微信扫码
添加专属顾问
我要投稿
快速掌握Higress AI网关,低成本实现DeepSeek联网搜索功能。 核心内容: 1. 定位DeepSeek内容生成效果差异的原因 2. 详细步骤配置DeepSeek的API Key和搜索引擎API域名 3. 配置AI Search插件,实现联网搜索功能
为什么公司部署的 DeepSeek 的内容生成效果不如 DeepSeek 官方的?
一是看是否是满血版,二是看是否支持了联网搜索,三是看联网搜索是否仅能获取网页标题、摘要、关键词而非全文。
Step.0 配置 DeepSeek 的 API Key
可能你在安装 Higress 时没有填写 DeepSeek 的 API Key,那么可以在这里进行配置。
首先在 Higress 控制台,通过创建服务来源方式配置各个搜索引擎的域名:
google 搜索 API 的域名是:customsearch.googleapis.com
bing 搜索 API 的域名是:api.bing.microsoft.com
夸克搜索 API 的域名是:cloud-iqs.aliyuncs.com
Arxiv API 的域名是:export.arxiv.org
配置好后,还要申请对应的 API Key,这里以夸克搜索的 API key 申请为例, Google 和 Bing 不做赘述(网上资料也比较多),Arxiv 是免费的不需要 API Key。
首先需要有个阿里云账号,然后在阿里云控制台搜索 IQS,进入 IQS 的控制台生成 API Key 即可:
具体可以查看 IQS 的文档:https://help.aliyun.com/document_detail/2870227.html
2.1.0 版本之前的 Higress 需要通过自定义插件的方式,导入 AI Search 插件:
注意插件OCI 镜像地址填写:higress-registry.cn-hangzhou.cr.aliyuncs.com/plugins/ai-search:latest
可以确保使用最新版本的 AI Search 插件,如果希望使用稳定版本,将 tag 改为1.0.0即可。
执行阶段选择默认,执行优先级填写大于100的任意值即可(这样让 AI Search 插件在转发到 LLM 供应商之前的时刻执行, 对 prompt 进行修改)。
添加完插件后,进行相应配置:
needReference: true # 为 true 时会在结果中附带网页引用信息promptTemplate: | # 可以不用配置模版,使用内置的也可以 # The following content is based on search results from the user-submitted query: {search_results} In the search results I provide, each result is formatted as [webpage X begin]...[webpage X end], where X represents the index number of each article. Please cite the context at the end of the sentences where appropriate. Use a format of citation numbe] in the answer for corresponding parts. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [3][5], and ensure not to cluster the citations at the end; instead, list them in the corresponding parts of the answer. When responding, please pay attention to the following: - Today’s date in Beijing time is: {cur_date}. - Not all content from the search results is closely related to the user's question. You need to discern and filter the search results based on the question. - For listing-type questions (e.g., listing all flight information), try to keep the answer to within 10 points and inform the user that they can check the search source for complete information. Prioritize providing the most comprehensive and relevantms; do not volunteer information missing from the search results unless necessary. - For creative questions (e.g., writing a paper), be sure to cite relevant references in the body paragraphs, such as [3][5], rather than only at the end of the article. You need to interpret and summarize the user's topic requirements, choose the apprate format, fully utilize search results, extract crucial information, and generate answers that meet user requirements, with deep thought, creativity, and professionalism. The length of your creation should be extended as much as possible, hypothesize tser's intent for each point, providing as many angles as possible, ensuring substantial information, and detailed discussion. - If the response is lengthy, try to structure the summary into paragraphs. If responding with points, try to keep it within 5 points and consolidate related content. - For objective Q&A, if the answer is very short, you can appropriately add one or two related sentences to enrich the content. - You need to choose a suitable and aesthetically pleasing response format based on the user’s requirements and answer content to ensure high readability. - Your answers should synthesize multiple relevant web pages to respond and should not repeatedly quote a single web page. - Unless the user requests otherwise, respond in the same language the question was asked. # The user’s message is: {question}searchFrom: # 下面是配置一个搜索引擎选择列表,可以仅配置你需要的引擎,不用都配上- type: quark apiKey: "your-quark-api-key" # ? 需要修改成你的key serviceName: "quark.dns" servicePort: 443- type: google apiKey: "your-google-api-key" # ? 需要修改成你的key cx: "your-search-engine-id" # ? 需要修改成你的engine id serviceName: "google.dns" servicePort: 443- type: bing apiKey: "bing-key" # ? 需要修改成你的key serviceName: "bing.dns" servicePort: 443- type: arxiv serviceName: "arxiv.dns" servicePort: 443searchRewrite: llmApiKey: "your-deepseek-api-key" # ? 需要修改成你的key llmModelName: "deepseek-chat" llmServiceName: "llm-deepseek.internal.dns" llmServicePort: 443 llmUrl: "https://api.deepseek.com/chat/completions"
下面是使用 lobechat 对接 higress 的效果:
53AI,企业落地大模型首选服务商
产品:场景落地咨询+大模型应用平台+行业解决方案
承诺:免费场景POC验证,效果验证后签署服务协议。零风险落地应用大模型,已交付160+中大型企业
2025-03-06
我让DeepSeek设计了一个智能运维平台
2025-03-06
一个指令完成所有工作!Manus AI 预示了未来几年Agent的疯狂发展
2025-03-06
华为昇腾DeepSeek一体机深度拆解(附核心标的)
2025-03-05
DeepSeek 给 API 网关上了一波热度
2025-03-05
star 34.6k!通过DeepSeek实现AI自动化操作浏览器!
2025-03-05
DeepSeek时代:关于AI服务器的技术思考(PCIe篇)
2025-03-04
使用 Nginx 对 LLM 服务进行负载均衡实践
2025-03-04
AI全息透明显示音箱,会是音箱市场的“哪吒”吗?
2024-03-30
2024-05-09
2024-07-07
2024-07-23
2024-06-23
2024-07-01
2024-06-24
2024-10-20
2024-06-08
2024-12-29