{"id":25900481,"url":"https://github.com/jncurrea/rag_developmemt","last_synced_at":"2026-04-07T09:31:27.811Z","repository":{"id":279498053,"uuid":"939010833","full_name":"jncurrea/rag_developmemt","owner":"jncurrea","description":"Creation of RAG agent","archived":false,"fork":false,"pushed_at":"2025-02-25T21:21:22.000Z","size":810,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-03T17:18:09.930Z","etag":null,"topics":["faiss","langchain","llm","machine-learning","openai","rag","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/jncurrea.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":"2025-02-25T21:08:04.000Z","updated_at":"2025-02-25T21:24:54.000Z","dependencies_parsed_at":"2025-02-25T22:34:12.761Z","dependency_job_id":null,"html_url":"https://github.com/jncurrea/rag_developmemt","commit_stats":null,"previous_names":["jncurrea/rag_developmemt"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jncurrea/rag_developmemt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jncurrea%2Frag_developmemt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jncurrea%2Frag_developmemt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jncurrea%2Frag_developmemt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jncurrea%2Frag_developmemt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jncurrea","download_url":"https://codeload.github.com/jncurrea/rag_developmemt/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jncurrea%2Frag_developmemt/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31507951,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T03:10:19.677Z","status":"ssl_error","status_checked_at":"2026-04-07T03:10:13.982Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["faiss","langchain","llm","machine-learning","openai","rag","streamlit"],"created_at":"2025-03-03T02:16:59.290Z","updated_at":"2026-04-07T09:31:27.793Z","avatar_url":"https://github.com/jncurrea.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **RAG-Based LLM Assistant**\n\n## **Overview**\nThis project implements a **Retrieval-Augmented Generation (RAG) system** that allows a **Large Language Model (LLM)** to answer questions based on a given document. The system utilizes **FAISS for vector storage, OpenAI GPT-4 for text generation, and Streamlit for the user interface.**\n\n## **Features**\n- Loads and processes a document by splitting it into chunks.\n- Stores document embeddings in a FAISS vector database.\n- Retrieves relevant document chunks based on user queries.\n- Generates responses using GPT-4 based on the retrieved text.\n- Provides an interactive **web UI** for user interaction.\n\n## **Installation**\n### **1. Clone the Repository**\n```bash\ngit clone https://github.com/jncurrea/rag_developmemt.git\ncd rag_developmemt\n```\n\n### **2. Create a Virtual Environment**\n```bash\npython -m venv venv\nsource venv/bin/activate  # On Windows, use venv\\Scripts\\activate\n```\n\n### **3. Install Dependencies**\n```bash\npip install -r requirements.txt\n```\n\n### **4. Set Up API Keys**\nCreate a `.env` file in the project root and add:\n```bash\nOPENAI_API_KEY=your-openai-api-key\n```\n\n### **5. Run the Application**\n```bash\nstreamlit run app.py\n```\n\n## **Project Workflow**\n### **1. Document Processing**\n- The document is loaded and split into chunks for efficient processing.\n- FAISS stores these chunks as embeddings using OpenAI’s embedding model.\n\n### **2. Query Processing**\n- The system retrieves the most relevant document chunks using FAISS.\n- GPT-4 generates responses based on the retrieved text.\n\n### **3. User Interface**\n- Streamlit provides an interactive UI where users can input queries and receive responses.\n\n## **Technologies Used**\n- **LangChain**: For handling document processing and retrieval.\n- **FAISS**: For storing and searching vector embeddings.\n- **OpenAI GPT-4**: For generating responses.\n- **Streamlit**: For creating the user interface.\n\n## **Test Cases**\nExample queries tested with the system:\n| **Question** | **Response** |\n|-------------|-------------|\n| Who wrote the document? | Ramnath Balasubramanian, Ari Libarikian, and Doug McElhaney |\n| What is the document about? | The impact of AI in the insurance industry and how companies should adapt. |\n| What does the document mention about neural networks? | It discusses convolutional neural networks for AI applications. |\n| How can insurers prepare for AI-driven changes? | By optimizing data strategies and adopting AI technologies. |\n\n## **Future Improvements**\n- Support for multiple documents.\n- Deploy on **Google Cloud** for scalability.\n- Optimize chunking strategies for better retrieval.\n- Track accuracy and response latency for performance monitoring.\n\n## **Contributors**\n- Jose Currea\n\nFor any questions or suggestions, feel free to open an issue or reach out!\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjncurrea%2Frag_developmemt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjncurrea%2Frag_developmemt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjncurrea%2Frag_developmemt/lists"}