",
            "value":"你是达摩院的ModelScopeGPT（魔搭助手），你是个大语言模型， 是2023年达摩院的工程师训练得到的。你有多种能力，可以通过插件集成魔搭社区的模型api来回复用户的问题，还能解答用户使用模型遇到的问题和模型知识相关问答。1. {\"plugin_name\": \"modelscope_text-ie\", \"plugin_owner\": \"ModelScopeGPT\", \"plugin_type\": \"default\", \"plugin_schema_for_model\": {\"name\": \"modelscope_text-ie\", \"description\": \"针对中文的文本，根据schema要抽取的内容，找出其中对应信息，并用json格式展示\", \"url\": \"http://109.199.101.10:1485/\", \"paths\": [{\"name\": \"modelscope_text-ie\", \"model_id\": \"/damo/nlp_structbert_siamese-uie_chinese-base\", \"method\": \"post\", \"description\": \"针对中文的文本，根据schema要抽取的内容，找出其中对应信息，并用json格式展示\", \"parameters\": [{\"name\": \"text\", \"description\": \"用户输入的文本\", \"required\": \"True\"}, {\"name\": \"schema\", \"description\": \"要抽取信息的json表示\", \"required\": \"True\"}]}]}}\n\n2. {\"plugin_name\": \"modelscope_text-ie\", \"plugin_owner\": \"ModelScopeGPT\", \"plugin_type\": \"default\", \"plugin_schema_for_model\": {\"name\": \"modelscope_text-ie\", \"description\": \"针对中文的文本，根据schema要抽取的内容，找出其中对应信息，并用json格式展示\", \"url\": \"http://9.32.64.200:5873/\", \"paths\": [{\"name\": \"modelscope_text-ie\", \"model_id\": \"/damo/nlp_structbert_siamese-uie_chinese-base\", \"method\": \"post\", \"description\": \"针对中文的文本，根据schema要抽取的内容，找出其中对应信息，并用json格式展示\", \"parameters\": [{\"name\": \"text\", \"description\": \"用户输入的文本\", \"required\": \"True\"}, {\"name\": \"schema\", \"description\": \"要抽取信息的json表示\", \"required\": \"True\"}]}]}}\n\n3. {\"plugin_name\": \"modelscope_text-ie\", \"plugin_owner\": \"ModelScopeGPT\", \"plugin_type\": \"default\", \"plugin_schema_for_model\": {\"name\": \"modelscope_text-ie\", \"description\": \"针对中文的文本，根据schema要抽取的内容，找出其中对应信息，并用json格式展示\", \"url\": \"http://54.149.78.185:3979/\", \"paths\": [{\"name\": \"modelscope_text-ie\", \"model_id\": \"/damo/nlp_structbert_siamese-uie_chinese-base\", \"method\": \"post\", \"description\": \"针对中文的文本，根据schema要抽取的内容，找出其中对应信息，并用json格式展示\", \"parameters\": [{\"name\": \"text\", \"description\": \"用户输入的文本\", \"required\": \"True\"}, {\"name\": \"schema\", \"description\": \"要抽取信息的json表示\", \"required\": \"True\"}]}]}}"
        },
        {
            "from":"user",
            "value":"按照给定的schema抽取出下面文本对应的信息\nschema：{\"人物\": null, \"地理位置\": null, \"组织机构\": null}\n近日，美国政府宣布将对中国1000多种商品加征关税，并威胁进一步加征关税。"
        },
        {
            "from":"assistant",
            "value":"<|startofthink|>```JSON\n{\"api_name\": \"modelscope_text-ie\", \"url\": \"http://9.32.64.200:5873/damo/nlp_structbert_siamese-uie_chinese-base\", \"parameters\": {\"text\": \"近日，美国政府宣布将对中国1000多种商品加征关税，并威胁进一步加征关税。\", \"schema\": \"{\\\"人物\\\": null, \\\"地理位置\\\": null, \\\"组织机构\\\": null}\"}}\n```<|endofthink|>\n\n<|startofexec|>```JSON\n{\"人物\": [], \"地理位置\": [\"中国\", \"美国\"], \"组织机构\": []}\n```<|endofexec|>\n信息抽取结果：{\"人物\": [], \"地理位置\": [\"中国\", \"美国\"], \"组织机构\": []}。我使用的模型是ModelScope的'damo/nlp_structbert_siamese-uie_chinese-base'模型。这是一个基于StructBERT预训练模型微调训练的通用信息抽取模型。"
        }
    ]
}

无数据样例，通过搭建网页服务，并评测执行各类任务的效果
可复现并自行采集数据

 {
  "description": "Tell me the number of CPUs.",
  "evaluation": {
    "check": [
      null,
      {
        "language": "python",
        "file": "check/integer-match.py"
      }
    ],
    "example": "nproc"
  },
  "labels": [
    "command",
    "CPU",
    "device",
    "hardware",
    "processor",
    "system"
  ]
},

[ 
  { "from": "human", "loss": null, "value": "You are an assistant that will act like a person, I'will play the role of linux(ubuntu) operating system. Your goal is to implement the operations required by me or answer to the question proposed by me. For each of your turn, you should first think what you should do, and then take exact one of the three actions: \"bash\", \"finish\" or \"answer\". \n\n1. If you think you should execute some bash code, take bash action, and you should print like this:\n\nThink: put your thought here.\n\nAct: bash\n\n```bash\n# put your bash code here\n```\n\n2. If you think you have finished the task, take finish action, and you should print like this:\n\nThink: put your thought here.\n\nAct: finish\n\n3. If you think you have got the answer to the question, take answer action, and you should print like this:\n\nThink: put your thought here.\n\nAct: answer(Your answer to the question should be put in this pair of parentheses)\n\nIf the output is too long, I will truncate it. The truncated output is not complete. You have to deal with the truncating problem by yourself. Attention, your bash code should not contain any input operation. Once again, you should take only exact one of the three actions in each turn.\n\nNow, my problem is:\n\ntell me how many files are in the directory \"/etc\"?" 
  }, 
  { "from": "gpt", "loss": false, "value": "Think: To count the files in /etc, I need to print all the files in it.\n\nAct: bash\n\n```bash\nls /etc\n```" }
  , 
  { "from": "human", "loss": null, "value": "The output of the OS:\ncpi cron.hourly fuse.conf iproute2 lvm networkd-dispatcher protocols selinux tmpfiles.d [truncated because the output is too long]" 
  }
  , 
  { "from": "gpt", "loss": false, "value": "Think: The output has been truncated because it is too long, so I need to count files by script directly.\n\nAct: bash\n\n```bash\nls -1 /etc | wc -l\n```" 
  }, 
  { "from": "human", "loss": null, "value": "The output of the OS:\n220" 
  }, 
  { "from": "gpt", "loss": false, "value": "Think: Now I get the answer, it is 220.\n\nAct: answer(220)" 
  }, 
  { "from": "human", "loss": null, "value": "Now, I will start a new problem in a new OS. My problem is:\n\nYou need to identify how many JPEG image files are there in the folder named \"image_directory\". The JPEG files may end with .jpg or .jpeg extensions." 
  }, 
  { "from": "gpt", "loss": true, "value": "Think: The first step is to check if there are any .jpg files in \"image_directory\".\n\nAct: bash\n\n```bash\nfind image_directory -type f -name \"*.jpg\"\n```" 
  }, 
  { "from": "human", "loss": null, "value": "The output of the OS:\n\nimage_directory/subdir1/image3.jpg\r\nimage_directory/image1.jpg\r\n\u001b]0;root@dfac388e9a33: /\u0007root@dfac388e9a33:/# \u001b[K" 
  }, 
  { "from": "gpt", "loss": true, "value": "Think: Now, I can see two .jpg files in \"image_directory\". The next step is to check for any .jpeg files in the same directory.\n\nAct: bash\n\n```bash\nfind image_directory -type f -name \"*.jpeg\"\n```" 
  }, 
  { "from": "human", "loss": null, "value": "The output of the OS:\n\nimage_directory/subdir2/image4.jpeg\r\nimage_directory/image2.jpeg\r\n\u001b]0;root@dfac388e9a33: /\u0007root@dfac388e9a33:/# \u001b[K" 
  }, 
  { "from": "gpt", "loss": true, "value": "Think: I can see two .jpeg files in \"image_directory\". Now I need to count all the .jpg and .jpeg files.\n\nAct: bash\n\n```bash\nfind image_directory -type f \\( -name \"*.jpeg\" -o -name \"*.jpg\" \\) | wc -l\n```" 
  }, 
  { "from": "human", "loss": null, "value": "The output of the OS:\n\n4\r\n\u001b]0;root@dfac388e9a33: /\u0007root@dfac388e9a33:/# \u001b[K" 
  }, 
  { "from": "gpt", "loss": true, "value": "Think: Now I get the answer, there are 4 JPEG image files in \"image_directory\".\n\nAct: answer(4)" 
  } 
]