{"id":32492886,"url":"https://github.com/fkucukkara/ollamaplayground","last_synced_at":"2026-05-07T14:42:02.062Z","repository":{"id":317068395,"uuid":"1018879891","full_name":"fkucukkara/ollamaPlayground","owner":"fkucukkara","description":"This a playground project about Ollama which is an open-source project that allows you to run large language models (LLMs) locally on your machine.","archived":false,"fork":false,"pushed_at":"2025-10-04T12:39:08.000Z","size":13,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-27T11:56:47.729Z","etag":null,"topics":["ai","csharp","dotnet-core","llm","ollama","ollama-api"],"latest_commit_sha":null,"homepage":"","language":"C#","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/fkucukkara.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-07-13T08:50:40.000Z","updated_at":"2025-10-05T12:33:36.000Z","dependencies_parsed_at":"2025-09-28T17:52:53.174Z","dependency_job_id":null,"html_url":"https://github.com/fkucukkara/ollamaPlayground","commit_stats":null,"previous_names":["fkucukkara/ollamaplayground"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/fkucukkara/ollamaPlayground","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fkucukkara%2FollamaPlayground","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fkucukkara%2FollamaPlayground/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fkucukkara%2FollamaPlayground/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fkucukkara%2FollamaPlayground/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fkucukkara","download_url":"https://codeload.github.com/fkucukkara/ollamaPlayground/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fkucukkara%2FollamaPlayground/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32742560,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-07T02:14:30.463Z","status":"ssl_error","status_checked_at":"2026-05-07T02:14:29.405Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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","csharp","dotnet-core","llm","ollama","ollama-api"],"created_at":"2025-10-27T11:56:22.182Z","updated_at":"2026-05-07T14:42:02.055Z","avatar_url":"https://github.com/fkucukkara.png","language":"C#","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Ollama Guide\n\nOllama is an open-source project that allows you to run large language models (LLMs) locally on your machine. It provides an easy way to download, run, and manage various AI models.\n\n\u003e **Note**: This project's code was generated with the assistance of GitHub Copilot, showcasing the power of AI-assisted development.\n\nThis repository contains:\n1. Documentation for using Ollama\n2. A .NET Core minimal API project for interacting with Ollama\n3. Model library information\n\n## Table of Contents\n- [Installation](#installation)\n- [Quick Start](#quick-start)\n- [Available Models](#available-models)\n- [System Requirements](#system-requirements)\n- [Model Management](#model-management)\n- [API Usage](#api-usage)\n- [.NET Core API Project](#net-core-api-project)\n\n## Installation\n\n### Windows Installation\n1. Download the [OllamaSetup.exe](https://ollama.com/download/OllamaSetup.exe)\n2. Run the installer\n3. Follow the installation wizard\n4. After installation, Ollama will start automatically\n\n### System Requirements\n\n- Minimum 8GB RAM for 7B models\n- Minimum 16GB RAM for 13B models\n- Minimum 32GB RAM for 33B models\n- NVIDIA GPU (optional but recommended)\n\n## Quick Start\n\n1. Open a terminal/command prompt\n2. Pull a model:\n```sh\nollama pull phi3\n```\n\n3. Run the model:\n```sh\nollama run phi3\n```\n\n## Model Management\n\nBasic commands:\n```sh\n# List available models\nollama list\n\n# Remove a model\nollama rm modelname\n\n# Show model info\nollama show modelname\n\n# Copy a model\nollama cp source destination\n```\n\n## Available Models\n\nSome popular models include:\n\n| Model | Size | Description |\n|-------|------|-------------|\n| Gemma 3 | 4B | General purpose model |\n| Mistral | 7B | General chat model |\n| CodeLlama | 7B | Code generation |\n| LLaVA | 7B | Vision model |\n| Phi 4 | 14B | Advanced reasoning |\n\n[View full model library](https://ollama.com/library)\n\n## API Usage\n\nOllama provides a REST API for integration:\n\n```sh\n# Generate a response\ncurl http://localhost:11434/api/generate -d '{\n  \"model\": \"phi3\",\n  \"prompt\": \"Why is the sky blue?\"\n}'\n\n# Chat conversation\ncurl http://localhost:11434/api/chat -d '{\n  \"model\": \"phi3\",\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"Why is the sky blue?\" }\n  ]\n}'\n```\n\n## .NET Core API Project\n\nThe repository includes a .NET Core minimal API project that provides a RESTful interface to Ollama. The API is built using minimal API architecture and includes:\n\n### Features\n- Swagger/OpenAPI documentation\n- Strongly typed responses\n- Proper error handling\n- Clean architecture with service layer\n\n### API Endpoints\n\nAll endpoints are available under `/api/ollama` and return typed responses:\n\n#### List Models\n```http\nGET /api/ollama/models\n```\nReturns a list of available models.\n\n#### Generate Text\n```http\nPOST /api/ollama/generate\nContent-Type: application/json\n\n{\n    \"model\": \"modelname\",\n    \"prompt\": \"Your prompt here\"\n}\n```\nGenerates text using the specified model.\n\n#### Chat\n```http\nPOST /api/ollama/chat\nContent-Type: application/json\n\n{\n    \"model\": \"modelname\",\n    \"messages\": [\n        {\n            \"role\": \"user\",\n            \"content\": \"Your message here\"\n        }\n    ]\n}\n```\nStart or continue a chat conversation.\n\n### Response Format\nAll endpoints return properly typed responses:\n- 200: Successful operation with typed response\n- 404: Model not found\n- 500: Internal server error\n\n### API Documentation\nThe API includes Swagger documentation available at `/swagger` when running in development mode.\n\n### Features\n- Minimal API design for better performance\n- Swagger/OpenAPI documentation\n- Error handling with proper HTTP status codes\n- Async/await pattern\n- Dependency injection\n\n### API Endpoints\n\n1. Generate Text\n```http\nPOST /api/ollama/generate\nContent-Type: application/json\n\n{\n  \"model\": \"phi3\",\n  \"prompt\": \"What is quantum computing?\"\n}\n```\n\n2. Chat\n```http\nPOST /api/ollama/chat\nContent-Type: application/json\n\n{\n  \"model\": \"phi3\",\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"What is quantum computing?\" }\n  ]\n}\n```\n\n3. List Models\n```http\nGET /api/ollama/models\n```\n\n### Running the Project\n\n1. Make sure Ollama is installed and running\n2. Navigate to the project directory:\n```sh\ncd OllamaApi\n```\n\n3. Run the project:\n```sh\ndotnet run\n```\n\n4. Open Swagger UI:\n```\nhttps://localhost:7000/swagger\n```\n\n### Error Handling\n- 404: Model not found\n- 500: Internal server error with detailed message\n- Proper exception handling for HTTP and deserialization errors\n\n## Additional Resources\n- [Official Documentation](https://github.com/ollama/ollama/tree/main/docs)\n- [GitHub Repository](https://github.com/ollama/ollama)\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffkucukkara%2Follamaplayground","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffkucukkara%2Follamaplayground","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffkucukkara%2Follamaplayground/lists"}