{"id":29873144,"url":"https://github.com/garvitjain-02/modular-rag-chatbot","last_synced_at":"2026-04-10T13:31:43.384Z","repository":{"id":298645173,"uuid":"1000632431","full_name":"garvitjain-02/Modular-RAG-Chatbot","owner":"garvitjain-02","description":"A Modular Retrieval-Augmented Generation (RAG) application that allows users to upload PDF documents and chat with an AI assistant that answers queries based on the document content. It features a microservice architecture with a decoupled FastAPI backend and Streamlit frontend, using ChromaDB as the vector store and Groq's LLaMA3 model as the LLM.","archived":false,"fork":false,"pushed_at":"2025-08-05T04:49:25.000Z","size":6672,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-05T06:28:34.194Z","etag":null,"topics":["chromadb","fastapi","generative-ai","groq","langchain","llama3","llm","python","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/garvitjain-02.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":"2025-06-12T05:00:43.000Z","updated_at":"2025-08-05T04:49:29.000Z","dependencies_parsed_at":"2025-06-12T06:21:00.463Z","dependency_job_id":"8df061af-b6ca-4c76-9d15-6f4b7b07b6c2","html_url":"https://github.com/garvitjain-02/Modular-RAG-Chatbot","commit_stats":null,"previous_names":["garvitjain-02/question-your-pdf-rag","garvitjain-02/modular-rag-chatbot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/garvitjain-02/Modular-RAG-Chatbot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garvitjain-02%2FModular-RAG-Chatbot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garvitjain-02%2FModular-RAG-Chatbot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garvitjain-02%2FModular-RAG-Chatbot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garvitjain-02%2FModular-RAG-Chatbot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/garvitjain-02","download_url":"https://codeload.github.com/garvitjain-02/Modular-RAG-Chatbot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garvitjain-02%2FModular-RAG-Chatbot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279001300,"owners_count":26083058,"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":"2025-10-09T02:00:07.460Z","response_time":59,"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":["chromadb","fastapi","generative-ai","groq","langchain","llama3","llm","python","rag-chatbot","streamlit"],"created_at":"2025-07-30T22:16:05.650Z","updated_at":"2025-10-09T11:32:02.049Z","avatar_url":"https://github.com/garvitjain-02.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Modular RAG PDF Chatbot with FastAPI, ChromaDB \u0026 Streamlit\n\nThis project is a modular **Retrieval-Augmented Generation (RAG)** application that allows users to upload PDF documents and chat with an AI assistant that answers queries based on the document content. It features a microservice architecture with a decoupled **FastAPI backend** and **Streamlit frontend**, using **ChromaDB** as the vector store and **Groq's LLaMA3 model** as the LLM.\n\n---\n\n## 📂 Project Structure\n\n```\nragbot2.0/\n├── client/         # Streamlit Frontend\n│   |──components/\n|   |  |──chatUI.py\n|   |  |──history_download.py\n|   |  |──upload.py\n|   |──utils/\n|   |  |──api.py\n|   |──app.py\n|   |──config.py\n├── server/         # FastAPI Backend\n│   ├── chroma_store/ ....after run\n|   |──modules/\n│      ├── load_vectorestore.py\n│      ├── llm.py\n│      ├── pdf_handler.py\n│      ├── query_handlers.py\n|   |──uploaded_pdfs/ ....after run\n│   ├── logger.py\n│   └── main.py\n└── README.md\n```\n\n---\n\n## ✨ Features\n\n- 📄 Upload and parse PDFs\n- 🧠 Embed document chunks with HuggingFace embeddings\n- 💂️ Store embeddings in ChromaDB\n- 💬 Query documents using LLaMA3 via Groq\n- 🌍 Microservice architecture (Streamlit client + FastAPI server)\n\n---\n\n## 🎓 How RAG Works\n\nRetrieval-Augmented Generation (RAG) enhances LLMs by injecting external knowledge. Instead of relying solely on pre-trained data, the model retrieves relevant information from a vector database (like ChromaDB) and uses it to generate accurate, context-aware responses.\n\n---\n\n## 🚀 Getting Started Locally\n\n### 1. Clone the Repository\n\n```bash\ngit clone https://github.com/garvitjain-02/Modular-RAG-Chatbot.git\ncd Modular-RAG-Chatbot\n```\n\n### 2. Setup the Backend (FastAPI)\n\n```bash\ncd server\npython -m venv venv\nsource venv/bin/activate  # Windows: venv\\Scripts\\activate\npip install -r requirements.txt\n\n# Set your Groq API Key (.env)\nGROQ_API_KEY=\"your_key_here\"\n\n# Run the FastAPI server\nuvicorn main:app --reload\n```\n\n### 3. Setup the Frontend (Streamlit)\n\n```bash\ncd ../client\npip install -r requirements.txt  # if you use a separate venv for client\nstreamlit run app.py\n```\n\n---\n\n## 🌐 API Endpoints (FastAPI)\n\n- `POST /upload_pdfs/` — Upload PDFs and build vectorstore\n- `POST /ask/` — Send a query and receive answers\n\nTestable via Postman or directly from the Streamlit frontend.\n\n---\n\n## 🌟 References\n\n- [LangChain](https://www.langchain.com/)\n- [ChromaDB](https://www.trychroma.com/)\n- [Groq](https://groq.com/)\n- [Streamlit](https://streamlit.io/)\n\n---\n\n## ✉️ Contact\n\nFor questions or suggestions, open an issue or contact at [garvitjainjnv@gmail.com]\n\n---\n\n\u003e Happy Building! 🚀","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgarvitjain-02%2Fmodular-rag-chatbot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgarvitjain-02%2Fmodular-rag-chatbot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgarvitjain-02%2Fmodular-rag-chatbot/lists"}