{"id":25266061,"url":"https://github.com/maharun0/cse299","last_synced_at":"2026-05-03T11:37:17.331Z","repository":{"id":275647207,"uuid":"919936403","full_name":"maharun0/cse299","owner":"maharun0","description":"Langchain | Streamlit | MongoDB | FastAPI | Ollama","archived":false,"fork":false,"pushed_at":"2025-04-14T16:51:37.000Z","size":315083,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-28T10:03:57.303Z","etag":null,"topics":["chatbot","langchain","ollama","retrieval-augmented-generation"],"latest_commit_sha":null,"homepage":"","language":"Python","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/maharun0.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":"2025-01-21T09:26:18.000Z","updated_at":"2025-04-14T16:51:42.000Z","dependencies_parsed_at":"2025-04-14T18:01:59.923Z","dependency_job_id":null,"html_url":"https://github.com/maharun0/cse299","commit_stats":null,"previous_names":["maharun0/cse299"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/maharun0/cse299","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maharun0%2Fcse299","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maharun0%2Fcse299/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maharun0%2Fcse299/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maharun0%2Fcse299/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/maharun0","download_url":"https://codeload.github.com/maharun0/cse299/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maharun0%2Fcse299/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281418054,"owners_count":26497723,"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":"2025-10-28T02:00:06.022Z","response_time":60,"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":["chatbot","langchain","ollama","retrieval-augmented-generation"],"created_at":"2025-02-12T08:32:16.644Z","updated_at":"2025-10-28T10:04:12.878Z","avatar_url":"https://github.com/maharun0.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Hybrid Documents RAG based Chatbot\n\n## Abstract\n\nState-of-the-art commercial conversational models\nare typically limited to public data, lacking direct access to\npersonal or specialized documents due to security concerns about\nexposing sensitive information. To bridge this gap, the Hybrid\nDocuments RAG based Chatbot empowers users to securely tap\ninto their own document collections for personalized information\nretrieval. By seamlessly combining rapid local indexing, context-\nsensitive ranking, and reranking, the system enables fast, precise\nsearches without relying on cloud-based services. This privacy-\ncentric design ensures that sensitive data remains safely on-\ndevice, while also offering online mode for accessing more compu-\ntational power. Ultimately, the chatbot offers a groundbreaking\nparadigm in personalized information discovery, striking an ideal\nbalance between performance, flexibility, and security.\n\n## Features\n\n- **Hybrid Retrieval** – Supports both online (web search) and offline (local document search) for flexibility and privacy.  \n- **Efficient Document Processing** – Extracts text from PDFs, DOCX, and other formats using semantic and fixed-size chunking for better context.  \n- **Vector-Based Search** – Uses FAISS and embeddings for fast and accurate information retrieval.  \n- **Reranking for Accuracy** – Combines BM25, cross-encoders, and hybrid retrieval to improve search relevance.  \n- **Adaptive AI Models** – SLMs for speed, LLMs for complex queries, with dynamic selection based on query needs.  \n- **Interactive Conversational Search** – Refines responses with follow-up queries and learns from user feedback.  \n- **Privacy \u0026 Security** – Offline mode ensures sensitives data stays on-device, reducing cloud dependencies.  \n- **User-Friendly Interface** – Enables seamless document search with conversational interaction.  \n\nThis chatbot enhances document-based search with AI-driven conversation, accuracy, and privacy.  \n\n---\n## Rag Pipeline\n![Rag Pipeline](./Reports/data/rag_pipeline.png)\n\n---\n## How to run the Project?\n\n### Prerequisites\n1. **Install Ollama**:\n   - Download and install Ollama from [ollama.com](https://ollama.com/).\n   - Install required models (e.g., `qwen2.5:0.5b`, `nomic-embed-text`):\n     ```bash\n     ollama pull qwen2.5:0.5b\n     ollama pull nomic-embed-text\n     ```\n\n2. **MongoDB Setup**:\n   - Install MongoDB Compass and create a database named `rag_app_db` with a collection `sessions`.\n\n### Running it\n- From the main directory run following command\n```\npython main.py\n```\n\nThis will start Frontend, Backend, MongoDb and Ollama.\n\n## Demo\n\u003cvideo width=\"400\" controls\u003e\n  \u003csource src=\"Reports/Demo/RAG%20Project%20Demo.mp4\" type=\"video/mp4\"\u003e\n  Your browser does not support the video tag.\n\u003c/video\u003e\n\n## Preview\n![image](https://github.com/user-attachments/assets/f7cf3c0e-3b8a-4190-853e-e70ef3a61696)\n\n## Contributors\n\n- **Maharun Afroz** \n- **Sanjida Amin Nadia**\n- **Tasnia Hossain**\n- **Tahmina Mozumdar**\n---\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaharun0%2Fcse299","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmaharun0%2Fcse299","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaharun0%2Fcse299/lists"}