微信扫码
与创始人交个朋友
我要投稿
内置示例
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Environment: ipython
Tools: brave_search, wolfram_alpha
Cutting Knowledge Date: December 2023
Today Date: 23 Jul 2024
You 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: ipython
Tools: brave_search, wolfram_alpha
Cutting Knowledge Date: December 2023
Today Date: 23 Jul 2024
You 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: ipython
Tools: brave_search, wolfram_alpha
Cutting Knowledge Date: December 2023
Today Date: 23 Jul 2024
You 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: ipython
Tools: brave_search, wolfram_alpha
Cutting Knowledge Date: December 2023
Today 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_search
You 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}
where
start_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 query
You 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,企业落地应用大模型首选服务商
产品:大模型应用平台+智能体定制开发+落地咨询服务
承诺:先做场景POC验证,看到效果再签署服务协议。零风险落地应用大模型,已交付160+中大型企业
2024-12-21
基于AI智能助理的软件开源组件安全检查
2024-12-21
Llama2024年度要点总结
2024-12-21
重磅! Github Copilot 免费了
2024-12-20
万字长文帮你搞定AI Agent选型
2024-12-20
微软开源的 Markitdown 可将任意文件转换为 Markdown 格式,PDF 解析咋样?
2024-12-20
Claude的MCP(模型上下文协议)简介
2024-12-20
历时2年,华人团队力作,震撼开源生成式物理引擎Genesis,可模拟世界万物
2024-12-19
开源!轻量!AI 代码助手插件 Continue 使用体验如何?
2024-05-06
2024-07-25
2024-08-13
2024-06-12
2024-07-11
2024-06-16
2024-07-20
2024-09-20
2024-06-15
2024-07-25
2024-12-20
2024-12-19
2024-11-22
2024-11-19
2024-11-13
2024-11-13
2024-10-07
2024-09-22