{"id":32521893,"url":"https://github.com/swagfin/ollamatest","last_synced_at":"2026-07-06T08:31:50.989Z","repository":{"id":308071748,"uuid":"1031525223","full_name":"swagfin/OllamaTest","owner":"swagfin","description":"RAG Demo App with Local Embeddings and Qdrant","archived":false,"fork":false,"pushed_at":"2025-09-18T19:43:13.000Z","size":20,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-10-28T06:46:08.128Z","etag":null,"topics":["ai","artificial-intelligence","machine-learning","ml","qdrant","qdrant-vector-database","text-embeddings"],"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/swagfin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2025-08-03T23:29:27.000Z","updated_at":"2025-09-18T19:43:17.000Z","dependencies_parsed_at":"2025-08-04T16:18:17.343Z","dependency_job_id":null,"html_url":"https://github.com/swagfin/OllamaTest","commit_stats":null,"previous_names":["swagfin/ollamatest"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/swagfin/OllamaTest","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/swagfin%2FOllamaTest","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/swagfin%2FOllamaTest/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/swagfin%2FOllamaTest/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/swagfin%2FOllamaTest/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/swagfin","download_url":"https://codeload.github.com/swagfin/OllamaTest/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/swagfin%2FOllamaTest/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35184015,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-06T02:00:07.184Z","response_time":106,"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","artificial-intelligence","machine-learning","ml","qdrant","qdrant-vector-database","text-embeddings"],"created_at":"2025-10-28T06:45:50.111Z","updated_at":"2026-07-06T08:31:50.982Z","avatar_url":"https://github.com/swagfin.png","language":"C#","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RAG Demo with Local Embeddings and Qdrant\n\nThis project demonstrates how to build a simple Retrieval-Augmented Generation (RAG) system using:\n\n- **Local Text Embeddings** via [SmartComponents.LocalEmbeddings](https://github.com/dotnet/smartcomponents)\n- **Vector Storage \u0026 Search** via [Qdrant](https://qdrant.tech/)\n- **Ollama** to serve a local language model (e.g., `mistral:7b`)\n\n## 💡 Why this project?\n\nThe biggest challenge in RAG systems is **text embedding** — converting meaningful text into high-dimensional vectors for retrieval. While many solutions rely on cloud APIs or heavy frameworks like ONNX, this project demonstrates how to:\n\n- Use **local embeddings** with minimal setup\n- Achieve **fast and accurate semantic search**\n- Keep everything **offline and privacy-preserving**\n\n## ⚙️ Technologies Used\n\n| Component         | Tool/Library                                 |\n|-------------------|----------------------------------------------|\n| Embeddings        | [SmartComponents.LocalEmbeddings](https://www.nuget.org/packages/SmartComponents.LocalEmbeddings/) |\n| Vector DB         | [Qdrant](https://qdrant.tech) (running locally) |\n| LLM               | [`Ollama`](https://ollama.com/) (`mistral:7b`) |\n| API Layer         | ASP.NET Core Web API                         |\n\n## 🧠 How It Works\n\n```\n[User Question]\n     ↓\nLocal Embedder (Microsoft's smartcomponents)\n     ↓\nQdrant Search (Vector DB)\n     ↓\nTop Document Retrieved\n     ↓\nMistral via Ollama (LLM)\n     ↓\nFinal Answer\n```\n\n## Setup\n\n1. Clone the repo.\n2. Install Qdrant locally or run via Docker.\n3. Run Ollama with:  \n   ```bash\n   ollama run mistral\n   ```\n4. Launch the ASP.NET API project.\n\n## License\n\nMIT License.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fswagfin%2Follamatest","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fswagfin%2Follamatest","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fswagfin%2Follamatest/lists"}