base on A reference .NET application using AI for a customer support ticketing system # eShopSupport A sample .NET application showcasing common use cases and development practices for build AI solutions in .NET (Generative AI, specifically). This sample demonstrates a customer support application for an e-commerce website using a services-based architecture with .NET Aspire. It includes support for the following AI use cases: * Text classification, applying labels based on content * Sentiment analysis based on message content * Summarization of large sets of text * Synthetic data generation, creating test content for the sample * Chat bot interactions with chat history and suggested responses <img width=400 align=top src=https://github.com/user-attachments/assets/5a41493f-565b-4dd0-ae31-1b5c3c2f6d22> <img width=400 align=top src=https://github.com/user-attachments/assets/7930a940-bb31-4dc0-b5f6-738d43dfcfe5> This sample also demonstrates the following development practices: * Developing a solution locally, using small local models * Evaluating the quality of AI responses using grounded Q&A data * Leveraging Python projects as part of a .NET Aspire solution * Deploying the application, including small local models, to the Cloud (coming soon) ## Architecture  ## Getting Started ### Prerequisites - A device with an Nvidia GPU (see [workaround for running on the CPU](https://github.com/dotnet/eShopSupport/issues/19)) - Clone the eShopSupport repository: https://github.com/dotnet/eshopsupport - [Install & start Docker Desktop](https://docs.docker.com/engine/install/) - [Install Python 3.12.5](https://www.python.org/downloads/release/python-3125/) #### Windows with Visual Studio - Install [Visual Studio 2022 version 17.10 or newer](https://visualstudio.microsoft.com/vs/) - Select the following workloads: - `ASP.NET and web development` workload. - `Python Development` workload. - `.NET Aspire SDK` component in `Individual components`. #### Mac, Linux, & Windows without Visual Studio - Install the latest [.NET 8 SDK](https://dot.net/download?cid=eshop) - Install the [.NET Aspire workload](https://learn.microsoft.com/dotnet/aspire/fundamentals/setup-tooling?tabs=dotnet-cli%2Cunix#install-net-aspire) with the following commands: ```powershell dotnet workload update dotnet workload install aspire dotnet restore eShopSupport.sln ``` - (Optionally) Install [Visual Studio Code](https://code.visualstudio.com) with the [C# Dev Kit extension](https://marketplace.visualstudio.com/items?itemName=ms-dotnettools.csdevkit) #### Install Python requirements From the Terminal, at the root of the cloned repo, run: ```powershell pip install -r src/PythonInference/requirements.txt ``` **Note:** If the above command doesn't work on Windows, use the following command: ```powershell py -m pip install -r src/PythonInference/requirements.txt ``` ### Running the solution > [!WARNING] > Remember to ensure that Docker is started. * (Windows only) Run the application from Visual Studio: - Open the `eShopSupport.sln` file in Visual Studio - Ensure that `AppHost` is your startup project - Hit Ctrl-F5 to launch .NET Aspire * Or run the application from your terminal: ```powershell dotnet run --project src/AppHost ``` then look for lines like this in the console output in order to find the URL to open the Aspire dashboard: ```sh Login to the dashboard at: http://localhost:17191/login?t=uniquelogincodeforyou ``` > You may need to install ASP.NET Core HTTPS development certificates first, and then close all browser tabs. Learn more at https://aka.ms/aspnet/https-trust-dev-cert # Contributing This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/). For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or contact [[email protected]](mailto:[email protected]) with any additional questions or comments. # Sample data The sample data is defined in [seeddata](https://github.com/dotnet/eShopSupport/tree/main/seeddata). All products/descriptions/brands, manuals, customers, and support tickets names are fictional and were generated using [GPT-35-Turbo](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/chatgpt) using the included [DataGenerator](https://github.com/dotnet/eShopSupport/tree/main/seeddata/DataGenerator) project. ", Assign "at most 3 tags" to the expected json: {"id":"12078","tags":[]} "only from the tags list I provide: [{"id":39,"name":"3d-generation","display_name":"3D generation","slug":"3d-generation"},{"id":3,"name":"ai-agent","display_name":"AI agent","slug":"ai-agent"},{"id":8,"name":"ai-coding","display_name":"AI coding assistant","slug":"ai-coding"},{"id":5,"name":"ai-image","display_name":"AI image generation","slug":"ai-image"},{"id":9,"name":"ai-infrastructure","display_name":"AI infrastructure","slug":"ai-infrastructure"},{"id":10,"name":"ai-memory","display_name":"AI memory","slug":"ai-memory"},{"id":11,"name":"ai-skills","display_name":"AI skills","slug":"ai-skills"},{"id":12,"name":"ai-translation","display_name":"AI translation","slug":"ai-translation"},{"id":6,"name":"ai-video","display_name":"AI video generation","slug":"ai-video"},{"id":4,"name":"ai-voice","display_name":"AI voice","slug":"ai-voice"},{"id":7,"name":"ai-workflow","display_name":"AI workflow","slug":"ai-workflow"},{"id":22,"name":"audio-processing","display_name":"Audio processing","slug":"audio-processing"},{"id":29,"name":"authentication","display_name":"Authentication","slug":"authentication"},{"id":51,"name":"bundler","display_name":"Bundler","slug":"bundler"},{"id":41,"name":"chatbot","display_name":"Chatbot","slug":"chatbot"},{"id":27,"name":"cloud-native","display_name":"Cloud native","slug":"cloud-native"},{"id":1,"name":"computer-vision","display_name":"Computer vision","slug":"computer-vision"},{"id":37,"name":"crypto-trading","display_name":"Crypto trading","slug":"crypto-trading"},{"id":57,"name":"curated-list","display_name":"Curated list","slug":"curated-list"},{"id":54,"name":"data-streaming","display_name":"Data streaming","slug":"data-streaming"},{"id":35,"name":"data-visualization","display_name":"Data visualization","slug":"data-visualization"},{"id":16,"name":"database-backup","display_name":"Database backup","slug":"database-backup"},{"id":49,"name":"design-system","display_name":"Design system","slug":"design-system"},{"id":38,"name":"digital-human","display_name":"Digital human","slug":"digital-human"},{"id":34,"name":"document-processing","display_name":"Document processing","slug":"document-processing"},{"id":44,"name":"ecommerce","display_name":"E-commerce","slug":"ecommerce"},{"id":45,"name":"emulator","display_name":"Emulator","slug":"emulator"},{"id":46,"name":"file-management","display_name":"File management","slug":"file-management"},{"id":32,"name":"fintech","display_name":"Fintech","slug":"fintech"},{"id":31,"name":"game-development","display_name":"Game development","slug":"game-development"},{"id":24,"name":"headless-browser","display_name":"Headless browser","slug":"headless-browser"},{"id":52,"name":"headless-cms","display_name":"Headless CMS","slug":"headless-cms"},{"id":36,"name":"home-automation","display_name":"Home automation","slug":"home-automation"},{"id":20,"name":"image-editing","display_name":"Image editing","slug":"image-editing"},{"id":28,"name":"iot","display_name":"IoT","slug":"iot"},{"id":13,"name":"local-llm","display_name":"Local LLM","slug":"local-llm"},{"id":17,"name":"mcp","display_name":"MCP","slug":"mcp"},{"id":47,"name":"monitoring","display_name":"Monitoring","slug":"monitoring"},{"id":2,"name":"nlp","display_name":"NLP","slug":"nlp"},{"id":26,"name":"observability","display_name":"Observability","slug":"observability"},{"id":40,"name":"pentesting","display_name":"Pentesting","slug":"pentesting"},{"id":48,"name":"programming-examples","display_name":"Programming examples","slug":"programming-examples"},{"id":42,"name":"proxy","display_name":"Proxy","slug":"proxy"},{"id":14,"name":"rag","display_name":"RAG","slug":"rag"},{"id":56,"name":"resume-building","display_name":"Resume building","slug":"resume-building"},{"id":33,"name":"robotics","display_name":"Robotics","slug":"robotics"},{"id":30,"name":"search","display_name":"Search","slug":"search"},{"id":43,"name":"self-hosted","display_name":"Self-hosted","slug":"self-hosted"},{"id":50,"name":"static-analysis","display_name":"Static analysis","slug":"static-analysis"},{"id":18,"name":"synthetic-data","display_name":"Synthetic data","slug":"synthetic-data"},{"id":19,"name":"text-to-speech","display_name":"Text to speech","slug":"text-to-speech"},{"id":53,"name":"ui-components","display_name":"UI components","slug":"ui-components"},{"id":15,"name":"vector-database","display_name":"Vector database","slug":"vector-database"},{"id":21,"name":"video-editing","display_name":"Video editing","slug":"video-editing"},{"id":25,"name":"web-scraping","display_name":"Web scraping","slug":"web-scraping"},{"id":55,"name":"webassembly","display_name":"WebAssembly","slug":"webassembly"},{"id":23,"name":"workflow-automation","display_name":"Workflow automation","slug":"workflow-automation"}]" returns me the "expected json"