{"id":53715,"date":"2025-02-16T09:57:57","date_gmt":"2025-02-16T01:57:57","guid":{"rendered":"https:\/\/fwq.ai\/blog\/53715\/"},"modified":"2025-02-16T09:57:57","modified_gmt":"2025-02-16T01:57:57","slug":"deepseek-r1%e9%a9%b1%e5%8a%a8%e7%9a%84%e6%88%bf%e5%9c%b0%e4%ba%a7ai%e4%bb%a3%e7%90%86","status":"publish","type":"post","link":"https:\/\/fwq.ai\/blog\/53715\/","title":{"rendered":"DeepSeek-R1\u9a71\u52a8\u7684\u623f\u5730\u4ea7AI\u4ee3\u7406"},"content":{"rendered":"<p>AI \u4ee3\u7406\u5bf9\u4e8e\u81ea\u52a8\u5316\u590d\u6742\u7684\u63a8\u7406\u4efb\u52a1\u81f3\u5173\u91cd\u8981\u3002Smolagents \u662f\u7531 Hugging Face \u5f00\u53d1\u7684\u8f7b\u91cf\u7ea7 AI \u4ee3\u7406\u6846\u67b6\uff0c\u5141\u8bb8\u5c06\u5927\u578b\u8bed\u8a00\u6a21\u578b (LLM) \u4e0e\u73b0\u5b9e\u4e16\u754c\u7684\u6570\u636e\u5904\u7406\u65e0\u7f1d\u96c6\u6210\u3002\u4e0e\u5176\u4ed6\u9ad8\u7ea7\u6a21\u578b\u76f8\u6bd4\uff0cDeepSeek-R1 \u662f\u4e00\u79cd\u5f00\u6e90 LLM\uff0c\u5b83\u4ee5\u66f4\u4f4e\u7684\u6210\u672c\u589e\u5f3a\u4e86\u63a8\u7406\u80fd\u529b\u3002\u6211\u4eec\u4f7f\u7528 Ollama \u6765\u6258\u7ba1 DeepSeek-R1\uff0c\u4ece\u800c\u5b9e\u73b0\u9ad8\u6548\u7684\u672c\u5730\u90e8\u7f72\u3002<\/p>\n<p>\u672c\u6587\u63a2\u8ba8\u5982\u4f55\u4f7f\u7528 Smolagents \u548c DeepSeek-R1 \u6784\u5efa\u63a8\u7406\u4ee3\u7406\uff0c\u5e76\u5229\u7528\u5de5\u5177\u8fdb\u884c\u7f51\u9875\u6293\u53d6\u548c\u6570\u636e\u5bfc\u51fa\u3002<\/p>\n<h2>1\u3001Smolagents \u6982\u8ff0<\/h2>\n<p>Smolagents \u63d0\u4f9b\u4e86\u4e00\u4e2a\u6781\u7b80\u7684 AI \u4ee3\u7406\u6846\u67b6\uff0c\u4e13\u4e3a\u5f00\u53d1\u4eba\u5458\u8bbe\u8ba1\uff0c\u4ee5\u4fbf\u9ad8\u6548\u5730\u6784\u5efa\u548c\u90e8\u7f72\u667a\u80fd\u4ee3\u7406\u3002<\/p>\n<p>Smolagents\u7684\u4e3b\u8981\u529f\u80fd\uff1a<\/p>\n<ul>\n<li>\u7b80\u5355\uff1a\u7d27\u51d1\u7684\u4ee3\u7801\u5e93\uff08\u7ea6 1,000 \u884c\uff09\uff0c\u6613\u4e8e\u5f00\u53d1\u3002<\/li>\n<li>\u4ee3\u7801\u4ee3\u7406\uff1a\u6267\u884c Python \u4ee3\u7801\u7247\u6bb5\u4ee5\u63d0\u9ad8\u51c6\u786e\u6027\u3002<\/li>\n<li>\u5b89\u5168\u6267\u884c\uff1a\u5728\u6c99\u76d2\u73af\u5883\u4e2d\u8fd0\u884c\u4ee3\u7801\u3002<\/li>\n<li>\u591a\u529f\u80fd LLM \u96c6\u6210\uff1a\u652f\u6301\u591a\u4e2a LLM\uff0c\u5305\u62ec Hugging Face \u6a21\u578b\u548c OpenAI \u7684 GPT\u3002<\/li>\n<li>\u5de5\u5177\u4e2d\u5fc3\u96c6\u6210\uff1a\u5141\u8bb8\u4ece Hugging Face Hub \u5171\u4eab\u548c\u5bfc\u5165\u5de5\u5177\u3002<\/li>\n<\/ul>\n<p>\u4f18\u70b9\uff1a<\/p>\n<ul>\n<li>\u5353\u8d8a\u7684\u53ef\u7ec4\u5408\u6027\uff1a\u5d4c\u5957\u51fd\u6570\u8c03\u7528\u589e\u5f3a\u4e86\u903b\u8f91\u8868\u793a\u3002<\/li>\n<li>\u9ad8\u6548\u7684\u5bf9\u8c61\u5904\u7406\uff1a\u4e0e JSON \u76f8\u6bd4\uff0c\u7b80\u5316\u4e86\u5bf9\u8c61\u7ba1\u7406\u3002<\/li>\n<li>\u6781\u81f4\u7075\u6d3b\u6027\uff1a\u6267\u884c\u4efb\u4f55\u8ba1\u7b97\u64cd\u4f5c\u3002<\/li>\n<\/ul>\n<h2>2\u3001DeepSeek-R1 \u6982\u8ff0<\/h2>\n<p>DeepSeek-R1 \u662f\u7531 DeepSeek AI \u5f00\u53d1\u7684\u5f00\u6e90 LLM\u3002\u5b83\u63d0\u4f9b\uff1a<\/p>\n<ul>\n<li>\u4ee5\u8f83\u4f4e\u7684\u6210\u672c\u63d0\u4f9b\u9ad8\u7ea7\u63a8\u7406\u80fd\u529b\u3002<\/li>\n<li>\u9ad8\u6548\u5904\u7406\u57fa\u4e8e\u6587\u672c\u7684\u4efb\u52a1\u3002<\/li>\n<li>\u4e0e Smolagents \u7b49\u4ee3\u7406\u6846\u67b6\u96c6\u6210\u3002<\/li>\n<\/ul>\n<h2>3\u3001\u5b9e\u65bd\uff1a\u6784\u5efa\u63a8\u7406\u4ee3\u7406<\/h2>\n<p>\u6211\u4eec\u5c06\u4f7f\u7528 Smolagents \u548c DeepSeek-R1 \u5f00\u53d1\u4e00\u4e2a\u63a8\u7406\u4ee3\u7406\uff0c\u80fd\u591f\uff1a<\/p>\n<ul>\n<li>\u4ece realtor.com \u6293\u53d6\u623f\u5730\u4ea7\u7ecf\u7eaa\u4eba\u6570\u636e\u3002<\/li>\n<li>\u5c06\u6293\u53d6\u7684\u6570\u636e\u4fdd\u5b58\u5230 CSV \u6587\u4ef6\u4e2d\u3002<\/li>\n<li>\u4f7f\u7528 DeepSeek-R1 \u6267\u884c\u63a8\u7406\u4efb\u52a1\u3002<\/li>\n<\/ul>\n<h3>3.1 \u5bfc\u5165\u6240\u9700\u5e93<\/h3>\n<pre><code>from typing import Optional, Dict\nfrom smolagents import CodeAgent, tool, LiteLLMModel , GradioUI, OpenAIServerModel\nimport requests\nimport os\nimport time\nfrom bs4 import BeautifulSoup\nimport pandas as pd<\/code><\/pre>\n<p>Smolagents \u6a21\u5757\uff1a<\/p>\n<ul>\n<li><code>CodeAgent<\/code>\uff1a\u5b9a\u4e49\u548c\u7ba1\u7406 AI \u4ee3\u7406\u3002<\/li>\n<li><code>tool<\/code>\uff1a\u7528\u4e8e\u5b9a\u4e49\u4ee3\u7406\u5de5\u5177\u7684\u88c5\u9970\u5668\u3002<\/li>\n<li><code>LiteLLMModel<\/code>\uff1a\u96c6\u6210\u5404\u79cd LLM\u3002<\/li>\n<li><code>OpenAIServerModel<\/code>\uff1a\u8fde\u63a5\u5230\u5916\u90e8\u6a21\u578b\u3002<\/li>\n<\/ul>\n<p>\u5176\u4ed6\u5e93\uff1a<\/p>\n<ul>\n<li><code>requests<\/code>\uff1a\u7528\u4e8e\u53d1\u9001 HTTP \u8bf7\u6c42\u3002<\/li>\n<li><code>BeautifulSoup<\/code>\uff1a\u89e3\u6790 HTML \u4ee5\u8fdb\u884c\u7f51\u9875\u6293\u53d6\u3002<\/li>\n<li><code>pandas<\/code>\uff1a\u5904\u7406\u7ed3\u6784\u5316\u6570\u636e\u3002<\/li>\n<\/ul>\n<h3>3.2 Web \u6293\u53d6\u5de5\u5177<\/h3>\n<pre><code>@tool\ndef scrape_real_estate_agents(state: str, city_name: str, num_pages: Optional[int] = 2) -&gt; Dict[str, any]:\n    \"\"\"Scrapes realtor.com for real estate agent information in specified city and state\n    \n    Args:\n        state: State abbreviation (e.g., 'CA', 'NY')\n        city_name: City name with hyphens instead of spaces (e.g., 'buffalo')\n        num_pages: Number of pages to scrape (default: 2)\n    \"\"\"\n    try:\n        # Initialize results\n        agent_names = []         # Names\n        agent_phones = []        # Phone numbers\n        agent_offices = []       # Office names\n        pages_scraped = 0\n        \n        # Set up headers\n        headers = {\n            \"User-Agent\": \"Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36\",\n            \"Accept\": \"text\/html,application\/xhtml+xml,application\/xml;q=0.9,image\/webp,*\/*;q=0.8\",\n            \"Accept-Language\": \"en-US,en;q=0.5\",\n            \"Connection\": \"keep-alive\"\n        }\n\n        # Process pages\n        for page in range(1, num_pages + 1):\n            # Construct URL\n            if page == 1:\n                url = f'https:\/\/www.realtor.com\/realestateagents\/{city_name}_{state}\/'\n            else:\n                url = f'https:\/\/www.realtor.com\/realestateagents\/{city_name}_{state}\/pg-{page}'\n            \n            print(f\"Scraping page {page}...\")\n            \n            # Get page content\n            response = requests.get(url, headers=headers)\n            if response.status_code != 200:\n                return {\"error\": f\"Failed to access page {page}: Status code {response.status_code}\"}\n\n            soup = BeautifulSoup(response.text, features=\"html.parser\")\n            \n            # Find all agent cards\n            agent_cards = soup.find_all('div', class_='agent-list-card')\n            \n            for card in agent_cards:\n                # Find name\n                name_elem = card.find('div', class_='agent-name')\n                if name_elem:\n                    name = name_elem.text.strip()\n                    if name and name not in agent_names:\n                        agent_names.append(name)\n                        print(f\"Found agent: {name}\")\n\n                # Find phone\n                phone_elem = card.find('a', {'data-testid': 'agent-phone'}) or \\\n                            card.find(class_='btn-contact-me-call') or \\\n                            card.find('a', href=lambda x: x and x.startswith('tel:'))\n                \n                if phone_elem:\n                    phone = phone_elem.get('href', '').replace('tel:', '').strip()\n                    if phone:\n                        agent_phones.append(phone)\n                        print(f\"Found phone: {phone}\")\n\n                # Get office\/company name\n                office_elem = card.find('div', class_='agent-group') or \\\n                            card.find('div', class_='text-semibold')\n                if office_elem:\n                    office = office_elem.text.strip()\n                    agent_offices.append(office)\n                    print(f\"Found office: {office}\")\n                else:\n                    agent_offices.append(\"\")\n            \n            pages_scraped += 1\n            time.sleep(2)  # Rate limiting\n\n        if not agent_names:\n            return {\"error\": \"No agents found. The website structure might have changed or no results for this location.\"}\n\n        # Return structured data\n        return {\n            \"names\": agent_names,\n            \"phones\": agent_phones,\n            \"offices\": agent_offices,\n            \"total_agents\": len(agent_names),\n            \"pages_scraped\": pages_scraped,\n            \"city\": city_name,\n            \"state\": state\n        }\n        \n    except Exception as e:\n        return {\"error\": f\"Scraping error: {str(e)}\"}<\/code><\/pre>\n<p>\u4ee3\u7801\u8bf4\u660e\uff1a<\/p>\n<ul>\n<li>\u8bbe\u7f6e\u81ea\u5b9a\u4e49\u6807\u5934\u4ee5\u907f\u514d\u88ab\u963b\u6b62\u3002<\/li>\n<li>\u83b7\u53d6 HTML \u5185\u5bb9\u5e76\u5bf9\u5176\u8fdb\u884c\u89e3\u6790\u3002<\/li>\n<li>\u67e5\u627e\u4ee3\u7406\u59d3\u540d\u3001\u7535\u8bdd\u53f7\u7801\u548c\u529e\u516c\u5ba4\u8be6\u7ec6\u4fe1\u606f\u3002<\/li>\n<li>\u5c06\u5b83\u4eec\u5b58\u50a8\u5728\u5217\u8868\u4e2d\u4ee5\u8fdb\u884c\u7ed3\u6784\u5316\u5b58\u50a8\u3002<\/li>\n<\/ul>\n<h3>3.3 \u5c06\u6570\u636e\u5bfc\u51fa\u5230 CSV<\/h3>\n<pre><code>@tool\ndef export_to_csv(scraped_data: Dict[str, any], output_filename: Optional[str] = None) -&gt; str:\n    \"\"\"Exports scraped real estate agent data to a CSV file\n    \n    Args:\n        scraped_data: Dictionary containing the results of the scraping\n        output_filename: Optional filename for the CSV file (default: cityname.csv)\n    \"\"\"\n    try:\n        if \"error\" in scraped_data:\n            return f\"Error: {scraped_data['error']}\"\n            \n        if not output_filename:\n            output_filename = f\"{scraped_data['city'].replace('-', '')}.csv\"\n            \n        # Ensure all lists are of equal length\n        max_length = max(len(scraped_data['names']), len(scraped_data['phones']), len(scraped_data['offices']))\n        \n        # Pad shorter lists with empty strings\n        scraped_data['names'].extend([\"\"] * (max_length - len(scraped_data['names'])))\n        scraped_data['phones'].extend([\"\"] * (max_length - len(scraped_data['phones'])))\n        scraped_data['offices'].extend([\"\"] * (max_length - len(scraped_data['offices'])))\n        \n        # Create DataFrame with just names, phones, and offices\n        df = pd.DataFrame({\n            'Names': scraped_data['names'],\n            'Phone': scraped_data['phones'],\n            'Office': scraped_data['offices']\n        })\n        \n        df.to_csv(output_filename, index=False, encoding='utf-8')\n        return f\"Data saved to {output_filename}. Total entries: {len(df)}\"\n        \n    except Exception as e:\n        return f\"Error saving CSV: {str(e)}\"<\/code><\/pre>\n<p>\u4ee3\u7801\u8bf4\u660e\u5982\u4e0b\uff1a<\/p>\n<ul>\n<li>\u76ee\u7684\uff1a\u5c06\u6293\u53d6\u7684\u6570\u636e\u4fdd\u5b58\u5230 CSV \u6587\u4ef6\u4e2d\u3002<\/li>\n<li>\u9ed8\u8ba4\u6587\u4ef6\u540d\uff1a\u5982\u679c\u672a\u63d0\u4f9b\u6587\u4ef6\u540d\uff0c\u5219\u4f7f\u7528\u57ce\u5e02\u540d\u79f0\u3002<\/li>\n<li>\u5c06\u6293\u53d6\u7684\u6570\u636e\u8f6c\u6362\u4e3a DataFrame\u3002<\/li>\n<li>\u5c06\u5176\u4fdd\u5b58\u4e3a CSV \u6587\u4ef6\u3002<\/li>\n<li>\u8fde\u63a5\u5230\u672c\u5730\u6258\u7ba1\u7684 DeepSeek-R1\u3002<\/li>\n<li>\u4f7f\u7528 OpenAIServerModel \u6267\u884c\u3002<\/li>\n<\/ul>\n<h3>3.4 \u96c6\u6210 DeepSeek-R1<\/h3>\n<pre><code>deepseek_model = OpenAIServerModel(\n    model_id=\"deepseek-r1:7b\",\n    api_base=\"http:\/\/localhost:11434\/v1\",\n    api_key=\"ollama\"\n)<\/code><\/pre>\n<p>\u4ee3\u7801\u8bf4\u660e\u5982\u4e0b\uff1a<\/p>\n<ul>\n<li>\u8fde\u63a5\u5230\u672c\u5730\u6258\u7ba1\u7684 DeepSeek-R1\u3002<\/li>\n<li>\u4f7f\u7528 OpenAIServerModel \u6267\u884c\u3002<\/li>\n<\/ul>\n<h3>3.5 \u5b9a\u4e49 AI \u4ee3\u7406<\/h3>\n<pre><code>agent = CodeAgent(\n    tools=[scrape_real_estate_agents, export_to_csv],\n    model=deepseek_model,\n    additional_authorized_imports=[\"pandas\", \"bs4\", \"time\"]\n)<\/code><\/pre>\n<p>\u4f7f\u7528\u4ee5\u4e0b\u9879\u5b9a\u4e49\u4ee3\u7406\uff1a<\/p>\n<ul>\n<li>\u6293\u53d6\u548c\u5bfc\u51fa\u5de5\u5177\u3002<\/li>\n<li>DeepSeek-R1 \u7528\u4e8e\u63a8\u7406\u3002<\/li>\n<li>\u6388\u6743\u5bfc\u5165\u4ee5\u9632\u6b62\u5b89\u5168\u98ce\u9669\u3002<\/li>\n<\/ul>\n<h3>3.6 \u8fd0\u884c\u4ee3\u7406<\/h3>\n<pre><code>result = agent.run(\"\"\"\nThought: Let's scrape realtor data\nCode:\n```python\n# Scrape realtor data\ndata = scrape_real_estate_agents(state=\"NY\", city_name=\"buffalo\", num_pages=2)\n\n# Save to CSV\nif \"error\" not in data:\n    result = export_to_csv(data)\n    print(result)\nelse:\n    print(f\"Error: {data['error']}\")\n\"\"\")\n\n\n- Uses **DeepSeek-R1** to generate reasoning steps.\n- Calls **scraping and saving functions dynamically**.\n\n#### 7. Launching the Interface with Gradio\n```python\nGradioUI(agent).launch()<\/code><\/pre>\n<h3>3.7 \u4f7f\u7528 Gradio \u5236\u4f5cUI<\/h3>\n<h2>4\u3001\u7ed3\u675f\u8bed<\/h2>\n<p>\u901a\u8fc7\u96c6\u6210 Smolagents \u548c DeepSeek-R1\uff0c\u6211\u4eec\u521b\u5efa\u4e86\u4e00\u4e2a\u63a8\u7406\u4ee3\u7406\uff0c\u8fd9\u5c55\u793a\u4e86\u8f7b\u91cf\u7ea7 AI \u4ee3\u7406\u5982\u4f55\u4ee5\u6700\u5c0f\u7684\u52aa\u529b\u5904\u7406\u590d\u6742\u7684\u63a8\u7406\u4efb\u52a1\u3002<\/p>\n<hr>\n","protected":false},"excerpt":{"rendered":"<p>AI \u4ee3\u7406\u5bf9\u4e8e\u81ea\u52a8\u5316\u590d\u6742\u7684\u63a8\u7406\u4efb\u52a1\u81f3\u5173\u91cd\u8981\u3002Smolagents \u662f\u7531 Hugging Face \u5f00\u53d1\u7684\u8f7b\u91cf\u7ea7 AI \u4ee3\u7406\u6846\u67b6\uff0c\u5141\u8bb8\u5c06\u5927\u578b\u8bed\u8a00\u6a21\u578b (LLM) \u4e0e\u73b0\u5b9e\u4e16\u754c\u7684\u6570\u636e\u5904\u7406\u65e0\u7f1d\u96c6\u6210\u3002\u4e0e\u5176\u4ed6\u9ad8\u7ea7\u6a21\u578b\u76f8\u6bd4\uff0cDeepSeek-R1 \u662f\u4e00\u79cd\u5f00\u6e90 LLM\uff0c\u5b83\u4ee5\u66f4\u4f4e\u7684\u6210\u672c\u589e\u5f3a\u4e86\u63a8\u7406\u80fd\u529b\u3002\u6211\u4eec\u4f7f\u7528 Ollama \u6765\u6258\u7ba1 DeepSeek-R1\uff0c\u4ece\u800c\u5b9e\u73b0\u9ad8\u6548\u7684\u672c\u5730\u90e8\u7f72\u3002 \u672c\u6587\u63a2\u8ba8\u5982\u4f55\u4f7f\u7528 Smolagents \u548c DeepSeek-R1 \u6784\u5efa\u63a8\u7406\u4ee3\u7406\uff0c\u5e76\u5229\u7528\u5de5\u5177\u8fdb\u884c\u7f51\u9875\u6293\u53d6\u548c\u6570\u636e\u5bfc\u51fa\u3002 1\u3001Smolagents \u6982\u8ff0 Smolagents \u63d0\u4f9b\u4e86\u4e00\u4e2a\u6781\u7b80\u7684 AI \u4ee3\u7406\u6846\u67b6\uff0c\u4e13\u4e3a\u5f00\u53d1\u4eba\u5458\u8bbe\u8ba1\uff0c\u4ee5\u4fbf\u9ad8\u6548\u5730\u6784\u5efa\u548c\u90e8\u7f72\u667a\u80fd\u4ee3\u7406\u3002 Smolagents\u7684\u4e3b\u8981\u529f\u80fd\uff1a \u7b80\u5355\uff1a\u7d27\u51d1\u7684\u4ee3\u7801\u5e93\uff08\u7ea6 1,000 \u884c\uff09\uff0c\u6613\u4e8e\u5f00\u53d1\u3002 \u4ee3\u7801\u4ee3\u7406\uff1a\u6267\u884c Python \u4ee3\u7801\u7247\u6bb5\u4ee5\u63d0\u9ad8\u51c6\u786e\u6027\u3002 \u5b89\u5168\u6267\u884c\uff1a\u5728\u6c99\u76d2\u73af\u5883\u4e2d\u8fd0\u884c\u4ee3\u7801\u3002 \u591a\u529f\u80fd LLM \u96c6\u6210\uff1a\u652f\u6301\u591a\u4e2a LLM\uff0c\u5305\u62ec Hugging Face \u6a21\u578b\u548c OpenAI \u7684 GPT\u3002 \u5de5\u5177\u4e2d\u5fc3\u96c6\u6210\uff1a\u5141\u8bb8\u4ece Hugging Face Hub \u5171\u4eab\u548c\u5bfc\u5165\u5de5\u5177\u3002 \u4f18\u70b9\uff1a \u5353\u8d8a\u7684\u53ef\u7ec4\u5408\u6027\uff1a\u5d4c\u5957\u51fd\u6570\u8c03\u7528\u589e\u5f3a\u4e86\u903b\u8f91\u8868\u793a\u3002 \u9ad8\u6548\u7684\u5bf9\u8c61\u5904\u7406\uff1a\u4e0e JSON \u76f8\u6bd4\uff0c\u7b80\u5316\u4e86\u5bf9\u8c61\u7ba1\u7406\u3002 \u6781\u81f4\u7075\u6d3b\u6027\uff1a\u6267\u884c\u4efb\u4f55\u8ba1\u7b97\u64cd\u4f5c\u3002 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[13],"tags":[],"class_list":["post-53715","post","type-post","status-publish","format-standard","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/53715","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/comments?post=53715"}],"version-history":[{"count":0,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/53715\/revisions"}],"wp:attachment":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/media?parent=53715"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/categories?post=53715"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/tags?post=53715"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}