{"id":30273123,"url":"https://github.com/mrigank005/qdrant","last_synced_at":"2025-08-16T06:39:37.507Z","repository":{"id":310009996,"uuid":"1038372763","full_name":"Mrigank005/Qdrant","owner":"Mrigank005","description":null,"archived":false,"fork":false,"pushed_at":"2025-08-15T04:51:06.000Z","size":30,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-15T06:22:42.294Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/Mrigank005.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}},"created_at":"2025-08-15T04:37:33.000Z","updated_at":"2025-08-15T04:51:10.000Z","dependencies_parsed_at":"2025-08-15T06:22:43.624Z","dependency_job_id":"68f6986f-0ec3-405b-8e78-af3706af5db4","html_url":"https://github.com/Mrigank005/Qdrant","commit_stats":null,"previous_names":["mrigank005/qdrant"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Mrigank005/Qdrant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mrigank005%2FQdrant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mrigank005%2FQdrant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mrigank005%2FQdrant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mrigank005%2FQdrant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Mrigank005","download_url":"https://codeload.github.com/Mrigank005/Qdrant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mrigank005%2FQdrant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270678383,"owners_count":24626918,"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","status":"online","status_checked_at":"2025-08-16T02:00:11.002Z","response_time":91,"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":[],"created_at":"2025-08-16T06:39:36.095Z","updated_at":"2025-08-16T06:39:37.494Z","avatar_url":"https://github.com/Mrigank005.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Qdrant RAG Pipeline\n\nA complete implementation of a Retrieval-Augmented Generation (RAG) pipeline using Qdrant vector database, featuring document injection and semantic search capabilities.\n\n\n## Features\n\n- **Document Processing**: Supports multiple file formats (PDF, DOCX, CSV, JSON, etc.)\n- **Vector Embeddings**: Uses state-of-the-art sentence transformers\n- **Hybrid Search**: Combines semantic and keyword search\n- **Analytics Dashboard**: Track search performance and patterns\n- **Security**: Input validation and sanitization\n- **Health Monitoring**: System resource tracking\n\n## Components\n\n1. **Data-Injection.py**: Ingests and processes documents into Qdrant collections\n2. **Data-Retrieval.py**: Interactive search interface with analytics\n3. **config.yaml**: Centralized configuration for all components\n\n## Installation\n\n```bash\n# Clone the repository\ngit clone https://github.com/yourusername/qdrant-rag-pipeline.git\ncd qdrant-rag-pipeline\n\n# Install dependencies\npip install -r requirements.txt\n\n# Download spaCy model\npython -m spacy download en_core_web_sm\n```\n\n## Configuration\n\nEdit `config.yaml` to customize:\n\n```yaml\nqdrant:\n  host: \"localhost\"  # Qdrant server address\n  port: 6333         # Qdrant port\n\nmodel:\n  name: \"all-MiniLM-L6-v2\"  # Embedding model\n  device: \"cpu\"             # cpu/cuda/mps\n\nprocessing:\n  chunk_size: 500           # Text chunk size\n  supported_extensions:     # File types to process\n    - \".pdf\"\n    - \".docx\"\n    - \".txt\"\n\nInput Directory\ninput_dir: \"file\\\\path\\\\docs\"  # Custom path to your documents folder\n```\n\n## Usage\n\n### 1. Inject Documents\n```bash\npython Data-Injection.py\n```\n\n### 2. Search Interface\n```bash\npython Data-Retrieval.py\n```\n\n## System Architecture\n\n```mermaid\ngraph TD\n    A[Documents] --\u003e B[Data Injection]\n    B --\u003e C[Qdrant Vector DB]\n    C --\u003e D[Data Retrieval]\n    D --\u003e E[User Interface]\n```\n\n## License\n\n[MIT](LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmrigank005%2Fqdrant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmrigank005%2Fqdrant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmrigank005%2Fqdrant/lists"}