VaultRAG
An out-of-the-box enterprise-grade full-stack RAG scaffold integrating Ollama local LLM execution, a FastAPI backend, LangChain orchestration, a React frontend and Docker Compose deployment, supporting fully offline private deployment.
Timeline (last 90 days)
VaultRAG is an open-source enterprise-grade RAG scaffold, designed to let developers deploy a full-stack RAG application that is fully offline and keeps data within the internal network out of the box, created and open-sourced by developer toprakkbozbeyy.
VaultRAG's tech stack is: LLM and embedding models run locally via Ollama (using Llama 3.1, Qwen and nomic-embed-text), the backend uses Python and FastAPI, RAG orchestration uses LangChain, the frontend uses React with Tailwind CSS, and deployment is managed by Docker Compose.
VaultRAG's document ingestion flow is: the user uploads a PDF in the React interface, FastAPI receives the file, LangChain splits text chunks using RecursiveCharacterTextSplitter, then embedding vectors are generated via Ollama and stored in the local vector store.
In VaultRAG's retrieval and generation flow, the backend first retrieves the most relevant text chunks and assembles them into a prompt, then streams the response back from the local LLM via Server-Sent Events (SSE).
VaultRAG is positioned as a scaffold rather than a finished product, suitable for three types of users: freelance developers building AI tools for clients, teams participating in hackathons that need to quickly build prototypes, and individual users who want to deploy private AI for their own privacy documents.
Some of VaultRAG's components and documentation are already open-sourced on GitHub, at github.com/toprakkbozbeyy/vaultrag-enterprise-starter-kit.
All Facts (6)
VaultRAG is an open-source enterprise-grade RAG scaffold, designed to let developers deploy a full-stack RAG application that is fully offline and keeps data within the internal network out of the box, created and open-sourced by developer toprakkbozbeyy.
50%UnverifiedVaultRAG's tech stack is: LLM and embedding models run locally via Ollama (using Llama 3.1, Qwen and nomic-embed-text), the backend uses Python and FastAPI, RAG orchestration uses LangChain, the frontend uses React with Tailwind CSS, and deployment is managed by Docker Compose.
50%UnverifiedVaultRAG's document ingestion flow is: the user uploads a PDF in the React interface, FastAPI receives the file, LangChain splits text chunks using RecursiveCharacterTextSplitter, then embedding vectors are generated via Ollama and stored in the local vector store.
50%UnverifiedIn VaultRAG's retrieval and generation flow, the backend first retrieves the most relevant text chunks and assembles them into a prompt, then streams the response back from the local LLM via Server-Sent Events (SSE).
50%UnverifiedVaultRAG is positioned as a scaffold rather than a finished product, suitable for three types of users: freelance developers building AI tools for clients, teams participating in hackathons that need to quickly build prototypes, and individual users who want to deploy private AI for their own privacy documents.
50%UnverifiedSome of VaultRAG's components and documentation are already open-sourced on GitHub, at github.com/toprakkbozbeyy/vaultrag-enterprise-starter-kit.
50%