Use AG2 in Microsoft Fabric#

# pyautogen<=0.1.14 supports openai<1
%pip install "pyautogen==0.1.14" "openai==0.28.1" -q

import autogen

# Set temperature, timeout and other LLM configurations
llm_config = autogen.LLMConfig(
    config_list=[
        {
            "model": "gpt-4o",
        },
    ],
    temperature=0,
    timeout=600,
)

agent = autogen.agentchat.ConversableAgent(
    name=llm_config.config_list[0].model, llm_config=llm_config, max_consecutive_auto_reply=1, human_input_mode="NEVER"
)
userproxy = autogen.agentchat.ConversableAgent(
    name="user",
    max_consecutive_auto_reply=0,
    llm_config=False,
    default_auto_reply="TERMINATE",
    human_input_mode="NEVER",
)
userproxy.initiate_chat(recipient=agent, message="Tell me a quick joke.")

# autogen>0.1.14 supports openai>=1
%pip install "autogen>0.2" "openai>1" -q

import types

from synapse.ml.fabric.credentials import get_openai_httpx_sync_client

import autogen

http_client = get_openai_httpx_sync_client()  # http_client is needed for openai>1
http_client.__deepcopy__ = types.MethodType(
    lambda self, memo: self, http_client
)  # https://docs.ag2.ai/docs/user-guide/advanced-concepts/llm-configuration-deep-dive/#adding-http-client-in-llm_config-for-proxy\n",

# Set temperature, timeout and other LLM configurations
llm_config = autogen.LLMConfig(
    config_list=[
        {
            "model": "gpt-4o",
            "http_client": http_client,
            "api_version": "2024-02-01",
            "api_type": "azure",
        },
    ],
    temperature=0,
)

import autogen

agent = autogen.agentchat.ConversableAgent(
    name=llm_config.config_list[0].model, llm_config=llm_config, max_consecutive_auto_reply=1, human_input_mode="NEVER"
)
userproxy = autogen.agentchat.ConversableAgent(
    name="user",
    max_consecutive_auto_reply=0,
    llm_config=False,
    default_auto_reply="TERMINATE",
    human_input_mode="NEVER",
)
userproxy.initiate_chat(recipient=agent, message="Tell me a joke about openai.")

%pip install "autogen[retrievechat,lmm]>=0.2.28" -q

import types

from synapse.ml.fabric.credentials import get_openai_httpx_sync_client

import autogen

http_client = get_openai_httpx_sync_client()  # http_client is needed for openai>1
http_client.__deepcopy__ = types.MethodType(
    lambda self, memo: self, http_client
)  # https://docs.ag2.ai/docs/user-guide/advanced-concepts/llm-configuration-deep-dive/#adding-http-client-in-llm_config-for-proxy

# Set temperature, timeout and other LLM configurations
llm_config = autogen.LLMConfig(
    config_list=[
        {
            "model": "gpt-4o",
            "http_client": http_client,
            "api_version": "2024-02-01",
            "api_type": "azure",
        },
    ],
    temperature=0,
)

import autogen

# create an AssistantAgent instance named "assistant"
assistant = autogen.AssistantAgent(
    name="assistant",
    llm_config=llm_config,
)

# create a UserProxyAgent instance named "user_proxy"
user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    human_input_mode="NEVER",  # input() doesn't work, so needs to be "NEVER" here
    max_consecutive_auto_reply=10,
    is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
    code_execution_config={
        "work_dir": "coding",
        "use_docker": False,  # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.
    },
    llm_config=llm_config,
    system_message="""Reply TERMINATE if the task has been solved at full satisfaction.
Otherwise, reply CONTINUE, or the reason why the task is not solved yet.""",
)

# the assistant receives a message from the user, which contains the task description
chat_result = user_proxy.initiate_chat(
    assistant,
    message="""
Who should read this paper: https://arxiv.org/abs/2308.08155
""",
)

print(f"Cost for the chat:\n{chat_result.cost}")

import tempfile

from autogen.coding import LocalCommandLineCodeExecutor

# Create a temporary directory to store the code files.
temp_dir = tempfile.TemporaryDirectory()

# Create a local command line code executor.
code_executor = LocalCommandLineCodeExecutor(
    timeout=40,  # Timeout for each code execution in seconds.
    work_dir=temp_dir.name,  # Use the temporary directory to store the code files.
)

from autogen import AssistantAgent
from autogen.agentchat.contrib.retrieve_user_proxy_agent import RetrieveUserProxyAgent

# 1. create an AssistantAgent instance named "assistant"
assistant = AssistantAgent(
    name="assistant",
    system_message="You are a helpful assistant.",
    llm_config=llm_config,
)

# 2. create the RetrieveUserProxyAgent instance named "ragproxyagent"
ragproxyagent = RetrieveUserProxyAgent(
    name="ragproxyagent",
    human_input_mode="NEVER",
    max_consecutive_auto_reply=5,
    retrieve_config={
        "docs_path": [
            "https://learn.microsoft.com/en-us/fabric/get-started/microsoft-fabric-overview",
            "https://learn.microsoft.com/en-us/fabric/data-science/tuning-automated-machine-learning-visualizations",
        ],
        "chunk_token_size": 2000,
        "model": llm_config.config_list[0].model,
        "vector_db": "chroma",  # to use the deprecated `client` parameter, set to None and uncomment the line above
        "overwrite": True,  # set to True if you want to overwrite an existing collection
    },
    code_execution_config={"executor": code_executor},  # Use the local command line code executor.
)

Microsoft Fabric is a comprehensive data platform that integrates various services and tools for data management, analytics, and collaboration. As of the latest information available, Microsoft Fabric includes the following components:

Data Integration:

Azure Data Factory: For creating, scheduling, and orchestrating data workflows.
Power Query: A data transformation and data preparation tool.
Data Engineering:

Azure Synapse Analytics: For big data and data warehousing solutions, including Synapse SQL, Spark, and Data Explorer.
Data Science:

Azure Machine Learning: For building, training, and deploying machine learning models.
Azure Databricks: For collaborative big data and AI solutions.
Data Warehousing:

...

The components of Microsoft Fabric are:

1. Power BI
2. Data Factory
3. Data Activator
4. Industry Solutions
5. Real-Time Intelligence
6. Synapse Data Engineering
7. Synapse Data Science
8. Synapse Data Warehouse

Sources: [Microsoft Fabric Overview](https://learn.microsoft.com/en-us/fabric/get-started/microsoft-fabric-overview)

assistant.reset()
problem = "List all the Components of Microsoft Fabric"
chat_result = ragproxyagent.initiate_chat(assistant, message=ragproxyagent.message_generator, problem=problem)

print(f"Cost for the chat:\n{chat_result.cost}")

import time
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

# Create a synthetic regression dataset
X, y = make_regression(n_samples=1000, n_features=20, noise=0.1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Initialize the model
model = LinearRegression()

# Record the start time
start_time = time.time()

# Train the model and record intermediate times
times = []
time_budget = 12  # in seconds

for _ in range(100):
    model.fit(X_train, y_train)
    current_time = time.time()
    elapsed_time = current_time - start_time
    times.append(elapsed_time)
    if elapsed_time > time_budget:
        break

# Plot the timeline
plt.figure(figsize=(10, 5))
plt.plot(times, label='Training time')
plt.axhline(y=time_budget, color='r', linestyle='--', label='Time Budget (12s)')
plt.xlabel('Iteration')
plt.ylabel('Elapsed Time (s)')
plt.title('Training Time Line Plot')
plt.legend()
plt.grid(True)
plt.show()

assistant.reset()
problem = "Train a regression model, set time budget to 12s, plot the time line plot after training."

chat_result = ragproxyagent.initiate_chat(assistant, message=ragproxyagent.message_generator, problem=problem)

print(f"Cost for the chat:\n{chat_result.cost}")

import flaml.visualization as fviz
from flaml import AutoML
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split

# Load the California housing data and split it into train and test sets
housing = fetch_california_housing()
x, y = housing.data, housing.target
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=7654321)

# Create an AutoML instance and set the parameters
automl = AutoML()
automl_settings = {
    "time_budget": 12,  # Time limit in seconds
    "task": "regression",  # Type of machine learning task
    "log_file_name": "aml_california.log",  # Name of the log file
    "metric": "rmse",  # Evaluation metric
    "log_type": "all",  # Level of logging
}

# Fit the AutoML instance on the training data
automl.fit(X_train=x_train, y_train=y_train, **automl_settings)

# Plot the timeline plot
fig = fviz.plot_timeline(automl)
fig.show()

from autogen.agentchat.contrib.multimodal_conversable_agent import MultimodalConversableAgent

llm_config = autogen.LLMConfig(
    config_list=[
        {
            "model": "gpt-4o",
            "http_client": http_client,
            "api_version": "2024-02-01",
            "api_type": "azure",
        },
    ],
    temperature=0.5,
    max_tokens=300,
)

image_agent = MultimodalConversableAgent(
    name="image-explainer",
    max_consecutive_auto_reply=10,
    llm_config=llm_config,
)

user_proxy = autogen.UserProxyAgent(
    name="User_proxy",
    system_message="A human admin.",
    human_input_mode="NEVER",  # Try between ALWAYS or NEVER
    max_consecutive_auto_reply=0,
    code_execution_config={
        "use_docker": False
    },  # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.
)

# Ask the question with an image
chat_result = user_proxy.initiate_chat(
    image_agent,
    message="""What's the breed of this dog?
<img https://th.bing.com/th/id/R.422068ce8af4e15b0634fe2540adea7a?rik=y4OcXBE%2fqutDOw&pid=ImgRaw&r=0>.""",
)

print(f"Cost for the chat:\n{chat_result.cost}")