{"id":25804776,"url":"https://github.com/itsaidi/ragify","last_synced_at":"2026-06-11T12:31:23.210Z","repository":{"id":265737538,"uuid":"896569849","full_name":"ITSAIDI/RAGify","owner":"ITSAIDI","description":"RAGify is a Retrieval-Augmented Generation (RAG) application designed to enhance the way you interact with PDF documents. Powered by Streamlit, LangChain, ChromaDB, and local LLMs via Ollama, this app allows you to query PDF files intelligently in both English and Arabic.","archived":false,"fork":false,"pushed_at":"2024-11-30T23:46:35.000Z","size":8705,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-28T01:24:23.164Z","etag":null,"topics":["langchain","ollama","python","rag","readthedocs","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/ITSAIDI.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}},"created_at":"2024-11-30T18:01:06.000Z","updated_at":"2025-02-21T23:07:22.000Z","dependencies_parsed_at":null,"dependency_job_id":"02139a36-7c4b-4d18-b6ff-f3447e698f42","html_url":"https://github.com/ITSAIDI/RAGify","commit_stats":null,"previous_names":["itsaidi/ragify"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ITSAIDI/RAGify","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ITSAIDI%2FRAGify","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ITSAIDI%2FRAGify/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ITSAIDI%2FRAGify/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ITSAIDI%2FRAGify/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ITSAIDI","download_url":"https://codeload.github.com/ITSAIDI/RAGify/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ITSAIDI%2FRAGify/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34199516,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-11T02:00:06.485Z","response_time":57,"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":["langchain","ollama","python","rag","readthedocs","streamlit"],"created_at":"2025-02-27T18:53:46.726Z","updated_at":"2026-06-11T12:31:23.205Z","avatar_url":"https://github.com/ITSAIDI.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"assets/RAGIFY_Logo.png\" alt=\"RAGify in Action\" align =\"center\" style=\"width:300px; height:300px;\"/\u003e\n\u003c/div\u003e  \n\n# RAGify  \n\n**RAGify** is a Retrieval-Augmented Generation (RAG) application designed to enhance the way you interact with PDF documents. Powered by **Streamlit**, **LangChain**, **ChromaDB**, and local **LLMs via Ollama**, this app allows you to query PDF files intelligently in both **English/French** and **Arabic**.  \n\n---\n\n## 🚀 Key Features  \n\n- **PDF Querying**: Upload PDFs and ask questions to extract insights quickly and accurately.  \n- **Multilingual Support**: Seamless handling of both **English** and **Arabic** text for querying and responses.  \n- **Local LLMs**: Ensures privacy by using local language models via **Ollama**—no external API required.  \n- **Efficient Retrieval**: Employs **ChromaDB** for fast and accurate document embeddings and retrieval.  \n- **Streamlit UI**: User-friendly interface for easy document interaction.  \n\n---\n\n## 📷 Screenshots  \n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd align=\"center\"\u003e\n      \u003cimg src=\"assets/Frame1.jpg\" alt=\"RAGify Screenshot 1\" style=\"width:600px; height:auto;\"/\u003e\n    \u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\n      \u003cimg src=\"assets/Frame2.jpg\" alt=\"RAGify Screenshot 2\" style=\"width:600px; height:auto;\"/\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd align=\"center\"\u003e\n      \u003cimg src=\"assets/Frame3.jpg\" alt=\"RAGify Screenshot 3\" style=\"width:600px; height:auto;\"/\u003e\n    \u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\n      \u003cimg src=\"assets/Frame4.jpg\" alt=\"RAGify Screenshot 4\" style=\"width:600px; height:auto;\"/\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n## 🛠️ Installation  \n\n### Clone the Repository  \n```bash  \ngit clone https://github.com/ITSAIDI/RAGify.git  \ncd RAGify\ncd Code \n```  \n\n### Install Dependencies\n\n- Install first \u003ca href=\"https://ollama.com/download\"\u003eOllama\u003c/a\u003e server in your machine.\n- In a new **cmd** run the commands bellow to install some models :\n\n```bash  \nollama pull hf.co/nomic-ai/nomic-embed-text-v1.5-GGUF:F32 \nollama pull llama3.2:3b\nollama pull llama3.1:8b\nollama pull qwen:7b \n```\n- Then in a new Conda env or venv install some python libraries with :\n\n```bash  \npip install -r requirements.txt  \n```  \n\n### Start the Application  \n```bash  \nstreamlit run main.py  \n```  \n\n---\n\n## 📝 How to Use  \n\n1. Upload a PDF file(s) via the Streamlit interface.  \n2. Choose your query language (Arabic or other).  \n3. Ask questions about the document.  \n4. Get precise answers powered by the RAG pipeline.  \n\n---\n\n## 🌐 Technologies Used  \n\n- **Streamlit**: Frontend interface for user interaction.  \n- **LangChain**: Framework for building RAG pipelines.  \n- **ChromaDB**: Vector database for document embeddings and retrieval.  \n- **Ollama LLMs**: Local language model server for secure and private inference.\n  \n---\n\n## 🤝 Contributing  \n\nContributions are welcome! Please fork the repository and submit a pull request.  \n\n---\n\n## 🌟 Acknowledgments  \n\nSpecial thanks to the developers of Streamlit, LangChain, ChromaDB, and Ollama for their fantastic tools that made this app possible.  \n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fitsaidi%2Fragify","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fitsaidi%2Fragify","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fitsaidi%2Fragify/lists"}