Practical overview
When it fits
Use ToK when you want a self-hosted document-chat workflow and are prepared to run its local model and application dependencies.
Who it is for
- People who want to ask questions about their own documents in a locally run app.
- Users building or exploring personal or team document knowledge bases.
- Developers interested in an open-source RAG application using Ollama and Neo4j.
Documented uses
- Upload text documents or folders and create an index for later queries.
- Ask questions that use uploaded material as context.
- Save, revisit and continue earlier conversations.
- Adjust chunking, context-window, temperature and chat-mode settings, or customize prompts.
Requirements & limits
The project is available as a public GitHub repository under an Apache-2.0 license. Its README recommends Docker Compose; the standalone executable is marked deprecated and no longer maintained.
- Ollama is a required dependency for running ToK.
- Docker and Docker Compose are prerequisites for the README's recommended setup.
- Neo4j Desktop is specified for non-Docker use, the deprecated executable route, or research purposes.
- The README notes a brief delay and temporary sidebar/chat issue when creating a new conversation immediately after prompting.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up ToK with Docker Compose
Start the documented Docker-based ToK application with Ollama available locally.
Before you start
- Docker and Docker Compose
- Ollama installed and serving models locally
- A cloned copy of the ToK repository
Steps
Clone the ToK repository.
Change to the ToK/docker directory.
Run ollama serve on the local system; the README says the app may serve it automatically.
Run docker-compose up -d.
Expected outcome
The Docker Compose application is started for local use.
Guide limitations
- The README gives no further run-time troubleshooting or model-selection steps in this setup sequence.
Ask questions about uploaded documents
Use ToK to query documents after setup is complete.
Before you start
- A running ToK installation
- Text documents or folders to upload, if querying personal material
Steps
Launch ToK.
Choose to chat directly or upload documents using the top-right upload button.
Ask a question in the chat; uploaded documents can provide context for the response.
Expected outcome
ToK provides a chat response, with uploaded material available to inform document questions.
Guide limitations
- The README notes that a new chat created immediately after prompting may be temporarily missing from the sidebar, with chat unavailable for a few seconds.
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 |
|---|---|---|---|
| Trove of Knowledge (ToK) | Upload text documents or folders and create an index for later queries. | Docker, Self-hosted, Web | The project is available as a public GitHub repository under an Apache-2.0 license. Its README recommends Docker Compose; the standalone executable is marked deprecated and no longer maintained. |
| 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
- 17 October 2026
- Original website title
- gurveervirk/ToK · Official homepage title · retained in its source language