{"id":31057351,"url":"https://github.com/devkimchi/meai-for-local-llms","last_synced_at":"2025-09-15T06:59:06.525Z","repository":{"id":311265094,"uuid":"1042579600","full_name":"devkimchi/meai-for-local-llms","owner":"devkimchi","description":"This provides sample codes that uses Microsoft.Extensions.AI for locally running LLMs through Ollama, Hugging Face, Docker Model Runner and Foundry Local","archived":false,"fork":false,"pushed_at":"2025-09-09T09:02:16.000Z","size":129,"stargazers_count":4,"open_issues_count":0,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-09T09:02:40.803Z","etag":null,"topics":["ai-template","blazor","docker-model-runner","dotnet","foundry-local","hugging-face","meai","microsoft-extensions-ai","ollama"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/devkimchi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-08-22T08:36:45.000Z","updated_at":"2025-08-29T14:29:27.000Z","dependencies_parsed_at":"2025-08-23T17:20:34.514Z","dependency_job_id":"4a66ec1e-17de-4e5f-91b6-6fdc395d93c7","html_url":"https://github.com/devkimchi/meai-for-local-llms","commit_stats":null,"previous_names":["devkimchi/meai-for-local-llms"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/devkimchi/meai-for-local-llms","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devkimchi%2Fmeai-for-local-llms","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devkimchi%2Fmeai-for-local-llms/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devkimchi%2Fmeai-for-local-llms/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devkimchi%2Fmeai-for-local-llms/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/devkimchi","download_url":"https://codeload.github.com/devkimchi/meai-for-local-llms/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devkimchi%2Fmeai-for-local-llms/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":275219533,"owners_count":25425889,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-15T02:00:09.272Z","response_time":75,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-template","blazor","docker-model-runner","dotnet","foundry-local","hugging-face","meai","microsoft-extensions-ai","ollama"],"created_at":"2025-09-15T06:59:02.652Z","updated_at":"2025-09-15T06:59:06.515Z","avatar_url":"https://github.com/devkimchi.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [Microsoft.Extensions.AI](https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai) for Local LLMs\n\nThis provides sample codes that uses Microsoft.Extensions.AI for locally running LLMs through [Docker Model Runner](https://docs.docker.com/ai/model-runner/), [Foundry Local](https://learn.microsoft.com/azure/ai-foundry/foundry-local/what-is-foundry-local), [Hugging Face](https://huggingface.co/) and [Ollama](https://ollama.com/).\n\n\u003e This is a trim-down version of [\u003cimg src=\"https://github.com/aliencube/open-chat-playground/raw/main/assets/icon-transparent.svg\" alt=\"OpenChat Playground\" width=\"16\" /\u003e OpenChat Playground](https://github.com/aliencube/open-chat-playground), specific to dealing with locally running LLMs. If you want to see more language models supported including MaaS and other vendors, try out [\u003cimg src=\"https://github.com/aliencube/open-chat-playground/raw/main/assets/icon-transparent.svg\" alt=\"OpenChat Playground\" width=\"16\" /\u003e OpenChat Playground](https://github.com/aliencube/open-chat-playground) instead.\n\n## Prerequisites\n\n- [.NET SDK 9](https://dotnet.microsoft.com/download/dotnet/9.0)\n- [Visual Studio Code](https://code.visualstudio.com/) + [C# DevKit](https://marketplace.visualstudio.com/items?itemName=ms-dotnettools.csdevkit) or [Visual Studio 2022 v17.14+](https://visualstudio.com/vs)\n- [GitHub CLI](https://cli.github.com/)\n- [PowerShell 7.5+](https://learn.microsoft.com/powershell/scripting/install/installing-powershell) 👉 Windows only\n- [Docker Desktop](https://docs.docker.com/desktop/)\n- [Foundry Local](https://learn.microsoft.com/azure/ai-foundry/foundry-local/get-started)\n- [Ollama](https://ollama.com/download)\n\n## Getting Started\n\n### Get the repository ready\n\n1. Login to GitHub.\n\n    ```bash\n    gh auth login\n    ```\n\n1. Check login status.\n\n    ```bash\n    gh auth status\n    ```\n\n1. Fork this repository to your account and clone the forked repository to your local machine.\n\n    ```bash\n    gh repo fork devkimchi/meai-for-local-llms --clone --default-branch-only\n    ```\n\n1. Navigate to the cloned repository.\n\n    ```bash\n    cd meai-for-local-llms\n    ```\n\n1. Get the repository root.\n\n    ```bash\n    # bash/zsh\n    REPOSITORY_ROOT=$(git rev-parse --show-toplevel)\n    ```\n\n    ```powershell\n    # PowerShell\n    $REPOSITORY_ROOT = git rev-parse --show-toplevel\n    ```\n\n### Use GitHub Models\n\nAs a default, this app uses [GitHub Models](https://github.com/marketplace?type=models).\n\n\u003cdetails open\u003e\n  \u003csummary\u003e\u003cstrong\u003eWith .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Add GitHub Personal Access Token (PAT) for GitHub Models connection. Make sure you should replace `{{YOUR_TOKEN}}` with your GitHub PAT.\n\n    ```bash\n    # bash/zsh\n    dotnet user-secrets --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        set \"Parameters:github-models-gh-apikey\" \"{{YOUR_TOKEN}}\"\n    ```\n\n    ```bash\n    # PowerShell\n    dotnet user-secrets --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        set \"Parameters:github-models-gh-apikey\" \"{{YOUR_TOKEN}}\"\n    ```\n\n    \u003e For more details about GitHub PAT, refer to the doc, [Managing your personal access tokens](https://docs.github.com/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens).\n\n1. Run the app. The default language model is `openai/gpt-4o-mini`.\n\n    ```bash\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost\n    ```\n\n   If you want to change the language model, add the `--model` option with a preferred model name. You can find the language model from the [GitHub Models catalog page](https://github.com/marketplace?type=models).\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type GitHubModels --model \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type GitHubModels --model \u003cmodel-name\u003e\n    ```\n\n1. Once the .NET Aspire dashboard opens, click navigate to `https://localhost:45160`, and enter prompts.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n  \u003csummary\u003e\u003cstrong\u003eWithout .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Add GitHub Personal Access Token (PAT) for GitHub Models connection. Make sure you should replace `{{YOUR_TOKEN}}` with your GitHub PAT.\n\n    ```bash\n    # bash/zsh\n    dotnet user-secrets --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        set GitHubModels:Token \"{{YOUR_TOKEN}}\"\n    ```\n\n    ```bash\n    # PowerShell\n    dotnet user-secrets --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        set GitHubModels:Token \"{{YOUR_TOKEN}}\"\n    ```\n\n    \u003e For more details about GitHub PAT, refer to the doc, [Managing your personal access tokens](https://docs.github.com/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens).\n\n1. Run the app. The default language model is `openai/gpt-4o-mini`.\n\n    ```bash\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp\n    ```\n\n   If you want to change the language model, add the `--model` option with a preferred model name. You can find the language model from the [GitHub Models catalog page](https://github.com/marketplace?type=models).\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type GitHubModels --model \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type GitHubModels --model \u003cmodel-name\u003e\n    ```\n\n1. Open your web browser, navigate to `http://localhost:5160`, and enter prompts.\n\n\u003c/details\u003e\n\n### Use Docker Model Runner\n\n\u003cdetails open\u003e\n  \u003csummary\u003e\u003cstrong\u003eWith .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\n1. Make sure Docker Desktop is up and running.\n\n    ```bash\n    docker info\n    ```\n\n1. Download language model, `ai/gpt-oss`, to your local machine.\n\n    ```bash\n    docker model pull ai/gpt-oss\n    ```\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Run the app using the `--connector-type` option with the `DockerModelRunner` value. The default language model is `ai/gpt-oss`.\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type DockerModelRunner\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type DockerModelRunner\n    ```\n\n   If you want to change the language model, add the `--model` option with a preferred model name.\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type DockerModelRunner --model \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type DockerModelRunner --model \u003cmodel-name\u003e\n    ```\n\n1. Once the .NET Aspire dashboard opens, click navigate to `https://localhost:45160`, and enter prompts.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n  \u003csummary\u003e\u003cstrong\u003eWithout .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\n1. Make sure Docker Desktop is up and running.\n\n    ```bash\n    docker info\n    ```\n\n1. Download language model, `ai/gpt-oss`, to your local machine.\n\n    ```bash\n    docker model pull ai/gpt-oss\n    ```\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Run the app using the `--connector-type` option with the `DockerModelRunner` value. The default language model is `ai/gpt-oss`.\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type DockerModelRunner\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type DockerModelRunner\n    ```\n\n   If you want to change the language model, add the `--model` option with a preferred model name.\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type DockerModelRunner --model \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type DockerModelRunner --model \u003cmodel-name\u003e\n    ```\n\n1. Open your web browser, navigate to `http://localhost:5160`, and enter prompts.\n\n\u003c/details\u003e\n\n### Use Foundry Local\n\n\u003cdetails open\u003e\n  \u003csummary\u003e\u003cstrong\u003eWith .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\n1. Make sure Foundry Local is NOT running.\n\n    ```bash\n    foundry service status\n    ```\n\n   If Foundry Local service is up and running, run the following command:\n\n    ```bash\n    foundry service stop\n    ```\n\n1. Download language model, `gpt-oss-20b`, to your local machine.\n\n    ```bash\n    foundry model download gpt-oss-20b\n    ```\n\n   Once you download a language model, the foundry service is automatically up and running. If the service is up and running, stop it first.\n\n    ```bash\n    foundry service stop\n    ```\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Run the app using the `--connector-type` option with the `FoundryLocal` value. The default language model is `gpt-oss-20b`.\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type FoundryLocal\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type FoundryLocal\n    ```\n\n   If you want to change the language model, add the `--alias` option with a preferred model name.\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type FoundryLocal --alias \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type FoundryLocal --model \u003cmodel-name\u003e\n    ```\n\n1. Once the .NET Aspire dashboard opens, click navigate to `https://localhost:45160`, and enter prompts.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n  \u003csummary\u003e\u003cstrong\u003eWithout .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\n1. Download language model, `gpt-oss-20b`, to your local machine.\n\n    ```bash\n    foundry model download gpt-oss-20b\n    ```\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Run the app using the `--connector-type` option with the `FoundryLocal` value. The default language model is `gpt-oss-20b`.\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type FoundryLocal\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type FoundryLocal\n    ```\n\n   If you want to change the language model, add the `--alias` option with a preferred model name.\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type FoundryLocal --alias \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type FoundryLocal --alias \u003cmodel-name\u003e\n    ```\n\n1. Open your web browser, navigate to `http://localhost:5160`, and enter prompts.\n\n\u003c/details\u003e\n\n### Use Hugging Face\n\nModels from Hugging Face are running through Ollama server.\n\n\u003cdetails open\u003e\n  \u003csummary\u003e\u003cstrong\u003eWith .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\nWith .NET Aspire, it uses the [ollama container image](https://hub.docker.com/r/ollama/ollama). Therefore, there's no need to run the Ollama server on your local machine.\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Run the app using the `--connector-type` option with the `HuggingFace` value. The default language model is `hf.co/LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF`.\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type HuggingFace\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type HuggingFace\n    ```\n\n   If you want to change the language model, add the `--model` option with a preferred model name. Make sure that the model name format MUST follow `hf.co/{ORG_NAME}/{MODEL_NAME}`, and the model name MUST be formatted in **GGUF**.\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type HuggingFace --model \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type HuggingFace --model \u003cmodel-name\u003e\n    ```\n\n1. Once the .NET Aspire dashboard opens, click navigate to `https://localhost:45160`, and enter prompts.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n  \u003csummary\u003e\u003cstrong\u003eWithout .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\n1. Make sure Ollama is up and running.\n\n    ```bash\n    ollama start\n    ```\n\n1. In a separate terminal, download language model, `LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF`, to your local machine.\n\n    ```bash\n    ollama pull hf.co/LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF\n    ```\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Run the app using the `--connector-type` option with the `HuggingFace` value. The default language model is `hf.co/LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF`.\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type HuggingFace\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type HuggingFace\n    ```\n\n   If you want to change the language model, add the `--model` option with a preferred model name.\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type HuggingFace --model \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type HuggingFace --model \u003cmodel-name\u003e\n    ```\n\n1. Open your web browser, navigate to `http://localhost:5160`, and enter prompts.\n\n\u003c/details\u003e\n\n### Use Ollama\n\n\u003cdetails open\u003e\n  \u003csummary\u003e\u003cstrong\u003eWith .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\nWith .NET Aspire, it uses the [ollama container image](https://hub.docker.com/r/ollama/ollama). Therefore, there's no need to run the Ollama server on your local machine.\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Run the app using the `--connector-type` option with the `Ollama` value. The default language model is `gpt-oss`.\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type Ollama\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type Ollama\n    ```\n\n   If you want to change the language model, add the `--model` option with a preferred model name.\n\n    ```bash\n    # bash/zsh\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost \\\n        -- --connector-type Ollama --model \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet watch run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.AppHost `\n        -- --connector-type Ollama --model \u003cmodel-name\u003e\n    ```\n\n1. Once the .NET Aspire dashboard opens, click navigate to `https://localhost:45160`, and enter prompts.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n  \u003csummary\u003e\u003cstrong\u003eWithout .NET Aspire\u003c/strong\u003e\u003c/summary\u003e\n\n1. Make sure Ollama is up and running.\n\n    ```bash\n    ollama start\n    ```\n\n1. In a separate terminal, download language model, `gpt-oss`, to your local machine.\n\n    ```bash\n    ollama pull gpt-oss\n    ```\n\n1. Make sure you are at the repository root.\n\n    ```bash\n    cd $REPOSITORY_ROOT\n    ```\n\n1. Run the app using the `--connector-type` option with the `Ollama` value. The default language model is `gpt-oss`.\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type Ollama\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type Ollama\n    ```\n\n   If you want to change the language model, add the `--model` option with a preferred model name.\n\n    ```bash\n    # bash/zsh\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp \\\n        -- --connector-type Ollama --model \u003cmodel-name\u003e\n    ```\n\n    ```powershell\n    # PowerShell\n    dotnet run --project $REPOSITORY_ROOT/src/MEAIForLocalLLMs.WebApp `\n        -- --connector-type Ollama --model \u003cmodel-name\u003e\n    ```\n\n1. Open your web browser, navigate to `http://localhost:5160`, and enter prompts.\n\n\u003c/details\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevkimchi%2Fmeai-for-local-llms","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdevkimchi%2Fmeai-for-local-llms","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevkimchi%2Fmeai-for-local-llms/lists"}