{"id":27172787,"url":"https://github.com/sushant1827/agentic-rag-deepseek","last_synced_at":"2026-05-08T03:47:36.409Z","repository":{"id":286504635,"uuid":"954116067","full_name":"sushant1827/Agentic-RAG-DeepSeek","owner":"sushant1827","description":"Project demonstrates an agentic Retrieval-Augmented Generation (RAG) application built using CrewAI and Streamlit.","archived":false,"fork":false,"pushed_at":"2025-03-24T15:32:17.000Z","size":6,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-02T04:45:02.670Z","etag":null,"topics":["agentic-rag","chatbot","crewai","deepseek-r1","local-llm","multi-agent-systems","ollama","retrieval-augmented-generation","serperapi","streamlit"],"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/sushant1827.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":"2025-03-24T15:29:46.000Z","updated_at":"2025-03-24T15:35:30.000Z","dependencies_parsed_at":"2025-04-06T22:13:18.501Z","dependency_job_id":"ce72fc0a-bbe7-435d-b163-0cefaa70d85a","html_url":"https://github.com/sushant1827/Agentic-RAG-DeepSeek","commit_stats":null,"previous_names":["sushant1827/agentic-rag-deepseek"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sushant1827/Agentic-RAG-DeepSeek","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FAgentic-RAG-DeepSeek","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FAgentic-RAG-DeepSeek/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FAgentic-RAG-DeepSeek/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FAgentic-RAG-DeepSeek/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sushant1827","download_url":"https://codeload.github.com/sushant1827/Agentic-RAG-DeepSeek/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sushant1827%2FAgentic-RAG-DeepSeek/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279014484,"owners_count":26085535,"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":"2025-10-13T02:00:06.723Z","response_time":61,"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","chatbot","crewai","deepseek-r1","local-llm","multi-agent-systems","ollama","retrieval-augmented-generation","serperapi","streamlit"],"created_at":"2025-04-09T10:30:16.379Z","updated_at":"2025-10-13T09:13:23.090Z","avatar_url":"https://github.com/sushant1827.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agentic RAG Application with CrewAI and Streamlit\n\nThis project demonstrates an agentic Retrieval-Augmented Generation (RAG) application built using CrewAI and Streamlit. It allows users to upload a PDF document and then ask questions about its content, leveraging the power of Large Language Models (LLMs) and intelligent agents.\n\n## Project Preview\n\n![image](https://github.com/user-attachments/assets/7a96ec1f-54ed-41df-9ad3-29f67cbcc2a1)\n\n## Features\n\n-   **PDF Document Upload:** Users can upload PDF files directly through the Streamlit interface.\n-   **PDF Indexing:** The application indexes the uploaded PDF, making its content searchable.\n-   **Agentic RAG:** Employs a CrewAI-powered crew of agents to handle information retrieval and response generation.\n-   **Web Search Fallback:** If information is not found in the PDF, the system intelligently falls back to web search using the Serper API.\n-   **Conversational Interface:** Provides a user-friendly chat interface for interacting with the system.\n-   **Clear Chat History:** Users can easily clear the chat history and start fresh.\n-   **Real-time Response:** The application displays the LLM's response in a streaming fashion, providing a more engaging user experience.\n- **Local LLM Support:** Uses Ollama to run a local LLM (deepseek-r1:14b)\n\n## How It Works\n\nThe application uses a crew of two agents:\n\n1.  **Retriever Agent:**\n    -   Responsible for retrieving relevant information based on the user's query.\n    -   Prioritizes searching the uploaded PDF.\n    -   Falls back to web search if the PDF doesn't contain the answer.\n    -   Uses `PDFSearchTool` and `SerperDevTool`.\n2.  **Response Agent:**\n    -   Synthesizes the retrieved information into a clear and concise response.\n    -   Handles cases where no relevant information is found.\n\nThese agents work together sequentially to provide accurate and helpful answers to user queries.\n\n## Technologies Used\n\n-   **CrewAI:** A framework for orchestrating multi-agent systems.\n-   **Streamlit:** A Python library for creating interactive web applications.\n-   **Ollama:** For running the local LLM.\n-   **Deepseek-r1:14b:** The specific LLM used in this project.\n-   **Serper API:** For web search capabilities.\n-   **PDFSearchTool:** A custom tool for searching PDF documents.\n-   **Python:** The primary programming language.\n-   **dotenv:** For managing environment variables.\n\n## Prerequisites\n\n-   **Python 3.8+**\n-   **Ollama:** You need to have Ollama installed and running locally.\n-   **Serper API Key:** You'll need a Serper API key for web search functionality.\n-   **Required Python Packages:**\n    ```bash\n    pip install streamlit crewai crewai-tools python-dotenv\n    ```\n\n## Installation and Setup\n\n1.  **Clone the Repository:**\n    ```bash\n    git clone \u003cyour-repository-url\u003e\n    cd \u003cyour-repository-directory\u003e\n    ```\n2.  **Install Dependencies:**\n    ```bash\n    pip install -r requirements.txt\n    ```\n    (You can create a `requirements.txt` file with the following content:\n    ```\n    streamlit\n    crewai\n    crewai-tools\n    python-dotenv\n    ```\n    )\n3.  **Set Environment Variables:**\n    -   Create a `.env` file in the project's root directory.\n    -   Add your Serper API key:\n        ```\n        SERPER_API_KEY=your_serper_api_key_here\n        ```\n4.  **Run Ollama:**\n    - Make sure you have Ollama installed and running.\n    - Pull the deepseek-r1:14b model:\n    ```bash\n    ollama pull deepseek-r1:14b\n    ```\n5.  **Run the Streamlit App:**\n    ```bash\n    streamlit run rag_app.py\n    ```\n\n## Usage\n\n1.  **Upload a PDF:** In the sidebar, use the file uploader to select and upload a PDF document.\n2.  **Wait for Indexing:** The application will index the PDF. This may take a few moments.\n3.  **Ask Questions:** In the chat interface, type your questions about the PDF content.\n4.  **View Responses:** The system will provide answers based on the PDF content or, if necessary, from the web.\n5. **Clear Chat:** Use the \"Clear Chat\" button in the sidebar to reset the conversation.\n\n---\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsushant1827%2Fagentic-rag-deepseek","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsushant1827%2Fagentic-rag-deepseek","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsushant1827%2Fagentic-rag-deepseek/lists"}