{"id":48542345,"url":"https://github.com/dark-ang3l07/nucleus-rag","last_synced_at":"2026-04-08T05:02:54.367Z","repository":{"id":348737142,"uuid":"1199317130","full_name":"daRk-ang3L07/Nucleus-rag","owner":"daRk-ang3L07","description":"A production-grade, multi-model RAG (Retrieval-Augmented Generation) system built for resilience and accuracy, featuring a TypeScript/React frontend and a Python/FastAPI backend. Architected to run efficiently on Hugging Face Spaces.","archived":false,"fork":false,"pushed_at":"2026-04-02T15:16:52.000Z","size":1097,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-03T03:40:02.239Z","etag":null,"topics":["docker-compose","gemini-api","google","huggingface","langchain"],"latest_commit_sha":null,"homepage":"https://dark-ang3l-nucleus-rag.hf.space/#","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/daRk-ang3L07.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2026-04-02T08:30:05.000Z","updated_at":"2026-04-02T15:20:23.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/daRk-ang3L07/Nucleus-rag","commit_stats":null,"previous_names":["dark-ang3l07/nucleus-rag"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/daRk-ang3L07/Nucleus-rag","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daRk-ang3L07%2FNucleus-rag","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daRk-ang3L07%2FNucleus-rag/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daRk-ang3L07%2FNucleus-rag/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daRk-ang3L07%2FNucleus-rag/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/daRk-ang3L07","download_url":"https://codeload.github.com/daRk-ang3L07/Nucleus-rag/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daRk-ang3L07%2FNucleus-rag/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31540831,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T16:28:08.000Z","status":"online","status_checked_at":"2026-04-08T02:00:06.127Z","response_time":54,"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":["docker-compose","gemini-api","google","huggingface","langchain"],"created_at":"2026-04-08T05:02:43.413Z","updated_at":"2026-04-08T05:02:54.345Z","avatar_url":"https://github.com/daRk-ang3L07.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# 🚀 Nucleus RAG: High-Performance GenAI Pipeline\n\nA production-grade, multi-model RAG (Retrieval-Augmented Generation) system built for resilience and accuracy, featuring a **TypeScript/React** frontend and a **Python/FastAPI** backend. Architected to run efficiently on **Hugging Face Spaces**.\n\n## 🏆 Industrial-Strength Features\n- **Multi-Model Fallback Router**: Intelligent failover from **Google Gemini 2.5** to **Hugging Face (Qwen-7B)** during API quota (429) events, ensuring 100% chat availability.\n- **Advanced Retrieval Pipeline**: Orchestrated via **LangChain**, combining **Hybrid Search (Keyword + Semantic)** with **Multi-Query Expansion** and **TinyBERT Cross-Encoder Reranking**.\n- **Quota-Friendly \"Lite Auditor\"**: A custom-engineered evaluation suite that performs full RAG benchmarking (Faithfulness, Relevancy) in a single-shot AI call to survive limited API quotas.\n- **TypeScript Glassmorphism UI**: A premium dashboard featuring citation accordions, real-time status polling, and markdown-rendered AI responses.\n- **Dockerized Architecture**: Fully containerized for one-click deployment to any OCI-compliant cloud provider.\n\n---\n\n## 🛠️ Tech Stack\n- **AI/LLM**: Google Gemini 2.5 Flash, LangChain, Qwen-7B (Hugging Face), Phi-3 Mini.\n- **Database**: ChromaDB (Vector Store), Supabase (Chat History \u0026 Auth).\n- **Backend**: FastAPI, Asynchronous Python, Background Tasks, Docker.\n- **Frontend**: React 18, TypeScript, Vite, Framer Motion, TailwindCSS.\n\n---\n\n## 🚀 One-Click HF Spaces Setup\nTo deploy this project to **Hugging Face Spaces**:\n\n1. **Create a New Space**: Select the **Docker** SDK.\n2. **Configure Secrets**: Add the following variables to your Space settings:\n   - `GOOGLE_API_KEY`: Your Gemini API Key.\n   - `HUGGINGFACEHUB_API_TOKEN`: For reranking and model fallbacks.\n   - `SUPABASE_URL` \u0026 `SUPABASE_ANON_KEY`: For chat persistence.\n3. **Push to Main**: The `Dockerfile` is pre-configured to handle the multi-process environment.\n\n---\n\n## 🧪 AI Performance Monitoring\nThe system includes a dedicated `/api/v1/evaluate/` endpoint that benchmarks your RAG pipeline. It uses a specialized \"Lite Auditor\" prompt to survive the 20-request daily limit of experimental LLM tiers.\n\n**Key Metrics:**\n- **Faithfulness**: Mathematically proves the answer is derived ONLY from your documents.\n- **Answer Relevancy**: Measures how precisely the AI addressed the user's specific intent.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdark-ang3l07%2Fnucleus-rag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdark-ang3l07%2Fnucleus-rag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdark-ang3l07%2Fnucleus-rag/lists"}