{"id":"3055d291-16af-4d31-a31e-07f9963694d6","slug":"qdrant-loader","kind":"mcp","name":"qdrant-loader","summary":"Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligen","owner":"cbtw-apac","repoUrl":"https://github.com/cbtw-apac/qdrant-loader","license":"Apache-2.0","licenseTier":"permissive","trust":"community","stars":56,"match":null,"fewStars":false,"format":"mcp","createdAt":null,"addedAt":"2026-10-14T03:46:07.632Z","logoUrl":"https://avatars.githubusercontent.com/u/142795199?v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools","files-documents","search"],"tags":["cli-tool","cursor-ide","developer-tools","document-processing","embbedings","enterprise-ready","file-conversion","git-integration"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-14T04:06:12.980Z","sample":false,"url":"https://conduits.dev/tools/qdrant-loader","language":"Python","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# QDrant Loader\n\n[![PyPI - qdrant-loader](https://img.shields.io/pypi/v/qdrant-loader?label=qdrant-loader)](https://pypi.org/project/qdrant-loader/)\n[![PyPI - mcp-server](https://img.shields.io/pypi/v/qdrant-loader-mcp-server?label=mcp-server)](https://pypi.org/project/qdrant-loader-mcp-server/)\n[![PyPI - qdrant-loader-core](https://img.shields.io/pypi/v/qdrant-loader-core?label=qdrant-loader-core)](https://pypi.org/project/qdrant-loader-core/)\n![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/martin-papy/qdrant-loader?labelColor=171717&color=FF570A&link=https%3A%2F%2Fcoderabbit.ai&label=CodeRabbit+Reviews)\n[![Test Coverage](https://img.shields.io/badge/coverage-view%20reports-blue)](https://qdrant-loader.net/coverage/)\n[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)\n\n📝 **[Changelog v1.0.4](./CHANGELOG.md)** - Latest improvements and bug fixes\n\n<div align=\"left\">\nA comprehensive toolkit for loading data into Qdrant vector database with advanced MCP server support for AI-powered development workflows.\n</div>\n\n## 🎯 What is QDrant Loader?\n\nQDrant Loader is a data ingestion and retrieval system that collects content from multiple sources, processes and vectorizes it, then provides intelligent search capabilities through a Model Context Protocol (MCP) server for AI development tools.\n\n**Perfect for:**\n\n- 🤖 **AI-powered development** with Cursor, Windsurf, and other MCP-compatible tools\n- 📚 **Knowledge base creation** from technical documentation\n- 🔍 **Intelligent code assistance** with contextual information\n- 🏢 **Enterprise content integration** from multiple data sources\n\n## 📦 Packages\n\nThis monorepo contains three complementary packages:\n\n### 🔄 [QDrant Loader](./packages/qdrant-loader/)\n\nData ingestion and processing engine\n\nCollects and vectorizes content from multiple sources into QDrant vector database.\n\n**Key Features:**\n\n- **Multi-source connectors**: Git, Confluence (Cloud & Data Center), JIRA (Cloud & Data Center), Public Docs, Local Files\n- **File conversion**: PDF, Office docs (Word, Excel, PowerPoint), images, audio, EPUB, ZIP, and more using MarkItDown\n- **Smart chunking**: Modular chunking strategies with intelligent document processing and hierarchical context\n- **Incremental updates**: Change detection and efficient synchronization\n- **Multi-project support**: Organize sources into projects with shared collections\n- **Provider-agnostic LLM**: OpenAI, Azure OpenAI, Ollama, and custom endpoints with unified configuration\n\n### ⚙️ [QDrant Loader Core](./packages/qdrant-loader-core/)\n\nCore library and LLM abstraction layer\n\nProvides the foundational components and provider-agnostic LLM interface used by other packages.\n\n**Key Features:**\n\n- **LLM Provider Abstraction**: Unified interface for OpenAI, Azure OpenAI, Ollama, and custom endpoints\n- **Configuration Management**: Centralized settings and validation for LLM providers\n- **Rate Limiting**: Built-in rate limiting and request management\n- **Error Handling**: Robust error handling and retry mechanisms\n- **Logging**: Structured logging with configurable levels\n\n### 🔌 [QDrant Loader MCP Server](./packages/qdrant-loader-mcp-server/)\n\nAI development integration layer\n\nModel Context Protocol server providing search capabilities to AI development tools.\n\n**Key Features:**\n\n- **MCP Protocol 2025-06-18**: Latest protocol compliance with dual transport support (stdio + HTTP)\n- **Advanced search tools**: Semantic search, hierarchy-aware search, attachment discovery, and conflict detection\n- **Cross-document intelligence**: Document similarity, clustering, relationship analysis, and knowledge graphs\n- **Streaming capabilities**: Server-Sent Events (SSE) for real-time search results\n- **Production-ready**: HTTP transport with security, session management, and health checks\n\n## 🚀 Quick Start\n\n### Installation\n\n```bash\n# Install both packages\npip install qdrant-loader qdrant-loader-mcp-server\n\n# Or install individually\npip install qdrant-loader          # Data ingestion only\npip install qdrant-loader-mcp-server  # MCP server only\n```\n\n### 5-Minute Setup\n\n1. **Create a workspace**\n\n   ```bash\n   mkdir my-workspace && cd my-workspace\n   ```\n\n2. **Initialize workspace with templates**\n\n   ```bash\n   qdrant-loader init --workspace .\n   ```\n\n3. **Configure your environment** (edit `.env`)\n\n   ```bash\n   # Qdrant connection\n   QDRANT_URL=http://localhost:6333\n   QDRANT_COLLECTION_NAME=my_docs\n\n   # LLM provider (new unified configuration)\n   OPENAI_API_KEY=your_openai_key\n   LLM_PROVIDER=openai\n   LLM_BASE_URL=https://api.openai.com/v1\n   LLM_EMBEDDING_MODEL=text-embedding-3-small\n   LLM_CHAT_MODEL=gpt-4o-mini\n   ```\n\n4. **Configure data sources** (edit `config.yaml`)\n\n   ```yaml\n   global:\n     qdrant:\n       url: \"http://localhost:6333\"\n       collection_name: \"my_docs\"\n     llm:\n       provider: \"openai\"\n       base_url: \"https://api.openai.com/v1\"\n       api_key: \"${OPENAI_API_KEY}\"\n       models:\n         embeddings: \"text-embedding-3-small\"\n         chat: \"gpt-4o-mini\"\n       embeddings:\n         vector_size: 1536\n\n   projects:\n     my-project:\n       project_id: \"my-project\"\n       sources:\n         git:\n           docs-repo:\n             base_url: \"https://github.com/your-org/your-repo.git\"\n             branch: \"main\"\n             file_types: [\"*.md\", \"*.rst\"]\n   ```\n\n5. **Load your data**\n\n   ```bash\n   qdrant-loader ingest --workspace .\n   ```\n\n6. **Start the MCP server**\n\n   ```bash\n   mcp-qdrant-loader --env /path/tp/your/.env\n   ```\n\n## 🔧 MCP-Compatible IDE Setup\n\nQDrant Loader works with any IDE/tool that supports MCP, including Cursor, Windsurf, and Claude Desktop.\n\nMinimal MCP server entry (adapt path/format to your tool):\n\n```json\n{\n  \"mcpServers\": {\n    \"qdrant-loader\": {\n      \"command\": \"/path/to/venv/bin/mcp-qdrant-loader\",\n      \"env\": {\n        \"QDRANT_URL\": \"http://localhost:6333\",\n        \"QDRANT_COLLECTION_NAME\": \"my_docs\",\n        \"OPENAI_API_KEY\": \"your_key\"\n      }\n    }\n  }\n}\n```\n\n**Alternative: Use configuration file** (recommended for complex setups):\n\n```json\n{\n  \"mcpServers\": {\n    \"qdrant-loader\": {\n      \"command\": \"/path/to/venv/bin/mcp-qdrant-loader\",\n      \"args\": [\n        \"--config\",\n        \"/path/to/your/config.yaml\",\n        \"--env\",\n        \"/path/to/your/.env\"\n      ]\n    }\n  }\n}\n```\n\nFor tool-specific setup and exact config format:\n\n- **[MCP Setup and Integration](./docs/users/detailed-guides/mcp-server/setup-and-integration.md)** - Full guide\n- **[Cursor Setup](./docs/users/detailed-guides/mcp-server/setup-and-integration.md#-cursor-ide)**\n- **[Windsurf Setup](./docs/users/detailed-guides/mcp-server/setup-and-integration.md#-windsurf)**\n- **[Claude Desktop Setup](./docs/users/detailed-guides/mcp-server/setup-and-integration.md#-claude-desktop)**\n\n**Example queries in AI tools:**\n\n- _\"Find documentation about authentication in our API\"_\n- _\"Show me examples of error handling patterns\"_\n- _\"What are the deployment requirements for this service?\"_\n- _\"Find all attachments related to database schema\"_\n\n## 📚 Documentation\n\n### Getting Started\n\n- **[Getting Started](./docs/getting-started/)** - Quick start and core concepts\n- **[Installation Guide](./docs/getting-started/installation.md)** - Complete setup instructions\n- **[Quick Start](./docs/getting-started/quick-start.md)** - Step-by-step tutorial\n- **[Core Concepts](./docs/getting-started/README.md#-core-concepts)** - Understand the core architecture: workspace model, projects and sources, ingestion pipeline, and MCP search flow\n\n### User Guides\n\n- **[User Guides](./docs/users/)** - Detailed usage instructions\n- **[Configuration](./docs/users/configuration/)** - Complete configuration reference\n- **[Data Sources](./docs/users/detailed-guides/data-sources/)** - Git, Confluence, JIRA setup\n- **[File Conversion](./docs/users/detailed-guides/file-conversion/)** - File processing capabilities\n- **[MCP Server](./docs/users/detailed-guides/mcp-server/)** - AI tool integration\n\n## 🛠️ Developer Resources\n\n- **[Developer hub](./docs/developers)** - Developer guides for architecture, testing, deployment, and contribution workflows.\n- **[Architecture](./docs/developers/architecture/)** - System design overview\n- **[Testing](./docs/developers/testing/)** - Testing guide and best practices\n\n## 🆘 Support\n\n- **[Issues](https://github.com/martin-papy/qdrant-loader/issues)** - Bug reports and feature requests\n- **[Discussions](https://github.com/martin-papy/qdrant-loader/discussions)** - Community Q&A\n\n## 🤝 Contributing\n\nWe welcome contributions! See our [Contributing Guide](./CONTRIBUTING.md) for:\n\n- Development environment setup\n- Code style and standards\n- Pull request process\n\n### Quick Development Setup\n\n```bash\n# Clone and setup\ngit clone https://github.com/martin-papy/qdrant-loader.git\ncd qdrant-loader\n\n# Sync workspace environment (recommended)\nuv sync --all-packages --all-extras\n\n# Add a new dependency during development\nuv add fastapi\nuv sync\n```\n\n## 📄 License\n\nThis project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.\n\n---\n\n**Ready to get started?** Check out our [Quick Start Guide](./docs/getting-started/quick-start.md) or browse the [complete documentation](./docs/).\n"}