Practical overview
When it fits
Use the main branch when you want a locally run notebook that links personal notes and documents through a knowledge graph. Choose base-rag when your task is specifically to study or adapt the separate vector-RAG document-question-answering service.
Who it is for
- Individuals organizing personal notes and document collections.
- Developers or learners exploring RAG and knowledge-graph application patterns.
- People who want AI-assisted retrieval, note discovery, or writing tools connected to their own knowledge base.
Documented uses
- Create, edit, categorize, search, and export Markdown notes.
- Upload TXT, PDF, Markdown, PPTX, and DOCX files for knowledge-base retrieval.
- Ask questions across notes and documents using graph-guided retrieval and receive source references.
- Browse connections between entities and notes in a visual knowledge graph.
- Use AI completion, continuation, expansion, and summarization while writing.
Requirements & limits
The repository is public and declares an MIT license. The documented application is run locally using Docker or a local-development setup; no hosted service is described.
- Main and base-rag branches serve different purposes: graph-based knowledge management versus vector-RAG document dialogue.
- AI functions require a configured model endpoint and key; the README describes OpenAI-compatible services and gives provider examples.
- The Docker quick start bundles services, while local development requires the listed language runtimes and database services.
- The main branch uses Neo4j for graph and retrieval data and MySQL for persistent records; Redis is also included in the stack.
- The README states that user-level knowledge-base isolation restricts RAG retrieval to the user's own data.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Start Ragnotebook with Docker
Prepare the documented Docker-based startup configuration for the main application.
Before you start
- Docker Desktop installed and its engine running; at least 4 GB of memory is recommended.
- A model key and values for OPENAI_BASE_URL, OPENAI_API_KEY, and OPENAI_MODEL_NAME.
Steps
Clone the RAGNotebook repository and change into its directory.
On Linux or macOS, copy backend/.env.example to backend/.env and fill in the required model settings.
Run docker compose up -d --build. On Windows, the README instead documents running the root start.bat file.
Expected outcome
The README lists the frontend at http://localhost:3000 and API documentation at http://localhost:8000/docs after startup.
Guide limitations
- The model key is required for AI functions such as question answering; the service may start and allow browsing without it.
- The README says the first Docker build takes about 10 minutes; this is an estimate, not a measured result.
Compare options for Retrieval-augmented applications
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Ragnotebook | Create, edit, categorize, search, and export Markdown notes. | Server, Web | The repository is public and declares an MIT license. The documented application is run locally using Docker or a local-development setup; no hosted service is described. |
| Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And Pdfs | Retrieve relevant passages from web and PDF content to answer a question. | Web | |
| LangChain in Supabase Edge Functions | Initialize and start a Supabase project locally. | Cloud, Server |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 9 October 2026
- Original website title
- RMA-MUN/RAGNotebook · Official homepage title · retained in its source language