Table of Contents

👉 Try the demo:
https://github.com/LM-Kit/lm-kit-net-samples/tree/main/console_net/text-generation/conversations/multi_turn_chat_with_chat_history_guidance

Create Multi-Turn Chat with History in .NET


🎯 Purpose of the Demo

The Multi-Turn Chat with Chat History Guidance Demo showcases how to use the LM-Kit.NET SDK to create an interactive chatbot that maintains context over multiple interactions by utilizing chat history. This sample demonstrates the integration of large language models (LLMs) into a .NET application to facilitate multi-turn conversations where the chatbot is guided by the entire conversation history.


👥 Industry Target Audience

This sample is particularly beneficial for developers and organizations in the following sectors:

  • 📞 Customer Support: Enhance customer service by maintaining context across multiple interactions, improving response relevance and user experience.
  • 📚 Education: Develop interactive tutoring systems that remember previous discussions to provide personalized learning experiences.
  • 🏥 Healthcare: Create virtual assistants that can maintain patient history across conversations, ensuring continuity of care.
  • 🛍️ E-commerce: Improve customer engagement by creating chatbots that can remember past interactions and provide personalized recommendations.

🚀 Problem Solved

Maintaining context over multiple interactions is crucial for creating meaningful and coherent conversations. The Multi-Turn Chat with Chat History Guidance Demo addresses this problem by leveraging chat history to guide the chatbot's responses, ensuring that the conversation remains relevant and contextually aware.


💻 Sample Application Description

The Multi-Turn Chat with Chat History Guidance Demo is a console application that allows users to interact with a chatbot designed to provide contextually relevant responses using chat history.

✨ Key Features

  • 📈 Model Selection: Users can choose from predefined models or provide a custom model URI.
  • ⏳ Progress Tracking: The application displays download and loading progress for the selected model.
  • 🔄 Chat History Guidance: The chatbot uses the entire conversation history to provide contextually relevant responses.
  • 📝 Special Commands: Users can reset the conversation or regenerate responses using special commands.
  • 📊 Performance Metrics: Displays generated tokens, stop reasons, quality score, and speed of response for each interaction.

🧠 Supported Models

The sample supports several state-of-the-art models:

  • Alibaba Qwen 3.5 9B (~7 GB VRAM)
  • Google Gemma 4 E4B (~6 GB VRAM)
  • Microsoft Phi-4 14.7B (~11 GB VRAM)
  • OpenAI GPT OSS 20B (~16 GB VRAM)
  • Z.ai GLM 4.7 Flash 30B (~18 GB VRAM)
  • Alibaba Qwen 3.8 27B (~18 GB VRAM)
  • Alibaba Qwen 3.6 35B-A3B (~22 GB VRAM)

🛠️ Special Commands

  • /reset: Start a new session and clear the conversation history.
  • /regenerate: Get a new completion from the last input.

🛠️ Getting Started

📋 Prerequisites

  • .NET 8.0 or later

📥 Download the Project

▶️ Running the Application

  1. 📂 Clone the repository:

    git clone https://github.com/LM-Kit/lm-kit-net-samples

  2. 📁 Navigate to the project directory:

    cd lm-kit-net-samples/console_net/text-generation/conversations/multi_turn_chat_with_chat_history_guidance

  3. 🔨 Build and run the application:

    dotnet build
dotnet run

  4. 🔍 Follow the on-screen prompts to select a model and start the multi-turn chat.

💡 Example Usage

  1. Select a Model: Choose from the available models or enter a custom model URI.
  2. Initiate Conversation: Start by entering a prompt, such as "Hello, I'm the user. Please introduce yourself.".
  3. Receive Contextually Relevant Responses: The chatbot will generate responses based on the entire conversation history.
  4. Continue Interaction: Enter another prompt or use the special commands to reset the conversation or regenerate responses.
  5. End the Chat: Submit an empty input to end the program.

By following these steps, developers can explore the functionalities of LM-Kit.NET and integrate advanced conversation history management into their chatbot applications, enhancing the relevance and coherence of automated responses through a multi-turn conversational AI.

📚 Related Content

Share