main.py

import os
from huggingface_hub import InferenceClient

## You need a token from https://hf.co/settings/tokens. If you run this on Google Colab, you can set it up in the "settings" tab under "secrets". Make sure to call it "HF_TOKEN"
hf_token = os.getenv("HF_TOKEN")
if hf_token is None:
    raise ValueError("HF_TOKEN environment variable is not set")
os.environ["HF_TOKEN"] = hf_token

client = InferenceClient("meta-llama/Llama-3.2-3B-Instruct")
# if the outputs for next cells are wrong, the free model may be overloaded. You can also use this public endpoint that contains Llama-3.2-3B-Instruct
# client = InferenceClient("https://jc26mwg228mkj8dw.us-east-1.aws.endpoints.huggingface.cloud")

# Dummy function
def get_weather(location):
    return f"the weather in {location} is sunny with low temperatures. \n"

get_weather('London')

system_prompt = """
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
    Answer the following questions as best you can. You have access to the following tools:

get_weather: Get the current weather in a given location

The way you use the tools is by specifying a json blob.
Specifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).

The only values that should be in the "action" field are:
get_weather: Get the current weather in a given location, args: {"location": {"type": "string"}}
example use : 

{{
  "action": "get_weather",
  "action_input": {"location": "New York"}
}}

ALWAYS use the following format:

Question: the input question you must answer
Thought: you should always think about one action to take. Only one action at a time in this format:
Action:

$JSON_BLOB (inside markdown cell)

Observation: the result of the action. This Observation is unique, complete, and the source of truth.
... (this Thought/Action/Observation can repeat N times, you should take several steps when needed. The $JSON_BLOB must be formatted as markdown and only use a SINGLE action at a time.)

You must always end your output with the following format:

Thought: I now know the final answer
Final Answer: the final answer to the original input question

Now begin! Reminder to ALWAYS use the exact characters `Final Answer:` when you provide a definitive answer. 
<|eot_id|>
"""
user_prompt = """
<|start_header_id|>user<|end_header_id|>
What's the weather in London ?
<|eot_id|><|start_header_id|>assistant<|end_header_id|>
"""

output = client.chat.completions.create(
    messages=[
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": user_prompt},
    ],
    stream=False,
    max_tokens=200,
)

print(output.choices[0].message.content)