{"id":24884165,"url":"https://github.com/mohd-faizy/rag-deepseek","last_synced_at":"2026-04-10T15:50:45.815Z","repository":{"id":275201712,"uuid":"925248443","full_name":"mohd-faizy/RAG-DeepSeek","owner":"mohd-faizy","description":"Efficiently search and retrieve information from PDF documents using a Retrieval-Augmented Generation (RAG) approach. This project leverages DeepSeek-R1 (1.5B) for advanced language understanding, FAISS for high-speed vector search, and Hugging Face’s ecosystem for enhanced NLP capabilities. With an intuitive Streamlit interface and Ollama for mode","archived":false,"fork":false,"pushed_at":"2025-03-09T20:12:58.000Z","size":415,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-09T21:17:52.504Z","etag":null,"topics":["deepseek-r1","faiss-cpu","faiss-vector-database","huggingface","langchain","ollama","rag","retrival-augmented-generation","streamlit"],"latest_commit_sha":null,"homepage":"","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/mohd-faizy.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}},"created_at":"2025-01-31T14:16:58.000Z","updated_at":"2025-03-09T20:13:01.000Z","dependencies_parsed_at":"2025-01-31T20:44:48.974Z","dependency_job_id":null,"html_url":"https://github.com/mohd-faizy/RAG-DeepSeek","commit_stats":null,"previous_names":["mohd-faizy/rag-deepseek"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FRAG-DeepSeek","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FRAG-DeepSeek/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FRAG-DeepSeek/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FRAG-DeepSeek/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mohd-faizy","download_url":"https://codeload.github.com/mohd-faizy/RAG-DeepSeek/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245815835,"owners_count":20676978,"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":["deepseek-r1","faiss-cpu","faiss-vector-database","huggingface","langchain","ollama","rag","retrival-augmented-generation","streamlit"],"created_at":"2025-02-01T14:19:37.996Z","updated_at":"2025-12-30T23:23:03.389Z","avatar_url":"https://github.com/mohd-faizy.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🤖 RAG PDF Assistant: Powered by 🏆 `DeepSeek-R1` ~ 1.5B , `Ollama`, `Streamlit` \u0026 `FAISS`\n\n![author](https://img.shields.io/badge/author-mohd--faizy-red)\n![Python 3.9+](https://img.shields.io/badge/Python-3.9%2B-3776AB?logo=python\u0026logoColor=white)\n![Streamlit](https://img.shields.io/badge/Streamlit-FF4B4B?logo=streamlit\u0026logoColor=white)\n![Ollama](https://img.shields.io/badge/Ollama-0C0D0E?logo=ollama\u0026logoColor=white)\n![PDFPlumber](https://img.shields.io/badge/PDFPlumber-FF0000?logo=pdf\u0026logoColor=white)\n![LangChain](https://img.shields.io/badge/LangChain-00ADD8?logo=langchain\u0026logoColor=white)\n![HuggingFace](https://img.shields.io/badge/HuggingFace-FFD43B?logo=huggingface\u0026logoColor=black)\n![FAISS](https://img.shields.io/badge/FAISS-00A98F?logo=faiss\u0026logoColor=white)\n\n---\n\n## 🚀🔥 Live Demo 🌍  \n\n👉 **Click below to try it now:**  \n\n[![🚀 Try it Now](https://img.shields.io/badge/Try%20Live-Click%20Here-28a745?style=for-the-badge)](https://rag-deepseek-4xbslhkxhxxdwtmxs7ceey.streamlit.app)\n\n\n\n## 🌟 **Overview**  \n\n**RAG PDF Assistant** is an AI-powered **Retrieval-Augmented Generation (RAG)** chatbot that enables **intelligent PDF document search and retrieval.** It combines:  \n\n✅ **DeepSeek-R1 (1.5B)** – Advanced AI-powered language model for **accurate responses.**  \n✅ **FAISS** – Fast vector search for **efficient document retrieval.**  \n✅ **Ollama** – Lightweight model serving and **seamless inference.**  \n✅ **LangChain** – Modular AI framework for **query execution and reasoning.**  \n✅ **Streamlit** – Intuitive and interactive **web-based UI.**  \n\n### 🎯 **Use Cases**  \n\n🔍 **Quickly search** through large PDF documents.  \n📄 **Summarize reports, research papers, contracts,** and more.  \n📘 **Extract relevant information** with AI-driven accuracy.  \n🤖 **Ask natural language questions** and get concise answers.  \n\n---\n\n## 🚀 **Demo Screenshots**  \n\n### **📌 UI Preview**  \n\n![Demo](https://github.com/mohd-faizy/RAG-DeepSeek/blob/main/assets/rag-pdf-retv.png?raw=true)  \n\n### **📌 Application Workflow**  \n\n![Workflow](https://github.com/mohd-faizy/RAG-DeepSeek/blob/main/assets/RAG-app-flow.png?raw=true)  \n\n---\n\n## 🛠️ **Installation \u0026 Setup**  \n\n### **🔧 Prerequisites**  \n\nEnsure you have the following installed:  \n\n- **Python 3.9+**  \n- **pip** (Python package manager)  \n- **Git** (for cloning the repository)  \n\n### **📥 Step 1: Clone the Repository**  \n\n```bash\n$ git clone https://github.com/mohd-faizy/RAG-DeepSeek.git\n$ cd RAG-DeepSeek\n```\n\n### **📦 Step 2: Install Dependencies**  \n\n```bash\n$ pip install -r requirements.txt\n```\n\n### **⚙️ Step 3: Run the Application**  \n\n1. Start Ollama service:\n\n   ```bash\n   ollama serve\n   ```\n\n2. In a separate terminal, launch the chat interface:\n\n   ```bash\n   streamlit run app/main.py\n   ```\n\nThe application will launch in your browser at `http://localhost:11434/`.  \n\n---\n\n## 📁 **Directory Structure**  \n\n```plaintext\nRAG-DeepSeek/\n├── app/\n│   ├── __init__.py          # Python package initialization\n│   ├── main.py              # Main Streamlit application file\n│   ├── utils.py             # Utility functions for PDF processing, embeddings, retrieval\n├── assets/                  # Static files like images, CSS, etc.\n├── requirements.txt         # Python dependencies\n├── .gitignore               # Files ignored by Git\n├── README.md                # Project documentation\n```\n\n---\n\n## 🧠 **How It Works**  \n\n1️⃣ **Upload a PDF** → The AI extracts and indexes the content.  \n2️⃣ **Ask a question** → The system searches for the most relevant passages.  \n3️⃣ **AI answers your query** → Based on retrieved document content.  \n\n🔹 **Uses FAISS** for **fast, efficient document retrieval.**  \n🔹 **DeepSeek-R1** ensures **high-quality, context-aware answers.**  \n\n---\n\n## 🔗 **Technologies Used**  \n\n| **Technology**  | **Purpose**  |\n|---------------|-------------|\n| **DeepSeek-R1 (1.5B)** | Language model for intelligent responses |\n| **Ollama** | Model serving and inference |\n| **FAISS** | Vector search for document retrieval |\n| **LangChain** | AI-driven reasoning and query handling |\n| **Streamlit** | User-friendly web interface |\n| **PDFPlumber** | Extracting text from PDFs |\n\n---\n\n\n### **🤝 Steps to Contribute**  \n\n1. Fork the repository  \n2. Create a new feature branch (`git checkout -b feature-name`)  \n3. Commit your changes (`git commit -m \"Added new feature\"`)  \n4. Push to your fork (`git push origin feature-name`)  \n5. Open a pull request  \n\n---\n\n## ⚖ ➤ License\n\nThis project is licensed under the **MIT License**. See the [LICENSE](LICENSE) file for details.  \n\n## ❤️ Support\n\nIf you find this repository helpful, show your support by starring it! For questions or feedback, reach out on [Twitter(`X`)](https://twitter.com/F4izy).\n\n## 🔗Connect with me\n\n➤ If you have questions or feedback, feel free to reach out!!!\n\n[\u003cimg align=\"left\" src=\"https://cdn4.iconfinder.com/data/icons/social-media-icons-the-circle-set/48/twitter_circle-512.png\" width=\"32px\"/\u003e][twitter]\n[\u003cimg align=\"left\" src=\"https://cdn-icons-png.flaticon.com/512/145/145807.png\" width=\"32px\"/\u003e][linkedin]\n[\u003cimg align=\"left\" src=\"https://cdn-icons-png.flaticon.com/512/2626/2626299.png\" width=\"32px\"/\u003e][Portfolio]\n\n[twitter]: https://twitter.com/F4izy\n[linkedin]: https://www.linkedin.com/in/mohd-faizy/\n[Portfolio]: https://ai.stackexchange.com/users/36737/faizy?tab=profile\n\n---\n\n\u003cimg src=\"https://github-readme-stats.vercel.app/api?username=mohd-faizy\u0026show_icons=true\" width=380px height=200px /\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohd-faizy%2Frag-deepseek","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmohd-faizy%2Frag-deepseek","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohd-faizy%2Frag-deepseek/lists"}