{"id":28497045,"url":"https://github.com/akdevv/ai-rag-prod","last_synced_at":"2025-08-04T14:34:15.737Z","repository":{"id":290975835,"uuid":"975882125","full_name":"akdevv/ai-rag-prod","owner":"akdevv","description":"A fast RAG app built with LangChain, QdrantDB, and Ollama for local models.","archived":false,"fork":false,"pushed_at":"2025-05-07T20:43:32.000Z","size":148,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-08T12:43:07.356Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/akdevv.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}},"created_at":"2025-05-01T04:36:22.000Z","updated_at":"2025-05-07T20:45:59.000Z","dependencies_parsed_at":"2025-05-01T17:57:08.836Z","dependency_job_id":null,"html_url":"https://github.com/akdevv/ai-rag-prod","commit_stats":null,"previous_names":["akdevv/ai-rag-prod"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/akdevv/ai-rag-prod","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akdevv%2Fai-rag-prod","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akdevv%2Fai-rag-prod/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akdevv%2Fai-rag-prod/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akdevv%2Fai-rag-prod/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/akdevv","download_url":"https://codeload.github.com/akdevv/ai-rag-prod/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akdevv%2Fai-rag-prod/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263218319,"owners_count":23432472,"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","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":[],"created_at":"2025-06-08T12:32:10.915Z","updated_at":"2025-07-02T21:32:39.275Z","avatar_url":"https://github.com/akdevv.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI-RAG: PDF Document Chat Application\n\nA powerful RAG (Retrieval-Augmented Generation) application that allows users to upload PDF documents and engage in contextual conversations with AI about the document content.\n\n## Features\n\n- PDF document upload and processing\n- AI-powered chat interface for document interaction\n- Local LLM integration using Ollama\n- Vector database for efficient document retrieval\n- Queue-based document processing\n- Modern and responsive UI\n- User authentication with Clerk\n\n## Tech Stack\n\n### Frontend\n- Next.js - React framework for building the user interface\n- Shadcn - UI component library for a modern design system\n- Clerk - Authentication and user management\n\n### Backend\n- Express.js - Node.js web application framework\n- Bun - JavaScript runtime and package manager\n- LangChain - Framework for building LLM-powered applications\n- Ollama - Local LLM integration (Mistral model)\n- QdrantDB - Vector database for storing embeddings\n- BullMQ - Queue system for handling document processing\n- Multer - File upload handling\n- Docker - Containerization\n- Valkey - Key-value store\n\n## Prerequisites\n\n- Docker and Docker Compose\n- Bun runtime\n- Ollama\n- Clerk account for authentication\n\n## Local Setup\n\n1. **Start Docker Services**\n   ```bash\n   docker compose up -d\n   # To stop services\n   docker compose down\n   ```\n\n2. **Setup Ollama**\n   - Install Ollama from [ollama.ai](https://ollama.ai)\n   - Pull required models:\n     ```bash\n     ollama pull mistral\n     ollama pull nomic-embed-text\n     ```\n   - Start Ollama service\n\n3. **Backend Setup**\n   ```bash\n   cd server\n   bun install\n   # Start the worker\n   bun run dev:worker\n   # In a new terminal, start the server\n   bun run dev\n   ```\n\n4. **Frontend Setup**\n   ```bash\n   cd client\n   bun install\n   # Create .env file and add Clerk credentials\n   echo \"NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=\u003cyour-key\u003e\n   CLERK_SECRET_KEY=\u003cyour-key\u003e\" \u003e .env\n   bun run dev\n   ```\n\n5. **Access the Application**\n   - Open [http://localhost:3000](http://localhost:3000)\n   - Sign in using Clerk authentication\n   - Upload a PDF document\n   - Start chatting with the AI about the document content\n\n## Technology Details\n\n- **Ollama**: Local LLM framework for running open-source models\n- **Docker**: Containerization platform for consistent development environments\n- **BullMQ**: Redis-based queue system for handling background jobs\n- **Valkey**: High-performance key-value store\n- **LangChain**: Framework for building LLM applications with RAG capabilities\n- **Multer**: Middleware for handling multipart/form-data (file uploads)\n- **QdrantDB**: Vector similarity search engine for storing and retrieving embeddings\n- **Clerk**: Authentication and user management platform\n\n## Credits\n\nThis project was inspired by and built following the tutorial from [Build AI Chat with PDF App with Next.js and Vector DB](https://www.youtube.com/watch?v=2DXiOtEwWtU).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakdevv%2Fai-rag-prod","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fakdevv%2Fai-rag-prod","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakdevv%2Fai-rag-prod/lists"}