{"id":992466,"date":"2024-12-27T08:37:35","date_gmt":"2024-12-27T00:37:35","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/992466.html"},"modified":"2024-12-27T08:37:37","modified_gmt":"2024-12-27T00:37:37","slug":"bl%e7%94%a8python%e5%a6%82%e4%bd%95%e5%ae%9e%e7%8e%b0","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/992466.html","title":{"rendered":"Bl\u7528python\u5982\u4f55\u5b9e\u73b0"},"content":{"rendered":"

\"Bl\u7528python\u5982\u4f55\u5b9e\u73b0\"<\/p>\n

\u8981\u7528Python\u5b9e\u73b0BL\uff08Boys' Love\uff09\u4e3b\u9898\u7684\u6545\u4e8b\u751f\u6210\uff0c\u53ef\u4ee5\u4f7f\u7528\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08NLP\uff09\u6280\u672f\u548c\u673a\u5668\u5b66\u4e60<\/a>\u6a21\u578b\u6765\u751f\u6210\u6587\u672c\u3002\u4f7f\u7528Python\u5b9e\u73b0BL\u6545\u4e8b\u751f\u6210\u7684\u6838\u5fc3\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528GPT\u6a21\u578b\u3001\u5229\u7528\u6587\u672c\u751f\u6210\u5de5\u5177\u3001\u5b9a\u5236\u5316\u8bad\u7ec3\u6570\u636e\u3002<\/strong>\u4e0b\u9762\u5c06\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u5b9e\u73b0\u8fd9\u4e9b\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528GPT\u6a21\u578b\u751f\u6210BL\u6545\u4e8b<\/h3>\n<\/p>\n

GPT\uff08Generative Pre-trAI<\/a>ned Transformer\uff09\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u6a21\u578b\uff0c\u80fd\u591f\u751f\u6210\u8fde\u8d2f\u4e14\u6709\u521b\u610f\u7684\u6587\u672c\u3002\u6211\u4eec\u53ef\u4ee5\u5229\u7528GPT\u6a21\u578b\u751f\u6210BL\u4e3b\u9898\u7684\u6545\u4e8b\u3002<\/p>\n<\/p>\n

1. \u5b89\u88c5\u548c\u4f7f\u7528GPT\u6a21\u578b<\/h4>\n<\/p>\n

\u8981\u4f7f\u7528GPT\u6a21\u578b\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5\u76f8\u5173\u7684Python\u5e93\uff0c\u4f8b\u5982transformers<\/code>\u5e93\u3002\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install transformers<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u52a0\u8f7d\u548c\u4f7f\u7528GPT\u6a21\u578b\uff1a<\/p>\n<\/p>\n
from transformers import GPT2LMHeadModel, GPT2Tokenizer<\/p>\n
\u52a0\u8f7d\u6a21\u578b\u548c\u5206\u8bcd\u5668<\/strong><\/h2>\n
model_name = 'gpt2'<\/p>\n
model = GPT2LMHeadModel.from_pretrained(model_name)<\/p>\n
tokenizer = GPT2Tokenizer.from_pretrained(model_name)<\/p>\n
\u8f93\u5165\u63d0\u793a<\/strong><\/h2>\n
prompt = "\u5728\u67d0\u4e2a\u9065\u8fdc\u7684\u56fd\u5ea6\uff0c\u4e24\u4e2a\u7537\u5b69\u76f8\u9047\u4e86\uff0c\u4ed6\u4eec\u662f"<\/p>\n
\u7f16\u7801\u8f93\u5165\u5e76\u751f\u6210\u6587\u672c<\/strong><\/h2>\n
input_ids = tokenizer.encode(prompt, return_tensors='pt')<\/p>\n
output = model.generate(input_ids, max_length=200, num_return_sequences=1)<\/p>\n
\u89e3\u7801\u8f93\u51fa<\/strong><\/h2>\n
story = tokenizer.decode(output[0], skip_special_tokens=True)<\/p>\n
print(story)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u5b9a\u5236\u5316\u751f\u6210<\/h4>\n<\/p>\n
\u4e3a\u4e86\u751f\u6210\u66f4\u7b26\u5408BL\u4e3b\u9898\u7684\u6545\u4e8b\uff0c\u53ef\u4ee5\u5bf9\u8f93\u5165\u7684\u63d0\u793a\u8fdb\u884c\u5b9a\u5236\u5316\uff0c\u589e\u52a0BL\u76f8\u5173\u7684\u5143\u7d20\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u5728\u63d0\u793a\u4e2d\u52a0\u5165\u89d2\u8272\u7684\u7279\u5f81\u3001\u6545\u4e8b\u80cc\u666f\u3001\u60c5\u611f\u51b2\u7a81\u7b49\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u5229\u7528\u6587\u672c\u751f\u6210\u5de5\u5177<\/h3>\n<\/p>\n
\u9664\u4e86GPT\u6a21\u578b\uff0c\u8fd8\u6709\u5176\u4ed6\u4e00\u4e9b\u6587\u672c\u751f\u6210\u5de5\u5177\u548c\u6846\u67b6\u53ef\u4ee5\u7528\u4e8eBL\u6545\u4e8b\u521b\u4f5c\u3002<\/p>\n<\/p>\n
1. \u4f7f\u7528Markov\u94fe<\/h4>\n<\/p>\n
Markov\u94fe\u662f\u4e00\u79cd\u7edf\u8ba1\u6a21\u578b\uff0c\u53ef\u4ee5\u6839\u636e\u524d\u4e00\u4e2a\u72b6\u6001\u9884\u6d4b\u4e0b\u4e00\u4e2a\u72b6\u6001\uff0c\u9002\u7528\u4e8e\u7b80\u5355\u7684\u6587\u672c\u751f\u6210\u4efb\u52a1\u3002\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u6b65\u9aa4\u5b9e\u73b0\uff1a<\/p>\n<\/p>\n
    \n
  • \u6536\u96c6BL\u6545\u4e8b\u7684\u6587\u672c\u6570\u636e\u3002<\/li>\n
  • \u5206\u6790\u6587\u672c\u6570\u636e\uff0c\u5efa\u7acb\u8bcd\u8bed\u7684\u8f6c\u79fb\u6982\u7387\u77e9\u9635\u3002<\/li>\n
  • \u6839\u636e\u8f6c\u79fb\u6982\u7387\u751f\u6210\u65b0\u7684\u6587\u672c\u3002<\/li>\n<\/ul>\n
    2. \u4f7f\u7528RNN\u548cLSTM\u6a21\u578b<\/h4>\n<\/p>\n
    \u5faa\u73af\u795e\u7ecf\u7f51\u7edc\uff08RNN\uff09\u548c\u957f\u77ed\u671f\u8bb0\u5fc6\u7f51\u7edc\uff08LSTM\uff09\u662f\u5e38\u7528\u7684\u5e8f\u5217\u751f\u6210\u6a21\u578b\uff0c\u9002\u5408\u751f\u6210\u5177\u6709\u4e0a\u4e0b\u6587\u8fde\u7eed\u6027\u7684\u6587\u672c\u3002<\/p>\n<\/p>\n
    import torch<\/p>\n
    import torch.nn as nn<\/p>\n
    import numpy as np<\/p>\n
    \u5b9a\u4e49LSTM\u6a21\u578b<\/strong><\/h2>\n
    class BLStoryGenerator(nn.Module):<\/p>\n
        def __init__(self, vocab_size, hidden_dim, n_layers):<\/p>\n
            super(BLStoryGenerator, self).__init__()<\/p>\n
            self.lstm = nn.LSTM(vocab_size, hidden_dim, n_layers, batch_first=True)<\/p>\n
            self.fc = nn.Linear(hidden_dim, vocab_size)<\/p>\n
        def forward(self, x):<\/p>\n
            out, _ = self.lstm(x)<\/p>\n
            out = self.fc(out)<\/p>\n
            return out<\/p>\n
    \u521d\u59cb\u5316\u6a21\u578b<\/strong><\/h2>\n
    vocab_size = 5000  # \u8bcd\u6c47\u91cf<\/p>\n
    hidden_dim = 256  # \u9690\u85cf\u5c42\u7ef4\u5ea6<\/p>\n
    n_layers = 2  # LSTM\u5c42\u6570<\/p>\n
    model = BLStoryGenerator(vocab_size, hidden_dim, n_layers)<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    3. \u4f7f\u7528\u6587\u672c\u751f\u6210API<\/h4>\n<\/p>\n
    \u6709\u4e00\u4e9b\u5728\u7ebf\u7684\u6587\u672c\u751f\u6210API\u53ef\u4ee5\u76f4\u63a5\u7528\u4e8e\u751f\u6210BL\u6545\u4e8b\uff0c\u4f8b\u5982OpenAI\u7684GPT-3 API\u3002\u901a\u8fc7\u8c03\u7528API\uff0c\u53ef\u4ee5\u5feb\u901f\u751f\u6210\u9ad8\u8d28\u91cf\u7684BL\u6587\u672c\u3002<\/p>\n<\/p>\n
    \u4e09\u3001\u5b9a\u5236\u5316\u8bad\u7ec3\u6570\u636e<\/h3>\n<\/p>\n
    \u4e3a\u4e86\u63d0\u9ad8\u751f\u6210\u7684BL\u6545\u4e8b\u7684\u8d28\u91cf\uff0c\u53ef\u4ee5\u4f7f\u7528\u5b9a\u5236\u5316\u7684\u8bad\u7ec3\u6570\u636e\u8fdb\u884c\u6a21\u578b\u5fae\u8c03\u3002<\/p>\n<\/p>\n
    1. \u6536\u96c6\u548c\u6e05\u6d17\u6570\u636e<\/h4>\n<\/p>\n
      \n
    • \u6536\u96c6BL\u5c0f\u8bf4\u3001\u6f2b\u753b\u3001\u5267\u672c\u7b49\u6587\u672c\u6570\u636e\u3002<\/li>\n
    • \u5bf9\u6570\u636e\u8fdb\u884c\u6e05\u6d17\u548c\u9884\u5904\u7406\uff0c\u4f8b\u5982\u53bb\u9664\u7279\u6b8a\u5b57\u7b26\u3001\u5206\u8bcd\u3001\u53bb\u505c\u7528\u8bcd\u7b49\u3002<\/li>\n<\/ul>\n
      2. \u5fae\u8c03\u6a21\u578b<\/h4>\n<\/p>\n
      \u901a\u8fc7\u4f7f\u7528\u6536\u96c6\u5230\u7684BL\u6570\u636e\u5bf9GPT\u6a21\u578b\u8fdb\u884c\u5fae\u8c03\uff0c\u53ef\u4ee5\u8ba9\u6a21\u578b\u66f4\u597d\u5730\u7406\u89e3\u548c\u751f\u6210BL\u4e3b\u9898\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n
      from transformers import Trainer, TrainingArguments<\/p>\n
      \u5b9a\u4e49\u8bad\u7ec3\u53c2\u6570<\/strong><\/h2>\n
      training_args = TrainingArguments(<\/p>\n
          output_dir='.\/results',<\/p>\n
          num_train_epochs=3,<\/p>\n
          per_device_train_batch_size=4,<\/p>\n
          save_steps=10_000,<\/p>\n
          save_total_limit=2,<\/p>\n
      )<\/p>\n
      \u521b\u5efaTrainer\u5bf9\u8c61<\/strong><\/h2>\n
      trainer = Trainer(<\/p>\n
          model=model,<\/p>\n
          args=training_args,<\/p>\n
          train_dataset=bl_dataset,  # \u9700\u8981\u4e8b\u5148\u51c6\u5907\u597d\u7684BL\u6570\u636e\u96c6<\/p>\n
      )<\/p>\n
      \u5f00\u59cb\u8bad\u7ec3<\/strong><\/h2>\n
      trainer.train()<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      3. \u8bc4\u4f30\u548c\u8c03\u6574<\/h4>\n<\/p>\n
      \u5728\u8bad\u7ec3\u548c\u751f\u6210\u8fc7\u7a0b\u4e2d\uff0c\u9700\u8981\u4e0d\u65ad\u8bc4\u4f30\u751f\u6210\u6587\u672c\u7684\u8d28\u91cf\uff0c\u5e76\u6839\u636e\u9700\u8981\u8c03\u6574\u6a21\u578b\u53c2\u6570\u548c\u8f93\u5165\u63d0\u793a\uff0c\u4ee5\u8fbe\u5230\u6700\u4f73\u6548\u679c\u3002<\/p>\n<\/p>\n
      \u56db\u3001\u751f\u6210BL\u6545\u4e8b\u7684\u6280\u5de7\u548c\u5efa\u8bae<\/h3>\n<\/p>\n
      1. \u63d0\u4f9b\u8be6\u7ec6\u7684\u63d0\u793a<\/h4>\n<\/p>\n
      \u5728\u751f\u6210BL\u6545\u4e8b\u65f6\uff0c\u63d0\u4f9b\u8be6\u7ec6\u7684\u63d0\u793a\u53ef\u4ee5\u5e2e\u52a9\u6a21\u578b\u751f\u6210\u66f4\u7b26\u5408\u9884\u671f\u7684\u6587\u672c\u3002\u63d0\u793a\u53ef\u4ee5\u5305\u62ec\u89d2\u8272\u7684\u80cc\u666f\u3001\u60c5\u8282\u7684\u8d77\u70b9\u3001\u60c5\u611f\u51b2\u7a81\u7b49\u3002<\/p>\n<\/p>\n
      2. \u63a7\u5236\u6587\u672c\u957f\u5ea6<\/h4>\n<\/p>\n
      \u901a\u8fc7\u8c03\u6574\u751f\u6210\u53c2\u6570\uff0c\u53ef\u4ee5\u63a7\u5236\u751f\u6210\u6587\u672c\u7684\u957f\u5ea6\u3002\u4f8b\u5982\uff0cmax_length<\/code>\u53c2\u6570\u53ef\u4ee5\u9650\u5236\u751f\u6210\u6587\u672c\u7684\u6700\u5927\u957f\u5ea6\u3002<\/p>\n<\/p>\n
      3. \u591a\u6837\u6027\u548c\u521b\u610f<\/h4>\n<\/p>\n
      \u901a\u8fc7\u8c03\u6574\u751f\u6210\u53c2\u6570\u5982temperature<\/code>\u548ctop_k<\/code>\uff0c\u53ef\u4ee5\u589e\u52a0\u751f\u6210\u6587\u672c\u7684\u591a\u6837\u6027\u548c\u521b\u610f\u6027\u3002<\/p>\n<\/p>\n
      4. \u4eba\u5de5\u540e\u671f\u7f16\u8f91<\/h4>\n<\/p>\n
      \u751f\u6210\u7684\u6587\u672c\u53ef\u80fd\u9700\u8981\u8fdb\u884c\u4eba\u5de5\u540e\u671f\u7f16\u8f91\uff0c\u4ee5\u63d0\u9ad8\u6587\u672c\u7684\u8fde\u8d2f\u6027\u548c\u6d41\u7545\u6027\u3002\u53ef\u4ee5\u6839\u636e\u751f\u6210\u7684\u521d\u7a3f\uff0c\u8fdb\u884c\u7ec6\u8282\u4fee\u6539\u548c\u6da6\u8272\u3002<\/p>\n<\/p>\n
      \u901a\u8fc7\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u5b9e\u73b0BL\u4e3b\u9898\u7684\u6545\u4e8b\u751f\u6210\u3002\u65e0\u8bba\u662f\u4f7f\u7528GPT\u6a21\u578b\u3001Markov\u94fe\u3001RNN\/LSTM\u6a21\u578b\uff0c\u8fd8\u662f\u6587\u672c\u751f\u6210API\uff0c\u90fd\u9700\u8981\u7ed3\u5408\u5177\u4f53\u7684\u5e94\u7528\u573a\u666f\u548c\u9700\u6c42\uff0c\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u548c\u65b9\u6cd5\uff0c\u5e76\u4e0d\u65ad\u8fdb\u884c\u4f18\u5316\u548c\u6539\u8fdb\u3002<\/p>\n<\/p>\n
      \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
       \u5982\u4f55\u4f7f\u7528Python\u8fdb\u884cBl\u7684\u5f00\u53d1\u548c\u5e94\u7528\uff1f<\/strong>
      Bl\uff08\u901a\u5e38\u6307\u7684\u662f\u4e8c\u6b21\u5143\u6587\u5316\u6216\u76f8\u5173\u5185\u5bb9\uff09\u5728Python\u4e2d\u7684\u5b9e\u73b0\u53ef\u4ee5\u901a\u8fc7\u591a\u79cd\u65b9\u5f0f\u8fdb\u884c\u3002\u9996\u5148\uff0c\u60a8\u53ef\u4ee5\u9009\u62e9\u4f7f\u7528\u56fe\u5f62\u5e93\uff08\u5982Pygame\u6216Tkinter\uff09\u6765\u521b\u5efa\u53ef\u89c6\u5316\u5e94\u7528\u7a0b\u5e8f\u3002\u5982\u679c\u60a8\u5e0c\u671b\u8fdb\u884c\u6570\u636e\u5206\u6790\u6216\u5904\u7406\u76f8\u5173\u5185\u5bb9\uff0c\u4f7f\u7528Pandas\u548cMatplotlib\u7b49\u5e93\u5c06\u4f1a\u975e\u5e38\u6709\u7528\u3002\u6b64\u5916\uff0c\u60a8\u8fd8\u53ef\u4ee5\u8003\u8651\u4f7f\u7528Flask\u6216Django\u7b49\u6846\u67b6\u6765\u6784\u5efaWeb\u5e94\u7528\u7a0b\u5e8f\uff0c\u4ee5\u4fbf\u66f4\u597d\u5730\u5c55\u793a\u548c\u5206\u4eab\u60a8\u7684Bl\u76f8\u5173\u9879\u76ee\u3002<\/p>\n
      Python\u4e2d\u6709\u54ea\u4e9b\u5e93\u548c\u5de5\u5177\u53ef\u4ee5\u5e2e\u52a9\u5b9e\u73b0Bl\u7684\u9879\u76ee\uff1f<\/strong>
      \u5728Python\u4e2d\uff0c\u6709\u5f88\u591a\u5e93\u53ef\u4ee5\u5e2e\u52a9\u5b9e\u73b0Bl\u76f8\u5173\u7684\u9879\u76ee\u3002\u4f8b\u5982\uff0cPillow\u53ef\u4ee5\u7528\u4e8e\u56fe\u50cf\u5904\u7406\uff0c\u5e2e\u52a9\u60a8\u521b\u5efa\u548c\u7f16\u8f91\u56fe\u50cf\uff1bBeautifulSoup\u53ef\u4ee5\u7528\u4e8e\u7f51\u9875\u6293\u53d6\uff0c\u4ee5\u83b7\u53d6Bl\u76f8\u5173\u5185\u5bb9\u3002\u82e5\u60a8\u9700\u8981\u8fdb\u884c\u673a\u5668\u5b66\u4e60\u6216\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff0cTensorFlow\u548cNLTK\u4e5f\u662f\u975e\u5e38\u4e0d\u9519\u7684\u9009\u62e9\u3002\u8fd9\u4e9b\u5de5\u5177\u7ed3\u5408\u53ef\u4ee5\u8ba9\u60a8\u66f4\u9ad8\u6548\u5730\u5b9e\u73b0\u81ea\u5df1\u7684\u521b\u610f\u3002<\/p>\n
      \u5bf9\u4e8e\u521d\u5b66\u8005\uff0c\u5982\u4f55\u5f00\u59cb\u4f7f\u7528Python\u5f00\u53d1Bl\u9879\u76ee\uff1f<\/strong>
      \u5bf9\u4e8e\u521d\u5b66\u8005\u6765\u8bf4\uff0c\u5efa\u8bae\u4ece\u7b80\u5355\u7684\u9879\u76ee\u5f00\u59cb\uff0c\u4f8b\u5982\u521b\u5efa\u4e00\u4e2a\u57fa\u672c\u7684\u56fe\u5f62\u754c\u9762\u5e94\u7528\u3002\u53ef\u4ee5\u9996\u5148\u5b66\u4e60Python\u7684\u57fa\u7840\u77e5\u8bc6\uff0c\u7136\u540e\u9009\u62e9\u4e00\u4e2a\u9002\u5408\u7684\u5e93\uff0c\u6bd4\u5982Pygame\u6216Tkinter\uff0c\u9010\u6b65\u5b9e\u73b0\u4e00\u4e9b\u5c0f\u529f\u80fd\u3002\u5728\u7f51\u4e0a\u4e5f\u6709\u5f88\u591a\u6559\u7a0b\u548c\u793e\u533a\u53ef\u4ee5\u63d0\u4f9b\u5e2e\u52a9\uff0c\u52a0\u5165\u76f8\u5173\u8ba8\u8bba\u5c06\u6709\u52a9\u4e8e\u60a8\u66f4\u5feb\u5730\u89e3\u51b3\u95ee\u9898\u548c\u83b7\u53d6\u7075\u611f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u8981\u7528Python\u5b9e\u73b0BL\uff08Boys' Love\uff09\u4e3b\u9898\u7684\u6545\u4e8b\u751f\u6210\uff0c\u53ef\u4ee5\u4f7f\u7528\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08NLP\uff09\u6280\u672f\u548c\u673a […]","protected":false},"author":3,"featured_media":992472,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/992466"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=992466"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/992466\/revisions"}],"predecessor-version":[{"id":992480,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/992466\/revisions\/992480"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/992472"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=992466"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=992466"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=992466"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}