{"id":28412575,"url":"https://github.com/rahulsamant37/agentic_rag_crewai","last_synced_at":"2026-04-17T02:31:15.480Z","repository":{"id":295046014,"uuid":"988911602","full_name":"rahulsamant37/agentic_rag_crewai","owner":"rahulsamant37","description":"A powerful Retrieval-Augmented Generation (RAG) system built with CrewAI that intelligently searches through documents and falls back to web search when needed. Features local LLM support with deep-seek-r1 or llama 3.2!","archived":false,"fork":false,"pushed_at":"2025-05-23T17:46:11.000Z","size":578,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-14T22:40:08.784Z","etag":null,"topics":["agentic-rag","crewai","deepseek","firecrawl","llama3","retrieval-augmented-generation","serperapi","uv"],"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/rahulsamant37.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":"2025-05-23T09:07:26.000Z","updated_at":"2025-06-05T07:31:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"d1b912bf-84ce-4362-a22d-8f5906ffed15","html_url":"https://github.com/rahulsamant37/agentic_rag_crewai","commit_stats":null,"previous_names":["rahulsamant37/agentic_rag_crewai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rahulsamant37/agentic_rag_crewai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsamant37%2Fagentic_rag_crewai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsamant37%2Fagentic_rag_crewai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsamant37%2Fagentic_rag_crewai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsamant37%2Fagentic_rag_crewai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rahulsamant37","download_url":"https://codeload.github.com/rahulsamant37/agentic_rag_crewai/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsamant37%2Fagentic_rag_crewai/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31912319,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T18:22:33.417Z","status":"online","status_checked_at":"2026-04-17T02:00:06.879Z","response_time":62,"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":["agentic-rag","crewai","deepseek","firecrawl","llama3","retrieval-augmented-generation","serperapi","uv"],"created_at":"2025-06-02T23:14:31.108Z","updated_at":"2026-04-17T02:31:15.404Z","avatar_url":"https://github.com/rahulsamant37.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# 🤖 Agentic RAG using CrewAI\n\n\u003cdiv align=\"center\"\u003e\n\n![GitHub](https://img.shields.io/github/license/yourusername/agentic-rag-crewai)\n![Python](https://img.shields.io/badge/python-v3.11+-blue.svg)\n![CrewAI](https://img.shields.io/badge/CrewAI-Latest-green)\n\nA powerful Retrieval-Augmented Generation (RAG) system built with CrewAI that intelligently searches through documents and falls back to web search when needed. Features local LLM support with deep-seek-r1 or llama 3.2!\n\n\u003c/div\u003e\n\n## 🌟 Features\n\n- 📚 Document-based search with RAG capabilities\n- 🌐 Automatic fallback to web search\n- 🤖 Local LLM support (deep-seek-r1 or llama 3.2)\n- 🔄 Seamless integration with CrewAI\n- 💨 Fast and efficient document processing\n- 🎯 Precise answer synthesis\n\n## 🔄 System Flow\n\nBelow is the detailed flow diagram of how the system processes queries and generates responses:\n\n```mermaid\ngraph TD\n    A[Start] --\u003e B[Initialize Streamlit App]\n    B --\u003e C[Load LLM Model]\n    C --\u003e D[Initialize Session State]\n    \n    D --\u003e E{PDF Uploaded?}\n    E --\u003e|Yes| F[Create DocumentSearchTool]\n    E --\u003e|No| G[Wait for PDF Upload]\n    \n    F --\u003e H[Index PDF Document]\n    H --\u003e I[Create Crew]\n    \n    I --\u003e J[Create Retriever Agent]\n    I --\u003e K[Create Response Synthesizer Agent]\n    \n    J --\u003e L[Add Tools to Retriever Agent]\n    L --\u003e L1[PDF Search Tool]\n    L --\u003e L2[Web Search Tool]\n    \n    K --\u003e M[Configure Response Agent]\n    \n    J \u0026 K --\u003e N[Create Tasks]\n    N --\u003e N1[Retrieval Task]\n    N --\u003e N2[Response Task]\n    \n    N --\u003e O[User Enters Query]\n    \n    O --\u003e P[Process Query]\n    P --\u003e Q[Show User Message]\n    Q --\u003e R[Crew Kickoff]\n    \n    R --\u003e S[Sequential Processing]\n    S --\u003e T1[Retriever Agent Searches]\n    T1 --\u003e T2[Response Agent Synthesizes]\n    \n    T2 --\u003e U[Stream Response]\n    U --\u003e V[Update Chat History]\n    \n    V --\u003e W[Wait for Next Query]\n    W --\u003e O\n```\n\n## 🚀 Prerequisites\n\nBefore running the application, ensure you have:\n\n1. **API Keys**:\n   - FireCrawl API or SEPER API key for web search capabilities\n   - LLM API key (if required for your chosen model)\n\n2. **Python Environment**:\n   - Python 3.11 or later\n   - Conda (recommended for environment management)\n\n## 💻 Installation\n\n1. **Create and Activate Environment**:\n   ```bash\n   conda create -n env_crewai python==3.12 -y\n   conda activate env_crewai\n   ```\n\n2. **Install Dependencies**:\n   ```bash\n   # Install package management tools\n   uv lock\n   uv sync\n\n   # Install required packages\n   pip install crewai crewai-tools markitdown qdrant-client fastembed\n   ```\n\n## 🎮 Running the Application\n\nChoose your preferred LLM model:\n\n- **For deep-seek-r1**:\n  ```bash\n  streamlit run app_deep_seek.py\n  ```\n\n- **For llama 3.2**:\n  ```bash\n  streamlit run app_llama3.2.py\n  ```\n\n## 🛠️ System Architecture\n\nThe system consists of two main agents:\n\n1. **Retriever Agent**:\n   - Handles document searching\n   - Manages web search fallback\n   - Uses both PDF and web search tools\n\n2. **Response Synthesizer Agent**:\n   - Processes retrieved information\n   - Generates coherent responses\n   - Ensures context relevance\n\n## 📚 Usage Examples\n\n1. **Document Search**:\n   - Upload your PDF document\n   - Enter your query\n   - Receive contextual answers from the document\n\n2. **Web Search Fallback**:\n   - System automatically detects when document search isn't sufficient\n   - Seamlessly switches to web search\n   - Combines information from multiple sources\n\n## 🤝 Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/AmazingFeature`)\n3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)\n4. Push to the branch (`git push origin feature/AmazingFeature`)\n5. Open a Pull Request\n\n## 📝 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🙏 Acknowledgments\n\n- [CrewAI](https://github.com/joaomdmoura/crewai) for the amazing framework\n- The open-source community for various tools and libraries used in this project\n\n---\n\n\u003cdiv align=\"center\"\u003e\nMade with ❤️ by Rahul Samant\n\u003c/div\u003e\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frahulsamant37%2Fagentic_rag_crewai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frahulsamant37%2Fagentic_rag_crewai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frahulsamant37%2Fagentic_rag_crewai/lists"}