微信扫码
添加专属顾问
内置示例
<|begin_of_text|><|start_header_id|>system<|end_header_id|>Environment: ipythonTools: brave_search, wolfram_alphaCutting Knowledge Date: December 2023Today Date: 23 Jul 2024You are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>What is the current weather in Menlo Park, California?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
步骤 - 1 用户提示和系统提示
<|begin_of_text|><|start_header_id|>system<|end_header_id|>Environment: ipythonTools: brave_search, wolfram_alphaCutting Knowledge Date: December 2023Today Date: 23 Jul 2024You are a helpful Assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>Can you help me solve this equation: x^3 - 4x^2 + 6x - 24 = 0<|eot_id|><|start_header_id|>assistant<|end_header_id|>
步骤 - 2 模型确定调用哪个工具
<|python_tag|>wolfram_alpha.call(query="solve x^3 - 4x^2 + 6x - 24 = 0")<|eom_id|>
步骤 - 3 由工具即 Wolfram Alpha 生成响应。
{"queryresult": {"success": true,"inputstring": "solve x^3 - 4x^2 + 6x - 24 = 0","pods": [{"title": "Input interpretation","subpods": [{"title": "","plaintext": "solve x^3 - 4 x^2 + 6 x - 24 = 0"}]},{"title": "Results","primary": true,"subpods": [{"title": "","plaintext": "x = 4"},{"title": "","plaintext": "x = ± (i sqrt(6))"}]},...]}}步骤 - 4 使用工具响应重新提示模型
<|begin_of_text|><|start_header_id|>system<|end_header_id|>Environment: ipythonTools: brave_search, wolfram_alphaCutting Knowledge Date: December 2023Today Date: 23 Jul 2024You are a helpful Assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>Can you help me solve this equation: x^3 - 4x^2 + 6x - 24 = 0<|eot_id|><|start_header_id|>assistant<|end_header_id|><|python_tag|>wolfram_alpha.call(query="solve x^3 - 4x^2 + 6x - 24 = 0")<|eom_id|><|start_header_id|>ipython<|end_header_id|>{"queryresult": {"success": true, "inputstring": "solve x^3 - 4x^2 + 6x - 24 = 0", "pods": [{"title": "Input interpretation", "subpods": [{"title": "", "plaintext": "solve x^3 - 4 x^2 + 6 x - 24 = 0"}]}, {"title": "Results", "primary": true, "subpods": [{"title": "", "plaintext": "x = 4"}, {"title": "", "plaintext": "x = \u00b1 (i sqrt(6))"}]}, ... ]}}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
步骤 - 5 智能体对用户的回复
The solutions to the equation x^3 - 4x^2 + 6x - 24 = 0 are x = 4 and x = ±(i√6).<|eot_id|>
自定义工具调用示例
Meta Llama 3.1模型现在可以从单个消息输出自定义工具调用,以便更轻松地调用工具。模型本身并不执行调用;它提供结构化输出以方便执行器调用。可以在llama-agentic-system中找到一个示例执行器,工具格式类似于OpenAI 定义。
使用自定义工具调用时,要使模型输出eom_id,需要在系统提示符中添加以下指令:Environment: ipython。否则,它应该输出eot_id。
需要调整系统提示以告知模型如何处理工具调用输出
工具定义在用户提示中提供,因为这是模型针对内置 JSON 工具调用进行训练的方式。但是,也可以在系统提示中提供工具定义,并获得类似的结果。开发人员必须测试哪种方式最适合他们的用例。
步骤 - 1 用户提示自定义工具详细信息
<|begin_of_text|><|start_header_id|>system<|end_header_id|>Environment: ipythonTools: brave_search, wolfram_alphaCutting Knowledge Date: December 2023Today Date: 23 Jul 2024# Tool Instructions- Always execute python code in messages that you share.- When looking for real time information use relevant functions if available else fallback to brave_searchYou have access to the following functions:Use the function 'spotify_trending_songs' to: Get top trending songs on Spotify{"name": "spotify_trending_songs","description": "Get top trending songs on Spotify","parameters": {"n": {"param_type": "int","description": "Number of trending songs to get","required": true}}}If a you choose to call a function ONLY reply in the following format:<{start_tag}={function_name}>{parameters}{end_tag}wherestart_tag => `<function`parameters => a JSON dict with the function argument name as key and function argument value as value.end_tag => `</function>`Here is an example,<function=example_function_name>{"example_name": "example_value"}</function>Reminder:- Function calls MUST follow the specified format- Required parameters MUST be specified- Only call one function at a time- Put the entire function call reply on one line"- Always add your sources when using search results to answer the user queryYou are a helpful Assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>Can you check the top 5 trending songs on spotify?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
步骤 - 2 模型确定调用哪个工具
{"name": "get_current_conditions", "parameters": {"location": "San Francisco, CA", "unit": "Fahrenheit"}}<eot_id>步骤 - 3 调用工具的结果被传回模型
<|begin_of_text|><|start_header_id|>system<|end_header_id|>You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the orginal use question.<|eot_id|><|start_header_id|>user<|end_header_id|>Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.{"type": "function","function": {"name": "get_current_conditions","description": "Get the current weather conditions for a specific location","parameters": {"type": "object","properties": {"location": {"type": "string","description": "The city and state, e.g., San Francisco, CA"},"unit": {"type": "string","enum": ["Celsius", "Fahrenheit"],"description": "The temperature unit to use. Infer this from the user's location."}},"required": ["location", "unit"]}}}Question: what is the weather like in San Fransisco?<|eot_id|><|start_header_id|>assistant<|end_header_id|>{"name": "get_current_conditions", "parameters": {"location": "San Francisco, CA", "unit": "Fahrenheit"}}<|eot_id|><|start_header_id|>ipython<|end_header_id|>Clouds giving way to sun Hi: 76° Tonight: Mainly clear early, then areas of low clouds forming Lo: 56°"<|eot_id|><|start_header_id|>assistant<|end_header_id|>
步骤 - 4 模型生成用户的最终响应
The weather in Menlo Park is currently cloudy with a high of 76° and a low of 56°, with clear skies expected tonight.<eot_id>
Nvidia Agentic RAG(Llama-3.1)
对于Llama 3.1的强大工具调用功能能力,NVIDIA已与Meta 合作,以确保最新的 Llama 模型能够通过 NVIDIA NIM得到最佳部署。
https://developer.nvidia.com/blog/build-an-agentic-rag-pipeline-with-llama-3-1-and-nvidia-nemo-retriever-nims/https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1/https://github.com/meta-llama/llama-agentic-system/tree/main
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POC验证,效果达标后再合作。零风险落地应用大模型,已交付160+中大型企业
2026-06-30
花叔的这个神器直接让你的AI Agent出高保真原型、PPT和动画,20k stars不是盖的
2026-06-30
阿里达摩院开源语音识别:比Whisper快170倍还免费,CPU就能跑
2026-06-30
MiniMax M3 实测:第一流的模型,已经对执行层动手了
2026-06-30
DSpark:DeepSeek 如何让大模型推理提速 85%
2026-06-30
告别云端付费!3秒克隆你的声音,这款开源AI不用GPU,手机CPU就能实时跑
2026-06-30
阿里开源 ReMe:像写双链笔记一样给 AI Agent 做长期记忆
2026-06-30
一次关于 AI 需求交付Skills的优化升级
2026-06-30
阿里开源 Open Code Review:让 AI 代码审查从“会看”走向“看得准”
2026-04-09
2026-04-03
2026-04-18
2026-04-18
2026-06-22
2026-04-02
2026-05-10
2026-05-06
2026-05-20
2026-04-02
2026-06-16
2026-05-30
2026-05-16
2026-04-22
2026-04-21
2026-04-15
2026-04-09
2026-04-01
欢迎您使用【53AI 官方网站】(以下简称“本网站”或“我们”)。本《会员服务协议》(以下简称“本协议”)是您(以下简称“会员”或“用户”)与【深圳市博思协创网络科技有限公司】之间关于注册、登录及使用本网站会员服务所订立的法律协议。
在您注册或登录前,请务必审慎阅读、充分理解各条款内容,特别是免除或限制责任的条款、知识产权条款、争议解决条款等。此类条款将以加粗形式提示您注意。 当您通过微信公众号授权、手机验证码验证或其他方式成功登录本网站时,即视为您已完全理解并同意接受本协议的全部内容。
一、 定义
本网站:指由【深圳市博思协创网络科技有限公司】运营的,域名为【53ai.com】的网站及相关移动端页面。
会员服务:指本网站向注册会员提供的知识库文章查阅、内容检索及其他相关增值服务。
知识库内容:指本网站发布的包括但不限于文字、图表、数据、研究报告、行业分析等数字化内容资源。
二、 账号注册与登录
登录方式:本网站支持以下登录方式,您可根据实际情况选择:
微信公众号授权登录:您同意将您的微信OpenID信息授权给本网站,用于创建或关联会员账号。
手机验证码登录:您需提供真实有效的手机号码,并通过短信验证码完成身份验证与登录/注册。
账号安全:您的账号仅限您本人使用,禁止赠与、借用、租用、转让或售卖。因您保管不善导致的账号被盗、密码泄露等损失,由您自行承担。
实名认证:根据相关法律法规要求,我们可能要求您在特定功能下完成实名认证。如您拒绝提供,可能无法使用部分或全部服务。
未成年人保护:若您未满18周岁,请在法定监护人的陪同下阅读本协议,并在征得监护人同意后使用本服务。
三、 服务内容与规范
知识库查阅权限:会员登录后,有权按照其会员等级对应的权限范围,在线浏览、检索本网站知识库中的相关文章及内容。
服务变更:我们有权根据业务发展需要,调整、变更或终止部分服务内容,并将以网站公告、公众号消息等方式提前通知。
禁止行为:您在使用服务时不得实施以下行为:
利用技术手段批量爬取、下载、转存知识库内容;
将知识库内容用于商业目的或未经授权地向第三方传播;
干扰本网站正常运行或侵犯其他用户合法权益;
发布违法违规信息或从事违反公序良俗的活动。
四、 知识产权声明
权利归属:本网站知识库中的排版设计、软件代码等内容的知识产权均归【公司全称】或原权利人所有,受《中华人民共和国著作权法》等法律保护。
有限许可:本网站授予会员一项非独占、不可转让、不可转授权的普通许可,仅限于个人学习、研究之目的在线查阅知识库内容。
侵权追责:未经书面许可,任何单位或个人不得以任何形式复制、转载、摘编、镜像、汇编或以其他方式使用上述内容。一经发现,我们保留追究其法律责任的权利。
五、 个人信息保护
我们重视对您个人信息的保护。关于我们如何收集、使用、存储和保护您的个人信息,请单独阅读 《隐私政策》。
您通过微信公众号授权或手机号验证所提供的信息,我们将严格按照《个人信息保护法》的规定处理,仅用于身份识别、服务提供及安全验证等必要用途。
您可以随时通过网站设置或联系客服行使查阅、更正、删除个人信息及撤回授权同意的权利。
六、 免责声明
内容准确性:知识库内容仅供参考,不构成专业建议。我们不对其完整性、准确性、时效性作任何明示或暗示的保证,您应自行判断并承担使用风险。
不可抗力:因自然灾害、政策法规变化、网络故障、第三方平台接口异常(如微信接口维护、运营商短信通道故障)等不可抗力导致的服务中断或延迟,我们不承担违约责任。
第三方链接:本网站可能包含指向第三方网站的链接,该等网站的内容和服务不受我们控制,请您自行甄别风险。
七、 违约责任
如您违反本协议约定,我们有权视情节采取警告、限制功能、暂停服务、注销账号等措施,并保留要求赔偿损失的权利。
如因您的违约行为导致我们遭受行政处罚、第三方索赔或商誉损失,您应承担全部赔偿责任(包括但不限于罚款、赔偿金、律师费、公证费等)。
八、 法律适用与争议解决
本协议的订立、执行和解释均适用中华人民共和国大陆地区法律。
因本协议产生的或与本协议有关的任何争议,双方应友好协商解决;协商不成的,任何一方均可向【公司所在地】有管辖权的人民法院提起诉讼。
九、 其他
本协议构成双方就本服务达成的完整协议,取代此前任何口头或书面约定。
本协议任一条款被认定为无效或不可执行的,不影响其他条款的效力。
我们对本协议享有最终解释权,并在法律允许的范围内保留随时修改的权利。修改后的协议一经公布即生效,继续使用服务即视为同意修订内容。