{"id":30131083,"url":"https://github.com/jokerdii/rag-streamlit-app","last_synced_at":"2026-04-16T05:01:34.313Z","repository":{"id":309115926,"uuid":"1035216100","full_name":"JoKerDii/rag-streamlit-app","owner":"JoKerDii","description":"Implemented Simple RAG, GraphRAG (Neo4j), AdaptiveRAG (LangGraph), RAG with Reranking (Cohere) in Streamlit app for information summarization","archived":false,"fork":false,"pushed_at":"2025-08-09T23:27:44.000Z","size":991,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-10T00:21:16.883Z","etag":null,"topics":["cohere","knowledge-graph","langgraph","neo4j","rag-chatbot","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/JoKerDii.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,"zenodo":null}},"created_at":"2025-08-09T22:47:55.000Z","updated_at":"2025-08-09T23:49:39.000Z","dependencies_parsed_at":"2025-08-10T00:32:15.910Z","dependency_job_id":null,"html_url":"https://github.com/JoKerDii/rag-streamlit-app","commit_stats":null,"previous_names":["jokerdii/rag-streamlit-app"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/JoKerDii/rag-streamlit-app","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoKerDii%2Frag-streamlit-app","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoKerDii%2Frag-streamlit-app/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoKerDii%2Frag-streamlit-app/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoKerDii%2Frag-streamlit-app/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JoKerDii","download_url":"https://codeload.github.com/JoKerDii/rag-streamlit-app/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoKerDii%2Frag-streamlit-app/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269772015,"owners_count":24473337,"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":"2025-08-10T02:00:08.965Z","response_time":71,"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":["cohere","knowledge-graph","langgraph","neo4j","rag-chatbot","streamlit"],"created_at":"2025-08-10T19:00:27.134Z","updated_at":"2026-04-16T05:01:29.268Z","avatar_url":"https://github.com/JoKerDii.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RAG Application\n\nThis project is a Streamlit application that showcases and compares different Retrieval-Augmented Generation (RAG) techniques for building an interactive chatbot that can answer questions based on your uploaded documents. \n\n-----\n\n### Features\n\n  * **Simple RAG**: A foundational RAG implementation using a simple vector store (**FAISS**) for document retrieval. It's a great starting point to understand the RAG workflow.\n  * **RAG with Neo4j**: An advanced approach that leverages a **Neo4j knowledge graph** to enhance document retrieval. It uses a hybrid search to combine the power of vector embeddings with structured graph data.\n  * **Adaptive RAG**: A sophisticated strategy powered by **Langgraph** that dynamically analyzes user queries to determine the optimal retrieval path, offering a more intelligent and flexible RAG pipeline.\n  * **RAG with Reranking**: Improves the quality of retrieved documents by using a **Cohere Rerank** model to reorder search results, ensuring the most relevant information is presented to the LLM for a more accurate response.\n\n---\n\n### Demo\n\n![demo](./demo.png)\n\n-----\n\n### Technologies Used\n\n  * **Streamlit**: For building the interactive web application user interface.\n  * **LangChain**: The framework for orchestrating the RAG pipelines, handling document loading, splitting, and conversational chains.\n  * **FAISS**: An efficient library for vector similarity search, used as the primary vector store.\n  * **Groq**: The LLM provider (**Llama3-70b-8192**) used for generating responses.\n  * **Neo4j**: An open-source graph database for the knowledge graph implementation.\n  * **HuggingFace Embeddings**: For converting text into dense vector representations.\n  * **Cohere Rerank**: A powerful reranking model to improve the relevance of retrieved documents.\n\n-----\n\n### Prerequisites\n\n  * **Python 3.8+**: The project is built with Python.\n  * **Neo4j Desktop or Server**: Required for the \"RAG with Neo4j\" feature. You must also install the **APOC plugin** and enable `apoc.*` procedures in `neo4j.conf`.\n  * **API Keys**: You will need API keys for Groq and Cohere.\n\n-----\n\n### Setup and Installation\n\n1.  **Clone the repository**:\n\n    ```bash\n    git clone \u003crepository-url\u003e\n    cd \u003crepository-name\u003e\n    ```\n\n2.  **Create a virtual environment**:\n\n    ```bash\n    python -m venv venv\n    source venv/bin/activate  # On Windows, use `venv\\Scripts\\activate`\n    ```\n\n3.  **Install dependencies**:\n\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n    *(Note: You will need to create a `requirements.txt` file by listing all the imported libraries in the code.)*\n\n4.  **Configure API Keys**:\n    Create a `.env` file in the root directory and add your API keys:\n\n    ```\n    GROQ_API_KEY=\"your_groq_api_key\"\n    COHERE_API_KEY=\"your_cohere_api_key\"\n    ```\n\n5.  **Neo4j Setup (Optional)**:\n    If you plan to use the Neo4j feature, ensure your Neo4j database is running and accessible with the correct credentials. The application assumes the default bolt URI (`bolt://localhost:7687`) and `neo4j` as the username. You can modify this in the code if needed.\n\n-----\n\n### Usage\n\nTo run the application, simply execute the following command from the project's root directory:\n\n```bash\nstreamlit run main.py\n```\n\nThis will launch the Streamlit application in your web browser. You can then navigate between the different RAG modes using the sidebar.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjokerdii%2Frag-streamlit-app","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjokerdii%2Frag-streamlit-app","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjokerdii%2Frag-streamlit-app/lists"}