Cerebras

!pip install autogen-agentchat["cerebras"]~=0.2

[
    {
        "model": "llama3.1-8b",
        "api_key": "your Cerebras API Key goes here",
        "api_type": "cerebras"
    },
    {
        "model": "llama3.1-70b",
        "api_key": "your Cerebras API Key goes here",
        "api_type": "cerebras"
    }
]

[
    {
        "model": "llama3.1-70b",
        "api_key": "your Cerebras API Key goes here",
        "api_type": "cerebras"
        "max_tokens": 10000,
        "seed": 1234,
        "stream" True,
        "temperature": 0.5,
        "top_p": 0.2, # Note: It is recommended to set temperature or top_p but not both.
    }
]

import os

from autogen.oai.cerebras import CerebrasClient, calculate_cerebras_cost

config_list = [{"model": "llama3.1-70b", "api_key": os.environ.get("CEREBRAS_API_KEY"), "api_type": "cerebras"}]

from pathlib import Path

from autogen import AssistantAgent, UserProxyAgent
from autogen.coding import LocalCommandLineCodeExecutor

# Setting up the code executor
workdir = Path("coding")
workdir.mkdir(exist_ok=True)
code_executor = LocalCommandLineCodeExecutor(work_dir=workdir)

# Setting up the agents

# The UserProxyAgent will execute the code that the AssistantAgent provides
user_proxy_agent = UserProxyAgent(
    name="User",
    code_execution_config={"executor": code_executor},
    is_termination_msg=lambda msg: "FINISH" in msg.get("content"),
)

system_message = """You are a helpful AI assistant who writes code and the user executes it.
Solve tasks using your coding and language skills.
In the following cases, suggest python code (in a python coding block) for the user to execute.
Solve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.
When using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can't modify your code. So do not suggest incomplete code which requires users to modify. Don't use a code block if it's not intended to be executed by the user.
Don't include multiple code blocks in one response. Do not ask users to copy and paste the result. Instead, use 'print' function for the output when relevant. Check the execution result returned by the user.
If the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can't be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.
When you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible.
IMPORTANT: Wait for the user to execute your code and then you can reply with the word "FINISH". DO NOT OUTPUT "FINISH" after your code block."""

# The AssistantAgent, using Llama-3.1-70B on Cerebras Inference, will take the coding request and return code
assistant_agent = AssistantAgent(
    name="Cerebras Assistant",
    system_message=system_message,
    llm_config={"config_list": config_list},
)

# Start the chat, with the UserProxyAgent asking the AssistantAgent the message
chat_result = user_proxy_agent.initiate_chat(
    assistant_agent,
    message="Provide code to count the number of prime numbers from 1 to 10000.",
)

import json
import os
from typing import Literal

from typing_extensions import Annotated

import autogen

config_list = [
    {
        "model": "llama3.1-70b",
        "api_key": os.environ.get("CEREBRAS_API_KEY"),
        "api_type": "cerebras",
    }
]

# Create the agent for tool calling
chatbot = autogen.AssistantAgent(
    name="chatbot",
    system_message="""
        For currency exchange and weather forecasting tasks,
        only use the functions you have been provided with.
        When you summarize, make sure you've considered ALL previous instructions.
        Output 'HAVE FUN!' when an answer has been provided.
    """,
    llm_config={"config_list": config_list},
)

# Note that we have changed the termination string to be "HAVE FUN!"
user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    is_termination_msg=lambda x: x.get("content", "") and "HAVE FUN!" in x.get("content", ""),
    human_input_mode="NEVER",
    max_consecutive_auto_reply=1,
)

# Currency Exchange function

CurrencySymbol = Literal["USD", "EUR"]

# Define our function that we expect to call


def exchange_rate(base_currency: CurrencySymbol, quote_currency: CurrencySymbol) -> float:
    if base_currency == quote_currency:
        return 1.0
    elif base_currency == "USD" and quote_currency == "EUR":
        return 1 / 1.1
    elif base_currency == "EUR" and quote_currency == "USD":
        return 1.1
    else:
        raise ValueError(f"Unknown currencies {base_currency}, {quote_currency}")


# Register the function with the agent


@user_proxy.register_for_execution()
@chatbot.register_for_llm(description="Currency exchange calculator.")
def currency_calculator(
    base_amount: Annotated[float, "Amount of currency in base_currency"],
    base_currency: Annotated[CurrencySymbol, "Base currency"] = "USD",
    quote_currency: Annotated[CurrencySymbol, "Quote currency"] = "EUR",
) -> str:
    quote_amount = exchange_rate(base_currency, quote_currency) * base_amount
    return f"{format(quote_amount, '.2f')} {quote_currency}"


# Weather function


# Example function to make available to model
def get_current_weather(location, unit="fahrenheit"):
    """Get the weather for some location"""
    if "chicago" in location.lower():
        return json.dumps({"location": "Chicago", "temperature": "13", "unit": unit})
    elif "san francisco" in location.lower():
        return json.dumps({"location": "San Francisco", "temperature": "55", "unit": unit})
    elif "new york" in location.lower():
        return json.dumps({"location": "New York", "temperature": "11", "unit": unit})
    else:
        return json.dumps({"location": location, "temperature": "unknown"})


# Register the function with the agent


@user_proxy.register_for_execution()
@chatbot.register_for_llm(description="Weather forecast for US cities.")
def weather_forecast(
    location: Annotated[str, "City name"],
) -> str:
    weather_details = get_current_weather(location=location)
    weather = json.loads(weather_details)
    return f"{weather['location']} will be {weather['temperature']} degrees {weather['unit']}"

import time

start_time = time.time()

# start the conversation
res = user_proxy.initiate_chat(
    chatbot,
    message="What's the weather in New York and can you tell me how much is 123.45 EUR in USD so I can spend it on my holiday? Throw a few holiday tips in as well.",
    summary_method="reflection_with_llm",
)

end_time = time.time()

print(f"LLM SUMMARY: {res.summary['content']}\n\nDuration: {(end_time - start_time) * 1000}ms")