# AI use cases for We Knora (Tencent/WeKnora)

Repo: [Tencent/WeKnora](https://github.com/Tencent/WeKnora) | Use cases: 3 | Page: https://dedupedai.com/use-cases/tencent-weknora/

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.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Run a private RAG knowledge base for your team's documents: https://dedupedai.com/use-cases/tencent-weknora/run-a-private-team-knowledge-base/
- Keep everything local with Ollama models: https://dedupedai.com/use-cases/tencent-weknora/use-local-ollama-models-with-weknora/
- Add a knowledge graph, object storage and tracing: https://dedupedai.com/use-cases/tencent-weknora/add-a-knowledge-graph-and-tracing/

## How to run a private RAG knowledge base for your team's documents with We Knora

Repo: [Tencent/WeKnora](https://github.com/Tencent/WeKnora) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Start the Docker Compose stack, upload documents and ask questions with citations.

**Who it is for:** A team lead who wants searchable answers over internal docs without sending them to a SaaS tool.

**The problem:** Team knowledge is scattered across files and wikis and hard to search.

**The outcome:** A web UI at http://localhost where questions are answered from your documents with source citations.

### Steps

1. Run `git clone https://github.com/Tencent/WeKnora.git` and `cd WeKnora`
2. Run `cp .env.example .env` and edit it
3. Run `docker compose pull` then `docker compose up -d`
4. Open http://localhost, create a knowledge base and upload documents

### Prompt to paste into your agent

```text
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.

Risk, credentials: The README strongly recommends an internal network, firewall rules and access controls rather than exposing it to the public internet.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/tencent-weknora/run-a-private-team-knowledge-base/

## How to keep everything local with Ollama models with We Knora

Repo: [Tencent/WeKnora](https://github.com/Tencent/WeKnora) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Run Ollama first and point We Knora's configuration at it.

**Who it is for:** A team that cannot send documents to a hosted model.

**The problem:** Hosted LLMs mean documents leave your environment.

**The outcome:** We Knora answering from your documents using a local Ollama model.

### Steps

1. Run `ollama serve > /dev/null 2>&1 &` first
2. Set the Ollama embedding model name and OLLAMA_BASE_URL as the Configuration docs describe
3. Start the stack with `docker compose up -d`
4. Pick the Ollama model in the model settings

### Prompt to paste into your agent

```text
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.
```

### Caveat

See the Configuration docs for RAM notes on local models.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/tencent-weknora/use-local-ollama-models-with-weknora/

## How to add a knowledge graph, object storage and tracing with We Knora

Repo: [Tencent/WeKnora](https://github.com/Tencent/WeKnora) | Difficulty: Intermediate | Time: 20 minutes | Basis: From the README

Turn on optional services with compose profiles.

**Who it is for:** An engineer who wants graph-based retrieval and visibility into each request.

**The problem:** The core stack has no graph store or tracing out of the box.

**The outcome:** Neo4j, MinIO or Langfuse running beside We Knora, with tracing at http://localhost:3000.

### Steps

1. Choose profiles: neo4j for the Knowledge Graph, minio for Object Storage, langfuse for Tracing, or full
2. Run `docker compose --profile neo4j --profile minio pull`
3. Run `docker compose --profile neo4j --profile minio up -d`
4. Run `docker compose down` to stop services

### Prompt to paste into your agent

```text
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.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/tencent-weknora/add-a-knowledge-graph-and-tracing/
