Who it is forAn engineer who wants graph-based retrieval and visibility into each request.
The problemThe core stack has no graph store or tracing out of the box.
The outcomeNeo4j, MinIO or Langfuse running beside We Knora, with tracing at http://localhost:3000.
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
- Choose profiles: neo4j for the Knowledge Graph, minio for Object Storage, langfuse for Tracing, or full
- Run
docker compose --profile neo4j --profile minio pull - Run
docker compose --profile neo4j --profile minio up -d - Run
docker compose downto stop services
Prompt for your agent
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.
Caveat. `docker compose up -d` alone reuses cached images; pull first when upgrading.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for Tencent/WeKnora and "Add a knowledge graph, object storage and tracing"
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