File size: 13,040 Bytes
12d654c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f9746a3
 
 
 
 
 
 
 
12d654c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f9746a3
12d654c
f9746a3
12d654c
 
f9746a3
 
 
12d654c
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
{
  "add_bos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "151643": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151644": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151645": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151646": {
      "content": "<|object_ref_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151647": {
      "content": "<|object_ref_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151648": {
      "content": "<|box_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151649": {
      "content": "<|box_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151650": {
      "content": "<|quad_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151651": {
      "content": "<|quad_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151652": {
      "content": "<|vision_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151653": {
      "content": "<|vision_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151654": {
      "content": "<|vision_pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151655": {
      "content": "<|image_pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151656": {
      "content": "<|video_pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151657": {
      "content": "<tool_call>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151658": {
      "content": "</tool_call>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151659": {
      "content": "<|fim_prefix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151660": {
      "content": "<|fim_middle|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151661": {
      "content": "<|fim_suffix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151662": {
      "content": "<|fim_pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151663": {
      "content": "<|repo_name|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151664": {
      "content": "<|file_sep|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151665": {
      "content": "<|PAD_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|im_start|>",
    "<|im_end|>",
    "<|object_ref_start|>",
    "<|object_ref_end|>",
    "<|box_start|>",
    "<|box_end|>",
    "<|quad_start|>",
    "<|quad_end|>",
    "<|vision_start|>",
    "<|vision_end|>",
    "<|vision_pad|>",
    "<|image_pad|>",
    "<|video_pad|>"
  ],
  "bos_token": null,
  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a Python expert.\nReturn ONLY the function implementation with no additional text or explanations.\n\nHere are some examples:\n\nex.1\n\n\nquery:\nwrite a function def analyze_nested_json(data, key_paths, value_types) to:\nAnalyzes a nested JSON structure to extract values at specified keys and categorize them based on their types.\n\nThe function should output with:\ndict: A dictionary mapping types to lists of extracted values.\n\nYou should start with:\n\\`\\`\\`\nimport json\nimport defaultdict\nimport chain\nimport pandas as pd\nimport numpy as np\ndef analyze_nested_json(data, key_paths, value_types) \\`\\`\\`\n\n\nresponse:\nimport json\nfrom collections import defaultdict\nfrom itertools import chain\nimport pandas as pd\nimport numpy as np\n\ndef analyze_nested_json(data, key_paths, value_types):\n    \"\"\"\n    Analyzes a nested JSON structure to extract values at specified keys and categorize them based on their types.\n    \n    Parameters:\n        - data (dict): A nested JSON data structure.\n        - key_paths (List[str]): Paths to keys in the JSON structure.\n        - value_types (List[type]): Types to categorize the extracted values.\n        \n    Requirements:\n        - json\n        - collections\n        - itertools\n        - pandas\n        - numpy\n    \n    Example:\n    >>> data = {\n    ...     \"root\": {\n    ...         \"child1\": {\"name\": \"Alice\", \"age\": 30, \"is_student\": False},\n    ...         \"child2\": {\"name\": \"Bob\", \"age\": 25, \"is_student\": True},\n    ...         \"child3\": {\"name\": \"Charlie\", \"age\": 35, \"is_student\": False},\n    ...         \"child4\": {\"name\": \"David\", \"age\": 22, \"is_student\": True}\n    ...     }\n    ... }\n    >>> key_paths = [\"root.child1.age\", \"root.child2.is_student\", \"root.child3.name\"]\n    >>> value_types = [int, bool, str]\n    >>> result = analyze_nested_json(data, key_paths, value_types)\n    >>> print(result)\n    {\n        \\'int\\': [30, 25, 35, 22],\n        \\'bool\\': [False, True, False, True],\n        \\'str\\': [\\'Alice\\', \\'Bob\\', \\'Charlie\\', \\'David\\']\n    }\n    \n    Returns:\n        dict: A dictionary mapping types to lists of extracted values.\n    \"\"\"\n    \n    def get_value_from_path(data, path):\n        keys = path.split(\\'.\\')\n        value = data\n        for key in keys:\n            value = value.get(key)\n            if value is None:\n                return None\n        return value\n    \n    categorized_values = defaultdict(list)\n    \n    for key_path, value_type in zip(key_paths, value_types):\n        value = get_value_from_path(data, key_path)\n        if isinstance(value, value_type):\n            categorized_values[str(value_type)].append(value)\n    \n    return dict(categorized_values)\n\n' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a Python expert.\nReturn ONLY the function implementation with no additional text or explanations.\n\nHere are some examples:\n\nex.1\n\n\nquery:\nwrite a function def analyze_nested_json(data, key_paths, value_types) to:\nAnalyzes a nested JSON structure to extract values at specified keys and categorize them based on their types.\n\nThe function should output with:\ndict: A dictionary mapping types to lists of extracted values.\n\nYou should start with:\n\\`\\`\\`\nimport json\nimport defaultdict\nimport chain\nimport pandas as pd\nimport numpy as np\ndef analyze_nested_json(data, key_paths, value_types) \\`\\`\\`\n\n\nresponse:\nimport json\nfrom collections import defaultdict\nfrom itertools import chain\nimport pandas as pd\nimport numpy as np\n\ndef analyze_nested_json(data, key_paths, value_types):\n    \"\"\"\n    Analyzes a nested JSON structure to extract values at specified keys and categorize them based on their types.\n    \n    Parameters:\n        - data (dict): A nested JSON data structure.\n        - key_paths (List[str]): Paths to keys in the JSON structure.\n        - value_types (List[type]): Types to categorize the extracted values.\n        \n    Requirements:\n        - json\n        - collections\n        - itertools\n        - pandas\n        - numpy\n    \n    Example:\n    >>> data = {\n    ...     \"root\": {\n    ...         \"child1\": {\"name\": \"Alice\", \"age\": 30, \"is_student\": False},\n    ...         \"child2\": {\"name\": \"Bob\", \"age\": 25, \"is_student\": True},\n    ...         \"child3\": {\"name\": \"Charlie\", \"age\": 35, \"is_student\": False},\n    ...         \"child4\": {\"name\": \"David\", \"age\": 22, \"is_student\": True}\n    ...     }\n    ... }\n    >>> key_paths = [\"root.child1.age\", \"root.child2.is_student\", \"root.child3.name\"]\n    >>> value_types = [int, bool, str]\n    >>> result = analyze_nested_json(data, key_paths, value_types)\n    >>> print(result)\n    {\n        \\'int\\': [30, 25, 35, 22],\n        \\'bool\\': [False, True, False, True],\n        \\'str\\': [\\'Alice\\', \\'Bob\\', \\'Charlie\\', \\'David\\']\n    }\n    \n    Returns:\n        dict: A dictionary mapping types to lists of extracted values.\n    \"\"\"\n    \n    def get_value_from_path(data, path):\n        keys = path.split(\\'.\\')\n        value = data\n        for key in keys:\n            value = value.get(key)\n            if value is None:\n                return None\n        return value\n    \n    categorized_values = defaultdict(list)\n    \n    for key_path, value_type in zip(key_paths, value_types):\n        value = get_value_from_path(data, key_path)\n        if isinstance(value, value_type):\n            categorized_values[str(value_type)].append(value)\n    \n    return dict(categorized_values)\n\n<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "errors": "replace",
  "extra_special_tokens": {},
  "model_max_length": 131072,
  "pad_token": "<|PAD_TOKEN|>",
  "padding_side": "left",
  "split_special_tokens": false,
  "tokenizer_class": "Qwen2Tokenizer",
  "unk_token": null
}