What do you want to do?
3 use cases
-
Run a private RAG knowledge base for your team's documents
Start the Docker Compose stack, upload documents and ask questions with citations.
- REPO
Tencent/WeKnora - Research
- Beginner
View prompt
Deploy Tencent/WeKnora with Docker Compose (`docker compose pull` then `docker compose up -d`), create a knowledge base from <folder>, and ask it <question> showing the cited passages.
- REPO
-
Keep everything local with Ollama models
Run Ollama first and point We Knora's configuration at it.
- REPO
Tencent/WeKnora - Research
- Intermediate
View prompt
Configure WeKnora to use my local Ollama for chat and embeddings (OLLAMA_BASE_URL=<url>), restart with `docker compose up -d`, and confirm a test question works offline.
- REPO
-
Add a knowledge graph, object storage and tracing
Turn on optional services with compose profiles.
- REPO
Tencent/WeKnora - Research
- Intermediate
View prompt
Enable WeKnora's neo4j and minio profiles with `docker compose --profile neo4j --profile minio up -d` and check that the Knowledge Graph works on one knowledge base.
- REPO
Quick start with We Knora
- Check you have what it needs: Docker with Docker Compose; An LLM provider key, or a local Ollama model; Optional Neo4j, MinIO or Langfuse via compose profiles.
- Open Tencent/WeKnora on GitHub and read the README and license.
- Run
git clone https://github.com/Tencent/WeKnora.gitandcd WeKnora - Run
cp .env.example .envand edit it - Run
docker compose pullthendocker compose up -d - Open http://localhost, create a knowledge base and upload documents
These steps come from our top use case, Run a private RAG knowledge base for your team's documents, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for Tencent/WeKnora
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forTeams that want a self-hosted knowledge base their people and agents can query.
- Why it is hot37k stars, talked about in 2 AI sources we track
- LanguageGo
- Sourcegithub.com/Tencent/WeKnora ยท Back to Hot repos
Requirements
- Docker with Docker Compose
- An LLM provider key, or a local Ollama model
- Optional Neo4j, MinIO or Langfuse via compose profiles
Add this badge to your README
Maintain We Knora? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/tencent-weknora/?utm_source=github&utm_medium=badge&utm_campaign=Tencent-WeKnora)
HTML
<a href="https://dedupedai.com/use-cases/tencent-weknora/?utm_source=github&utm_medium=badge&utm_campaign=Tencent-WeKnora"><img src="https://dedupedai.com/badge/Tencent/WeKnora.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about We Knora
What is We Knora?
WeKnora is an open-source, LLM-powered knowledge framework for document understanding, semantic retrieval and reasoning. It brings a team's documents into knowledge bases you can use through RAG, an agent for multi-step tasks, and a wiki, with auto-sync from sources such as Notion and Confluence, 10+ document formats, 29 built-in model vendors including Ollama, and a built-in MCP server. It deploys locally or on a private cloud. It is an open-source project on GitHub: https://github.com/Tencent/WeKnora.
How do I use We Knora?
Run git clone https://github.com/Tencent/WeKnora.git and cd WeKnora; then run cp .env.example .env and edit it; run docker compose pull then docker compose up -d. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is We Knora for?
Teams that want a self-hosted knowledge base their people and agents can query.
What can I do with We Knora?
3 use cases so far, for example: Run a private RAG knowledge base for your team's documents; Keep everything local with Ollama models; Add a knowledge graph, object storage and tracing. Each has steps and a copy-paste agent prompt.
What do I need to run We Knora?
Docker with Docker Compose; An LLM provider key, or a local Ollama model; Optional Neo4j, MinIO or Langfuse via compose profiles.
What are alternatives to We Knora?
Other hot AI repos in Research: Deep Tutor, Local Deep Research, Project Nomad, Nanochat, OpenMAIC.
Is We Knora safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.