Meta亲自下场教学Llama3.1 Agent/RAG！

<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Environment: ipythonTools: brave_search, wolfram_alpha
Cutting Knowledge Date: December 2023Today 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|>

<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Environment: ipythonTools: brave_search, wolfram_alpha
Cutting Knowledge Date: December 2023Today 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|>

{"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))"}]},...]}}

<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Environment: ipythonTools: brave_search, wolfram_alpha
Cutting Knowledge Date: December 2023Today 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|>

The solutions to the equation x^3 - 4x^2 + 6x - 24 = 0 are x = 4 and x = ±(i√6).<|eot_id|>

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Environment: ipythonTools: brave_search, wolfram_alpha
Cutting 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_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|>

{"name": "get_current_conditions", "parameters": {"location": "San Francisco, CA", "unit": "Fahrenheit"}}<eot_id>

<|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|>

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>

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