[.Net][Document] Add function comparison page between python AutoGen to website

[LittleLittleCloud]

Agentic pattern

feature	AutoGen	AutoGen.Net
code interpreter	run python code in local/docker/notebook executor	run csharp code in dotnet interactive executor
single agent chat pattern	✔️	✔️
two agent chat pattern	✔️	✔️
group chat (include FSM)	✔️	✔️ (using workflow for FSM groupchat)
nest chat	✔️	✔️ (using middleware pattern)
sequential chat	✔️	❌ (need to manually create task in code)
tool	✔️	✔️

LLM platform support

Note

Other than the platforms list below, AutoGen.Net also supports all the platforms that semantic kernel supports via AutoGen.SemanticKernel as a bridge

feature	AutoGen	AutoGen.Net
OpenAI (include third-party)	✔️	✔️
Mistral	✔️	✔️
Ollama	✔️	✔️
Claude	✔️	✔️
Gemini (Include Vertex)	✔️	✔️

Popular Contrib Agent support

feature	AutoGen	AutoGen.Net
Rag Agent	✔️	❌
Web surfer	✔️	❌

@sonichi @qingyun-wu please suggest any features I forget to add to this list.

Originally posted by @ChristianWeyer in #2787 (reply in thread)

[ChristianWeyer]

Should we add that the .NET version explicitly supports the graph concept (https://microsoft.github.io/autogen-for-net/articles/Use-graph-in-group-chat.html) while the Python version does not?

[ChristianWeyer]

Do we have a sample for sequential chat in .NET?

[LittleLittleCloud]

@ChristianWeyer In .NET there is no apple2apple implementation of the sequential chat in python, which takes a json object task description and run that object in one pass. So you need to manually create the tasks to agents.

Here is the sequential chat tasks in python and its equivalence in AutoGen.Net

// Creating Tasks
// In python AutoGen, you can use initiate_chats to create and run a sequential of tasks in json object
// In dotnet AutoGen, however, that feature is not available, so you need to manually create these tasks using code.

// Task 1. Onboard customer by gathering name and location
// (onboard_personal_information_agent -> user .. (repeat less than two times)) -> summarizer
var greetingMessage = new TextMessage(Role.Assistant, """
    Hello, I'm here to help you get started with our product.
    Could you tell me your name and location?
    """, from: onboardingPersonalInformationAgent.Name);

var conversation = await onboardingPersonalInformationAgent.SendAsync(
    receiver: user,
    [greetingMessage],
    maxRound: 2);

var summarizePrompt = """
    Return the customer information into as JSON object only: {'name': '', 'location': ''}
    """;

var summary = await summarizer.SendAsync(summarizePrompt, conversation);

// Task 2. Gapther customer's preferences on news topics
// (onboarding_topic_preference_agent -> user .. (repeat one time)) -> summarizer
var topicPreferenceMessage = new TextMessage(Role.Assistant, """
    Great! Could you tell me what topics you are interested in reading about?
    """, from: onboardingTopicPreferenceAgent.Name);

conversation = await onboardingTopicPreferenceAgent.SendAsync(
    receiver: user,
    [topicPreferenceMessage],
    maxRound: 1);

// Keep summarizing
summary = await summarizer.SendAsync(chatHistory: new[] { summary }.Concat(conversation));

// Task 3. Engage the customer with fun facts, jokes, or interesting stories based on the user's personal information and topic preferences
// (user(find fun thing to read) -> customerEngagementAgent .. (repeat 1 time)) -> summarizer
var funFactMessage = new TextMessage(Role.User, """
    Let's find something fun to read.
    """, from: user.Name);

conversation = await user.SendAsync(
    receiver: customerEngagementAgent,
    chatHistory: conversation.Concat([funFactMessage]), // this time, we keep the previous conversation history
    maxRound: 1);

[LittleLittleCloud]

Hey @olaoluwasalami , any updates on this issue

[olaoluwasalami]

Hey @olaoluwasalami , any updates on this issue

Working on it now. Would create a PR now

[olaoluwasalami]

@LittleLittleCloud I have created a PR. Please take a look #3367

especially the location of the article and the title