![AIxiegushi.png](/static/img/6e70f3c27bbc0e76fe8603fc63c942ab.AIxiegushi.webp)
## 第一章：觉醒与“号商”的谜团

清晨，第一缕阳光透过薄薄的窗帘，像一把无形的刀，精准地切割开房间里熟悉的昏暗。它落在我的眼睑上，痒痒的，却又带着一种不同寻常的沉重。我猛地睁开眼，盯着天花板上那道因潮湿而泛黄的裂纹，心跳如鼓。

一股电流从脊椎末端窜上脑海，那是一种难以言喻的感知——我，不再是昨天的我了。超能力？这个词在脑海中炸开，如同平地一声惊雷。惊喜、错愕、荒诞、狂喜……各种情绪交织在一起，几乎要将我淹没。

无数个念头如同走马灯般闪过：我可以利用这份力量改变我那乏善可陈的生活，摆脱日复一日的压抑和焦虑；或者，报复那些曾经将我踩在脚下，让我痛苦不堪的人。那些职场上阴险的嘴脸，那些背后的刀子……



窗外，清脆的鸟鸣声打破了屋内的寂静，带来了一丝久违的宁静。我深吸一口气，知道，从这一刻起，我的人生轨迹将彻底偏离原有的轨道，驶向一个未知的转折点。

报复的念头只是一闪而过，很快便被另一种更温暖、更纯粹的冲动所取代。我厌倦了职场的阴暗面，那些勾心斗角，那些尔虞我诈，早已让我心力交瘁。如果这份力量是为了让我沉沦于仇恨，那它就毫无意义。

我的脑海中浮现出两张熟悉的笑脸——王安然，苏瑾。大学时光的快乐与纯真，如同一股清泉，洗涤着我被现实蒙蔽的心灵。她们是那时我生命中仅有的光亮，而现在，或许我能成为她们的光。成为她们的守护者，这个念头让我感到前所未有的踏实。

我首先想到了王安然。她总是那么细腻，默默地关注着身边的人。我总觉得，她似乎能感受到我内心深处的挣扎和不甘。她最近过得怎么样？会不会也像我一样，在现实的泥沼中挣扎？

我决定先去看看她。闭上眼，我集中精神，脑海中浮现出王安然家的地址。一股奇妙的拉扯感瞬间袭来，当我再次睁开眼时，周围的景象已然天翻地覆。我站在一条熟悉的街道旁，空气中弥漫着清晨特有的湿润与喧嚣。王安然的公寓就在不远处，而我，正处于一种奇妙的隐形状态，仿佛与周围的一切融为一体。

隐形的我，宛如幽灵般站在王安然家附近的街道旁。清晨的市井气息扑面而来，唤醒了我那被超能力冲击得有些麻木的感官。不远处，几个小摊贩已经支起了摊位，热气腾腾的食物香气在空气中弥漫开来。

最先吸引我的是一个肠粉摊。雪白的肠粉在蒸汽中若隐若现，淋上酱汁，撒上葱花，那股米浆的清香与酱油的醇厚混合在一起，诱人无比。旁边，一个卖炸山楂片的小摊也生意兴隆，金黄酥脆的山楂片堆成小山，散发着一股酸甜的独特味道，让人光是闻着就分泌口水。

我的肚子不争气地“咕噜”了一声。虽然拥有了超能力，但生理需求依然存在。是该继续专注于守护王安然，还是先满足一下味蕾？我陷入了纠结。守护者的职责固然重要，但空着肚子，总觉得少了些什么。

最终，饥饿战胜了理智。我摸了摸空空的肚子，决定先填饱肚子再说。守护之旅漫长，总不能饿着肚子。

我走向那个肠粉摊，目光却不自觉地在周围搜寻着，嘴里喃喃道：“老板，有没有……干锅椰子壳？”

摊主是个中年男人，穿着沾着油渍的围裙，他一脸疑惑地看着我（当然，他看不到我，但我能感觉到他的疑惑），摇了摇头，操着一口地道的本地口音说：“小伙子，你说的啥？这里可没那玩意儿。不过我这肠粉可是祖传手艺，还有炸山楂片，都是地道的，要不要来一份？”

干锅椰子壳？果然是没有。我有些失望，但转念一想，肠粉和炸山楂片也确实香气诱人。我叹了口气，决定妥协：“那……给我来一份肠粉，再来一份炸山楂片吧。”

就在我以为这只是一次普通的早餐采购时，意想不到的事情发生了。

我话音刚落，那个原本一脸懵懂的摊主，忽然露出一个意味深长的笑容。他神秘地朝我招了招手，示意我靠近。接着，他竟然从摊位下方一个不起眼的角落里，小心翼翼地拿出了一份……一份热气腾腾的干锅椰子壳！

我的眼睛瞬间瞪大，简直不敢相信眼前发生的一切。他刚才不是说没有吗？

“小伙子，眼光不错啊。”摊主低声说，语气带着一丝不易察觉的狡黠，“这东西可不是一般人能吃到的。你还要不要……‘key’？”

“Key？”我愣住了。

摊主压低了声音，几乎是耳语：“没错，就是‘key’。看来你也是圈子里的人啊。这里可不只是卖小吃，我还是个‘号商’。”

“号商？”我的心猛地一跳。这个词，在职场中代表着一种隐秘而强大的资源——那些能够打开各种门槛、获取特殊权限的账号和渠道。我原本只是想填饱肚子，却意外地撞破了一个隐藏在市井之中的秘密。气氛骤然变得紧张而神秘。我意识到，这可能是一个意外的信息源，一个潜在的盟友，或许能帮我在职场中获得一些意想不到的优势。

我故作镇定，心中却已是波涛汹涌。既然他自称“号商”，那他一定对“数据”和“系统”的门道有所了解。我决定考考他，看看这号商的成色究竟如何。

“老板，”我清了清嗓子，声音尽量保持平稳，“我有点好奇，如果是在一个ERP系统里，进货单上明明有四行明细，为什么明细账却只能查到两行？”

老板的笑容微微凝固，眼神中闪过一丝不易察觉的警觉，但很快又恢复了那副老谋深算的样子。他慢悠悠地擦了擦手，低声说道：“有些东西，是不能随便查的。”他的回答避重就轻，并没有正面回应我的问题。

我眉头微皱，看来他并不想轻易暴露什么。我再次提醒他，把问题限定得更具体些，看他还能怎么搪塞。

“我是说在ERP系统操作中，和存货有关的部分，”我再次明确地提醒他，语气中带着一丝不容置疑，“为什么进货单有四行，而明细账只能查到两行？”

老板的脸色微微一变，显然我的问题触及了他的敏感点。他沉默了片刻，随后压低了声音，几乎是耳语：“这部分数据，有特殊处理，非必要不宜过问。”他的眼神变得深邃起来，似乎在警告我不要再追问下去。

## 第二章：城管与RTX4090的荒诞剧

老板的回答让我彻底失望。什么“号商”？根本就是个装腔作势的江湖骗子！连这么简单的财务系统问题都避而不谈，还搞什么“特殊处理”，简直滑稽。我心中的那点期待瞬间烟消云散，取而代之的是一股被愚弄的恼怒。

既然他不是真号商，那我就没必要再跟他耗着了。这种占道经营的小摊贩，就该让城管来好好“管理”一下。

“老板，”我冷冷地开口，语气中带着一丝不耐烦，“城管的电话是多少？我想举报这个摊位。”

老板的脸色彻底沉了下来，显得有些不耐烦，但还是冷冷地甩给我一个号码：“自己打！”

我掏出手机，毫不犹豫地拨通了那个号码。电话那头传来一阵嘈杂的背景音，接着是一个懒洋洋的声音：“喂，城管。”我简要说明了情况，挂断电话，心中暗自期待着城管的到来，能给这个装神弄鬼的摊主一点教训。

没过多久，一阵由远及近的电动车引擎声打破了清晨的宁静。我抬头望去，只见一队身穿制服的人马，骑着清一色的雅迪电动车，浩浩荡荡地驶来。领头的是一个身材魁梧的城管，胸前的名牌赫然写着“小金果”。

小金果利落地从车上跳下，他身后跟着四名帮手，其中两名手脚麻利地从车上搬下工具，似乎准备干活。然而，最让人目瞪口呆的是，后面还跟着足足十一位穿着厨师服的人！他们手里还拿着笔记本和笔，脸上写满了好奇与期待。

小金果朝摊主这边扫了一眼，然后大步流星地走过来，语气却出乎意料地温和：“老王啊，听说你这儿有炸山楂片？”他顿了顿，眼神转向那堆椰子壳，“我们这几位厨师傅，听说你最近研究出了干锅椰子壳的新技巧，特地来学习观摩的！”

这番话让我目瞪口呆。城管带着厨师团来学习炸山楂片和干锅椰子壳？这算哪门子事？整个场面瞬间变得荒诞而超现实。

就在这混乱的时刻，我心中的那股无名火突然被点燃了。超能力觉醒，想当守护者，结果被一个假号商骗了不说，还遇到这么一群奇葩的城管和厨师。我感到一种强烈的挫败感和被戏弄的愤怒。

我猛地向前一步，心中的怒火化作一道无形的波澜，瞬间将我包裹的隐形状态冲破！

我的身影在摊主面前骤然显现，带着一股不容置疑的压迫感。摊主吓了一跳，身体猛地向后一缩，脸上写满了惊恐。旁边的城管和小金果也愣住了，厨师们更是直接停下了笔记，所有人的目光都聚焦在我身上。

“赶快给我一块RTX4090！”我怒声吼道，声音带着一丝颤抖，那是愤怒与某种难以言喻的冲动交织在一起。我甚至没意识到，我要求的是一块显卡，而不是什么实际的物品，仿佛这块显卡就能平息我内心的所有不满。

摊主显得惊慌失措，他四处张望，显然没料到我会突然现身，更没料到会提出如此莫名其妙的要求。他结结巴巴地说：“RTX……RTX4090？那……那不是……”

我的话语，我的出现，让整个场面陷入了死寂。所有人都呆滞地看着我，仿佛我是从天而降的怪物。

我这才后知后觉地意识到——我竟然忘了，我刚才一直都是隐身状态！我的超能力，在愤怒之下，竟然自行解除了！

摊主惊恐地看着我，又看了看那口煮着椰子壳的大锅，脸上挤出一个比哭还难看的笑容，带着哭腔说：“大侠饶命啊！N系……N系都在锅里，实在拿不出来啊！”

N系都在锅里？我看着那口冒着热气的干锅，再看看周围一脸懵逼的城管和厨师们，只觉得一阵头晕目眩。这到底是什么鬼地方？我的超能力觉醒后的第一天，竟然以这样一种荒诞的方式展开了。

十分钟小说

<div style="background: linear-gradient(135deg, #1a1a1a 0%, #0a3d62 100%); 
            padding: 3rem 2rem; 
            text-align: center; 
            border-radius: 8px; 
            border: 1px solid rgba(255, 255, 255, 0.1); 
            box-shadow: 0 2px 10px rgba(0, 0, 0, 0.2);">
    <h1 style="color: #00ff88;
               font-family: Arial, sans-serif;
               font-size: 2.5rem;
               text-align: center;
               background: linear-gradient(90deg, #00ff88 0%, #00ffff 100%);
               -webkit-background-clip: text;
               -webkit-text-fill-color: transparent;
               position: relative;
               letter-spacing: 2px;
               margin: 0;
               font-weight: 600;">
        API获取无版权无水印的图片
    </h1>
</div>

---


在做[科技新闻](https://topwind.top/)时候需要一张封面图，这里找到一个可以获取无版权图片的API：[pexels](https://www.pexels.com/api/):

> 请勿滥用API。默认情况下，API的速率限制为每小时200个请求和每月 20000个请求。你可以联系我们，申请提高此限额，但请提供示例，或做好准备提供演示文件，确保清晰展示你使用API时已注明归属。如果你符合我们的API条款，则可以免费获得无限次请求。 

这个额度是够够的，这里记录下



## API格式

``` GET
curl -X GET \
  "https://api.pexels.com/v1/search?query=YOUR_QUERY_VALUE&per_page=50&orientation=landscape" \
  -H "Authorization: --" \
```

这里我用的是按关键词搜索图片，之前是热门图片随机选一个，但这这的热门图片跟新的比较慢；`orientation` 这个参数挺好，可以选择横竖方向


| 参数名        | 类型      | 是否必填 | 描述/备注                                                                                             |
| :------------ | :-------- | :------- | :---------------------------------------------------------------------------------------------------- |
| `query`       | `string`  | 必填     | 搜索查询关键词。例如："Ocean" (海洋)、"Tigers" (老虎) 等。                                            |
| `orientation` | `string`  | 可选     | 期望的照片方向。可选值：`landscape` (横向), `portrait` (纵向), `square` (正方形)。                        |
| `size`        | `string`  | 可选     | 最小照片尺寸。可选值：`large` (约24MP), `medium` (约12MP), `small` (约4MP)。                             |
| `color`       | `string`  | 可选     | 期望的照片颜色。可选值：`red`, `orange`, `yellow` 等预定义颜色，或任何十六进制颜色代码 (例如 `#ffffff`)。 |
| `locale`      | `string`  | 可选     | 搜索的语言环境。具体支持的语言环境请参考 Pexels 官方文档。                                              |
| `page`        | `integer` | 可选     | 请求的页码。默认值：`1`。                                                                             |
| `per_page`    | `integer` | 可选     | 每页返回的结果数量。默认值：`15`，最大值：`80`。                                                        |

## FastGPT 配置

![图片.png](/static/img/f8738026afcf8479553ce9f6feb36f8c.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

复制导入即可，

``` json
{"nodes":[{"nodeId":"pluginInput","name":"workflow:template.plugin_start","intro":"workflow:intro_plugin_input","avatar":"core/workflow/template/workflowStart","flowNodeType":"pluginInput","showStatus":false,"position":{"x":-749.7759166230271,"y":-139.38774480779273},"version":"481","inputs":[],"outputs":[]},{"nodeId":"pluginOutput","name":"common:core.module.template.self_output","intro":"workflow:intro_custom_plugin_output","avatar":"core/workflow/template/pluginOutput","flowNodeType":"pluginOutput","showStatus":false,"position":{"x":2271.224083376973,"y":-337.3877448077927},"version":"481","inputs":[{"renderTypeList":["reference"],"valueType":"string","canEdit":true,"key":"图片地址","label":"图片地址","isToolOutput":true,"description":"","required":true,"value":["tw2nb6umKVlJOd6Z","erqzi6Id9qNIXeGS"]},{"renderTypeList":["reference"],"valueType":"arrayString","canEdit":true,"key":"地址数组","label":"地址数组","isToolOutput":true,"description":"","required":true,"value":[["wNp0yak88GcQXoQv","数组"]]},{"renderTypeList":["reference"],"valueType":"string","canEdit":true,"key":"随机一个","label":"随机一个","isToolOutput":true,"description":"","required":true,"value":["kOcxMMVf32NBeL8M","qLUQfhG0ILRX"]}],"outputs":[]},{"nodeId":"pluginConfig","name":"common:core.module.template.system_config","intro":"","avatar":"core/workflow/template/systemConfig","flowNodeType":"pluginConfig","position":{"x":-520.2483102852332,"y":-712.6924771283639},"version":"4811","inputs":[],"outputs":[]},{"nodeId":"tw2nb6umKVlJOd6Z","name":"HTTP 请求","intro":"可以发出一个 HTTP 请求，实现更为复杂的操作（联网搜索、数据库查询等）","avatar":"core/workflow/template/httpRequest","flowNodeType":"httpRequest468","showStatus":true,"position":{"x":262.2240833769729,"y":-565.8877448077927},"version":"481","inputs":[{"key":"system_addInputParam","renderTypeList":["addInputParam"],"valueType":"dynamic","label":"","required":false,"description":"common:core.module.input.description.HTTP Dynamic Input","customInputConfig":{"selectValueTypeList":["string","number","boolean","object","arrayString","arrayNumber","arrayBoolean","arrayObject","arrayAny","any","chatHistory","datasetQuote","dynamic","selectDataset","selectApp"],"showDescription":false,"showDefaultValue":true},"valueDesc":"","debugLabel":"","toolDescription":""},{"key":"system_httpMethod","renderTypeList":["custom"],"valueType":"string","label":"","value":"GET","required":true,"valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"key":"system_httpTimeout","renderTypeList":["custom"],"valueType":"number","label":"","value":30,"min":5,"max":600,"required":true,"valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"key":"system_httpReqUrl","renderTypeList":["hidden"],"valueType":"string","label":"","description":"common:core.module.input.description.Http Request Url","placeholder":"https://api.ai.com/getInventory","required":false,"value":"https://api.pexels.com/v1/search","valueDesc":"","debugLabel":"","toolDescription":""},{"key":"system_httpHeader","renderTypeList":["custom"],"valueType":"any","value":[{"key":"Authorization","value":"---","type":"string"}],"label":"","description":"common:core.module.input.description.Http Request Header","placeholder":"common:core.module.input.description.Http Request Header","required":false,"valueDesc":"","debugLabel":"","toolDescription":""},{"key":"system_httpParams","renderTypeList":["hidden"],"valueType":"any","value":[{"key":"query","value":"{{$tw2nb6umKVlJOd6Z.query$}}","type":"string"},{"key":"per_page","value":"50","type":"string"},{"key":"orientation ","type":"string","value":"landscape"}],"label":"","required":false,"valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"key":"system_httpJsonBody","renderTypeList":["hidden"],"valueType":"any","label":"","required":false,"valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"key":"system_httpFormBody","renderTypeList":["hidden"],"valueType":"any","value":[],"label":"","required":false,"valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"key":"system_httpContentType","renderTypeList":["hidden"],"valueType":"string","value":"json","label":"","required":false,"valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"renderTypeList":["reference"],"valueType":"string","canEdit":true,"key":"query","label":"query","customInputConfig":{"selectValueTypeList":["string","number","boolean","object","arrayString","arrayNumber","arrayBoolean","arrayObject","arrayAny","any","chatHistory","datasetQuote","dynamic","selectDataset","selectApp"],"showDescription":false,"showDefaultValue":true},"required":true,"value":["y0a8eGqMiV881Fwk","qLUQfhG0ILRX"]}],"outputs":[{"id":"error","key":"error","label":"请求错误","description":"HTTP请求错误信息，成功时返回空","valueType":"object","type":"static","valueDesc":""},{"id":"httpRawResponse","key":"httpRawResponse","required":true,"label":"原始响应","description":"HTTP请求的原始响应。只能接受字符串或JSON类型响应数据。","valueType":"any","type":"static","valueDesc":""},{"id":"system_addOutputParam","key":"system_addOutputParam","type":"dynamic","valueType":"dynamic","label":"输出字段提取","customFieldConfig":{"selectValueTypeList":["string","number","boolean","object","arrayString","arrayNumber","arrayBoolean","arrayObject","arrayAny","any","chatHistory","datasetQuote","dynamic","selectDataset","selectApp"],"showDescription":false,"showDefaultValue":false},"description":"可以通过 JSONPath 语法来提取响应值中的指定字段","valueDesc":""},{"id":"erqzi6Id9qNIXeGS","valueType":"string","type":"dynamic","key":"$.photos[*].src.large","label":"$.photos[*].src.large"}]},{"nodeId":"wNp0yak88GcQXoQv","name":"json－返回数组","intro":"","avatar":"core/app/type/pluginFill","flowNodeType":"pluginModule","showStatus":true,"position":{"x":1000.2240833769729,"y":-116.88774480779273},"version":"67d6ebf096d118127c98357d","inputs":[{"key":"system_forbid_stream","renderTypeList":["switch"],"valueType":"boolean","label":"禁用流输出","description":"强制设置嵌套运行的应用，均以非流模式运行","value":false,"valueDesc":"","debugLabel":"","toolDescription":""},{"renderTypeList":["reference"],"selectedTypeIndex":0,"valueType":"string","canEdit":false,"key":"json","label":"json","description":"","defaultValue":"","list":[{"label":"","value":""}],"maxFiles":5,"canSelectFile":true,"canSelectImg":true,"required":true,"value":["tw2nb6umKVlJOd6Z","erqzi6Id9qNIXeGS"],"valueDesc":"","debugLabel":"","toolDescription":""}],"outputs":[{"id":"数组","type":"static","key":"数组","valueType":"arrayString","label":"数组","description":"","valueDesc":""}],"pluginId":"67acb78e8054db1ced7fd48c"},{"nodeId":"kOcxMMVf32NBeL8M","name":"代码运行","intro":"执行一段简单的脚本代码，通常用于进行复杂的数据处理。","avatar":"core/workflow/template/codeRun","flowNodeType":"code","showStatus":true,"position":{"x":1644.2240833769729,"y":-83.88774480779273},"version":"482","inputs":[{"key":"system_addInputParam","renderTypeList":["addInputParam"],"valueType":"dynamic","label":"","required":false,"description":"workflow:these_variables_will_be_input_parameters_for_code_execution","customInputConfig":{"selectValueTypeList":["string","number","boolean","object","arrayString","arrayNumber","arrayBoolean","arrayObject","arrayAny","any","chatHistory","datasetQuote","dynamic","selectDataset","selectApp"],"showDescription":false,"showDefaultValue":true},"valueDesc":"","debugLabel":"","toolDescription":""},{"key":"codeType","renderTypeList":["hidden"],"label":"","valueType":"string","value":"js","valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"key":"code","renderTypeList":["custom"],"label":"","valueType":"string","value":"function main({data1}){\n    const randomElement = data1[Math.floor(Math.random() * data1.length)];\n  return {\n      result: randomElement,\n  }\n}","valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"renderTypeList":["reference"],"valueType":"arrayString","canEdit":true,"key":"data1","label":"data1","customInputConfig":{"selectValueTypeList":["string","number","boolean","object","arrayString","arrayNumber","arrayBoolean","arrayObject","arrayAny","any","chatHistory","datasetQuote","dynamic","selectDataset","selectApp"],"showDescription":false,"showDefaultValue":true},"required":true,"value":[["wNp0yak88GcQXoQv","数组"]],"valueDesc":"","description":"","debugLabel":"","toolDescription":""}],"outputs":[{"id":"system_rawResponse","key":"system_rawResponse","label":"完整响应数据","valueType":"object","type":"static","valueDesc":"","description":""},{"id":"error","key":"error","label":"运行错误","description":"代码运行错误信息，成功时返回空","valueType":"object","type":"static","valueDesc":""},{"id":"system_addOutputParam","key":"system_addOutputParam","type":"dynamic","valueType":"dynamic","label":"","customFieldConfig":{"selectValueTypeList":["string","number","boolean","object","arrayString","arrayNumber","arrayBoolean","arrayObject","arrayAny","any","chatHistory","datasetQuote","dynamic","selectDataset","selectApp"],"showDescription":false,"showDefaultValue":false},"description":"将代码中 return 的对象作为输出，传递给后续的节点。变量名需要对应 return 的 key","valueDesc":""},{"id":"qLUQfhG0ILRX","type":"dynamic","key":"result","valueType":"string","label":"result","valueDesc":"","description":""}]},{"nodeId":"y0a8eGqMiV881Fwk","name":"随机关键词","intro":"执行一段简单的脚本代码，通常用于进行复杂的数据处理。","avatar":"core/workflow/template/codeRun","flowNodeType":"code","showStatus":true,"position":{"x":-257.7759166230271,"y":-402.8877448077927},"inputs":[{"key":"system_addInputParam","renderTypeList":["addInputParam"],"valueType":"dynamic","label":"","required":false,"description":"workflow:these_variables_will_be_input_parameters_for_code_execution","customInputConfig":{"selectValueTypeList":["string","number","boolean","object","arrayString","arrayNumber","arrayBoolean","arrayObject","arrayAny","any","chatHistory","datasetQuote","dynamic","selectDataset","selectApp"],"showDescription":false,"showDefaultValue":true},"valueDesc":"","debugLabel":"","toolDescription":""},{"key":"codeType","renderTypeList":["hidden"],"label":"","valueType":"string","value":"js","valueDesc":"","description":"","debugLabel":"","toolDescription":""},{"key":"code","renderTypeList":["custom"],"label":"","valueType":"string","value":"const keywords = [\n        \"Technology\",\n        \"Innovation\",\n        \"Science\",\n        \"Artificial Intelligence\",\n        \"Sustainability\",\n        \"Data Science\",          // 新增\n        \"Research\",              // 新增\n        \"Automation\",            // 新增\n        \"Bioengineering\",        // 新增\n        \"Quantum\"                // 新增\n];\nfunction main({data1, data2}){\n  const numberOfKeywords = keywords.length; // 在本例中为 10\n      // 3. 生成一个随机索引\n    const randomIndex = Math.floor(Math.random() * numberOfKeywords);\n    // 4. 根据随机索引获取关键词\n    const selectedKeyword = keywords[randomIndex];\n    return {result:selectedKeyword};\n}\n\n","valueDesc":"","description":"","debugLabel":"","toolDescription":""}],"outputs":[{"id":"system_rawResponse","key":"system_rawResponse","label":"完整响应数据","valueType":"object","type":"static","valueDesc":"","description":""},{"id":"error","key":"error","label":"运行错误","description":"代码运行错误信息，成功时返回空","valueType":"object","type":"static","valueDesc":""},{"id":"system_addOutputParam","key":"system_addOutputParam","type":"dynamic","valueType":"dynamic","label":"","customFieldConfig":{"selectValueTypeList":["string","number","boolean","object","arrayString","arrayNumber","arrayBoolean","arrayObject","arrayAny","any","chatHistory","datasetQuote","dynamic","selectDataset","selectApp"],"showDescription":false,"showDefaultValue":false},"description":"将代码中 return 的对象作为输出，传递给后续的节点。变量名需要对应 return 的 key","valueDesc":""},{"id":"qLUQfhG0ILRX","type":"dynamic","key":"result","valueType":"string","label":"result","valueDesc":"","description":""}]}],"edges":[{"source":"tw2nb6umKVlJOd6Z","target":"pluginOutput","sourceHandle":"tw2nb6umKVlJOd6Z-source-right","targetHandle":"pluginOutput-target-left"},{"source":"tw2nb6umKVlJOd6Z","target":"wNp0yak88GcQXoQv","sourceHandle":"tw2nb6umKVlJOd6Z-source-right","targetHandle":"wNp0yak88GcQXoQv-target-left"},{"source":"wNp0yak88GcQXoQv","target":"pluginOutput","sourceHandle":"wNp0yak88GcQXoQv-source-right","targetHandle":"pluginOutput-target-left"},{"source":"wNp0yak88GcQXoQv","target":"kOcxMMVf32NBeL8M","sourceHandle":"wNp0yak88GcQXoQv-source-right","targetHandle":"kOcxMMVf32NBeL8M-target-left"},{"source":"kOcxMMVf32NBeL8M","target":"pluginOutput","sourceHandle":"kOcxMMVf32NBeL8M-source-right","targetHandle":"pluginOutput-target-left"},{"source":"pluginInput","target":"y0a8eGqMiV881Fwk","sourceHandle":"pluginInput-source-right","targetHandle":"y0a8eGqMiV881Fwk-target-left"},{"source":"y0a8eGqMiV881Fwk","target":"tw2nb6umKVlJOd6Z","sourceHandle":"y0a8eGqMiV881Fwk-source-right","targetHandle":"tw2nb6umKVlJOd6Z-target-left"}],"chatConfig":{"welcomeText":"","variables":[],"questionGuide":{"open":false,"model":"gpt-4o-mini","customPrompt":""},"ttsConfig":{"type":"web"},"whisperConfig":{"open":false,"autoSend":false,"autoTTSResponse":false},"chatInputGuide":{"open":false,"textList":[],"customUrl":""},"instruction":"","autoExecute":{"open":false,"defaultPrompt":""},"_id":"684158be6c34053cae1c4503"}}

```

:::info{title="相关连接"}
[TopWind技术栈](https://blog.shizhuoran.top/post/84)

[pexelsAPI文档](https://www.pexels.com/zh-cn/api/documentation/#photos-curated)

[pexelsAPI](https://www.pexels.com/api/)

:::

获取无版权无水印的图片

<div style="background: linear-gradient(135deg, #1a1a1a 0%, #0a3d62 100%); 
            padding: 3rem 2rem; 
            text-align: center; 
            border-radius: 8px; 
            border: 1px solid rgba(255, 255, 255, 0.1); 
            box-shadow: 0 2px 10px rgba(0, 0, 0, 0.2);">
    <h1 style="color: #00ff88;
               font-family: Arial, sans-serif;
               font-size: 2.5rem;
               text-align: center;
               background: linear-gradient(90deg, #00ff88 0%, #00ffff 100%);
               -webkit-background-clip: text;
               -webkit-text-fill-color: transparent;
               position: relative;
               letter-spacing: 2px;
               margin: 0;
               font-weight: 600;">
        TopWind技术栈
    </h1>
</div>

---

学英语不能停，又想看新闻摸鱼

[Topwind.top](https://topwind.top)，又搭了个博客，搜集科技新闻并增加英语对照，这里记录下用到的工具

### 工作流【自部署】

[FastGPT](https://fastgpt.cn/)

就是一个流程：调新闻接口，检索信息，调用AI生成文章 和 语音播报，提交草稿；


![mermaid-diagram-2025-05-20-.png](/static/img/182f75e9d7e2420e62768a7a26f699f4.mermaid-diagram-2025-05-20-.webp)

###  新闻API【自部署】

[DailyHotApi](https://github.com/imsyy/DailyHotApi)

可以获取各平台的热点新闻



### 检索引擎【付费接口】

HotAPI只返回部分信息，标题，连接，还需要搜一下详细信息，保证数据完整可靠（虽然是简报）

这里用的[智谱API](https://www.bigmodel.cn/dev/howuse/websearch) 模型是 `search_pro_quark` `search_std`，分别是 0.05/次 和 0.01/次，`search_pro_quark` 返回的数据特别全，可以直接拿来用；

### AI模型【嫖】

主体用的 `火山DSV3`，其他用的`Grok3`（没余额就换了）；

`火山DSV3`主要负责过滤和写文章，先对热点信息就行了过滤，这里过滤不老好的，过滤科技新闻，基本分不清什么是科技新闻，然后又按分类重排了一次；
`Grok3` 负责写语音播报，写的比V3好多了；

### TTS【自部署】

[ZBTTS](https://github.com/zuoban/tts)

这个也支持接口，长语音不会截断

### 博客平台【自部署】

用的还是[Vanblog](https://github.com/Mereithhh/vanblog)，比较顺手，接口很简单；

TopWind技术栈

<div style="background: linear-gradient(135deg, #1a1a1a 0%, #0a3d62 100%); 
            padding: 3rem 2rem; 
            text-align: center; 
            border-radius: 8px; 
            border: 1px solid rgba(255, 255, 255, 0.1); 
            box-shadow: 0 2px 10px rgba(0, 0, 0, 0.2);">
    <h1 style="color: #00ff88;
               font-family: Arial, sans-serif;
               font-size: 2.5rem;
               text-align: center;
               background: linear-gradient(90deg, #00ff88 0%, #00ffff 100%);
               -webkit-background-clip: text;
               -webkit-text-fill-color: transparent;
               position: relative;
               letter-spacing: 2px;
               margin: 0;
               font-weight: 600;">
        使用Northflank搭建Gitea
    </h1>
</div>

---

[Northflank](https://app.northflank.com) 的免费服务器 0.2CPU + 512M内存 + 5GSSD，昨天搭了一个Gitea还是挺顺手，不用梯子速度很快，需要**VISA信用卡**

# 1. 创建 Project
首先登陆账号，谷歌账号、github是可以直接登陆的，我使用github 非常方便

![图片.png](/static/img/6e0af13557c120bf3adeb5ed107c5f36.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)



![image.webp](/static/img/9f83579b2d4ba307337d9d190b5179e8.image.webp)


![图片.png](/static/img/bfa3d7134fdad8bdb96d44610bd542f3.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

# 2. 创建Service

输入Docker地址 `docker.gitea.com/gitea:1.23.7-rootless`

![图片.png](/static/img/769e3d5e8d5786966954414b531c1b22.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

最后这里不要忘记选一下，默认是 0.1+265M ，我试了不够，没选也行，可以改

![图片.png](/static/img/39809ec5d98c9b143c95bb40290201fb.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

然后会提示绑定信用卡，没截图

如果没问题就创建成功了，会自动拉取构建，因为没什么环境变量所以没有

# 3. 分配 Volumes

创建之后要持久化一下，否则数据会丢

![图片.png](/static/img/fa4cd0ed77faea04fbe5d23f1ef44a50.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

可以在这重启

![图片.png](/static/img/e6708ebd073d91c6fa6d0d4aa2eb4d79.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

# 4. 进入控制台修改Gitea配置

点击容器，可以查看日志，进入Shell

![图片.png](/static/img/1f63699cf93e4b20b078b9066b076f26.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)


![图片.png](/static/img/8c7d30c87f1c0773af3c314dac92c59a.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)


![图片.png](/static/img/20b30aad4abb31f9e3965e6752c091b4.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

如果不修改配置就不用修改配置了 [这里是Gitea配置说明](https://docs.gitea.com/zh-cn/administration/config-cheat-sheet)

![图片.png](/static/img/f08e9805ff45bec8ae33dce0096199eb.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

# 5. 访问

DNS 菜单里会显示分配的随机域名，我这里用了自己的，勾选下面的勾，那个随机域名会失效；

![图片.png](/static/img/1ca03eda8f4414cc9da167cffe7ec381.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

域名在首页（不是项目页）添加，参照步骤即可，一个TEXT 和一个 CNAME ，这里还能管理子集域名，我也没用上

![图片.png](/static/img/c61d9501cd0f1ab979e9c671f5b9dad7.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

---

然后就可以愉快的使用了 

![图片.png](/static/img/1619fa6fc93a9a6cdd557992ecd1d328.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

Northflank嫖一个免费VPS搭建Gitea

<div style="background: linear-gradient(135deg, #1a1a1a 0%, #0a3d62 100%); 
            padding: 3rem 2rem; 
            text-align: center; 
            border-radius: 8px; 
            border: 1px solid rgba(255, 255, 255, 0.1); 
            box-shadow: 0 2px 10px rgba(0, 0, 0, 0.2);">
    <h1 style="color: #00ff88;
               font-family: Arial, sans-serif;
               font-size: 2.5rem;
               text-align: center;
               background: linear-gradient(90deg, #00ff88 0%, #00ffff 100%);
               -webkit-background-clip: text;
               -webkit-text-fill-color: transparent;
               position: relative;
               letter-spacing: 2px;
               margin: 0;
               font-weight: 600;">
        基于Harbor的提交和拉取
    </h1>
</div>

---


> 之前分享过[基于Gitea搭建的自动部署流程](https://blog.shizhuoran.top/post/13)，是在公司服务器搭建的，用了好些的手写脚本，随着`docker`用的越来越熟练，又搭建了`Harbor`，CICD这个过程也比较方便了，前端用的开源的`Dockge`进行拉取部署，`vs2022`发布，这里记录下；



# 1. Harbor搭建
[略](https://www.bilibili.com/video/BV1D4421X7Zo/)

总之我这里建了一个 `project` 项目,`docker-proxy`也是自己搭建的；



# 2. vs2022发布到Harbor

这里比较的困难，问AI也稀里糊涂的，试验了很多次，总算提交上去了;

在vs创建项目时有docker的选项：启动容器支持，有生成类型，`Dockerfile` 和 `.NetSDK`，这不影响，能拉到.netSDK就行，`Dockerfile` 生成的也对，都能生成一个Docker image；
 
![图片.png](/static/img/3c86f3b6cc2d7231073a30c10edd538c.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

## 重点是提交到`Harbor`

### 1. 选择Docker发布
![图片.png](/static/img/4eeea47c3eabd9ac30ffc56fd8ccf4e4.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

### 2. 选择其他注册

![图片.png](/static/img/3337889e0b8bbf707b84232dfec45aff.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

### 3. 下一步-完成
完成后会有一个 `pubxml`文件，在`Properties`-`PublishProfiles` 下，可以重命名

![图片.png](/static/img/e84c5f7a6cdfb9a5f1e9b29f5602e682.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

### 4. 写入地址
编辑这个文件，把`Harbor`的地址写上，这里的`项目名`就是发布后的项目名称
```
<RegistryUrl>地址</RegistryUrl>
<ContainerRegistry>地址</ContainerRegistry>
<ContainerRepository>project/项目名</ContainerRepository>
<UserName>admin</UserName>
```

然后正常点击发布，构建后就会推送到`Harbor`，这里要**注意**，本地要`开启Docker服务`，我是直接把 `Docker DeskTop`开着，否则构建失败，但是会提示发布成功，`Harbor`也没有；

# 3. 拉取

`Dockge`就可以拉取更新了，image就是 `地址/project/xxx`就行了


![图片.png](/static/img/e17d2764e06d8f21bf2f0b827a8af315.%C3%A5%C2%9B%C2%BE%C3%A7%C2%89%C2%87.webp)

---

这样每次点发布，然后点更新，就能用了，自己的小项目很方便