Credentials. The README strongly recommends an internal network, firewall rules and access controls rather than exposing it to the public internet.
Who it is forA team lead who wants searchable answers over internal docs without sending them to a SaaS tool.
The problemTeam knowledge is scattered across files and wikis and hard to search.
The outcomeA web UI at http://localhost where questions are answered from your documents with source citations.
What you need first
- Docker with Docker Compose
- An LLM provider key, or a local Ollama model
- Optional Neo4j, MinIO or Langfuse via compose profiles
Steps
- 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
Prompt for your agent
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.
Caveat. This card is written from the Tencent/WeKnora README, not from a test run by Deduped. Before you start, make sure you have Docker with Docker Compose. Check the repo for newer instructions before you rely on these steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for Tencent/WeKnora and "Run a private RAG knowledge base for your team's documents"
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 freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer